CN117560650A

CN117560650A - Network mobility management optimization method, base station, device, system and related equipment

Info

Publication number: CN117560650A
Application number: CN202210923982.6A
Authority: CN
Inventors: 张化; 许森; 熊尚坤; 信金灿
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2022-08-02
Filing date: 2022-08-02
Publication date: 2024-02-13

Abstract

The disclosure provides a network mobility management optimization method, a base station, a device, a system and related equipment, and relates to the technical field of mobile communication. The method comprises the following steps: the anchor base station and the auxiliary base station respectively send the IP address and the port address of the anchor base station and the auxiliary base station to the other party through a model reasoning request message and a model reasoning reply, and then a data channel for transmitting related data of the AL/ML model is established between the anchor base station and the auxiliary base station; after the anchor base station utilizes the trained network mobility management optimization model to infer and output network mobility management optimization decision information, the anchor base station sends the network mobility management optimization decision information to the auxiliary base station through the established data channel, and finally the anchor base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information, and the auxiliary base station executes network load balancing operation according to the network mobility management optimization decision information. The method and the device output the network mobility management optimization decision information based on the trained AL/M model, and can improve the network service quality.

Description

Network mobility management optimization method, base station, device, system and related equipment

Technical Field

The disclosure relates to the technical field of mobile communication, and in particular relates to a network mobility management optimization method, a base station, a device, a system and related equipment.

Background

In the future, a network will adopt a higher wireless frequency to meet the requirement of a large bandwidth, with the reduction of the coverage area of a single base station node, the switching frequency of a terminal between base stations will become higher, especially for a high mobility terminal, the success rate of switching and the network performance after switching are ensured, the key work of an operator for improving the service quality of the operator is ensured, and the management and optimization of mobility are necessary measures for ensuring the normal and safe operation of a mobile communication network.

The reasons for the problems related to the mobility performance are various, for example, the mobility interruption time of the delay sensitive service is too long, the cell edge coverage is poor, the success rate of the handover is low, the handover fails due to insufficient handover resources, and the problems of early/late/ping-pong handover caused by improper handover parameters are solved. There are different switching mechanisms for different problems. The dual active protocol stack (DuAI Active Protocol Stack, DAPS) can reduce service interruption time during handoff, conditional handoff (ConditionAI Handover, CHO) can improve handoff robustness, random access channel (Random Access Channel, RACH) handoff can reduce handoff delay, and so forth. Mobile robustness optimization (Mobility Robustness Optimization, MRO) is an important component of network self-optimization, and is mainly used for solving the situations of handover failure, radio link failure, ping-pong handover, etc. caused by unreasonable network parameter setting.

The traditional mobility management scheme based on the trial-and-error method is difficult to realize zero-failure switching, and the mode of adjusting mobility based on feedback cannot improve the robustness of switching along with the randomness and the instability of a transmission environment, so that the time delay requirement is met.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The disclosure provides a network mobility management optimization method, a base station, a device, a system and related equipment, which at least overcome the technical problems of low switching success, poor switching robustness and high switching delay of a mobility management scheme based on a trial-and-error method in the related technology to a certain extent.

Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.

According to one aspect of the present disclosure, there is provided a network mobility management method applied to an anchor base station, the method comprising: the method comprises the steps of sending a model reasoning request message to an auxiliary base station, wherein the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information; receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries an IP address and a port address of the auxiliary base station; establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by the model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by the model reasoning.

According to another aspect of the present disclosure, there is also provided a network mobility management optimization method applied to a secondary base station, the method including: receiving a model reasoning request message from an anchor base station, wherein the model reasoning request message carries an IP address and a port address of the anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information; returning a model reasoning reply message to the anchor base station, wherein the model reasoning reply message carries the IP address and the port address of the auxiliary base station; establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the network mobility management optimization decision information sent by the anchor base station is received through a data channel established between the anchor base station and the auxiliary base station, the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by model reasoning.

According to another aspect of the present disclosure, there is also provided a network mobility management optimization method applied to an OAM entity, the method including: determining a target area range for network mobility management optimization to be executed, wherein a plurality of base stations exist in the target area range; determining a first base station and a second base station according to the computing capability information and the energy storage capability information of each base station in the target area, wherein the first base station is an anchor point base station in the target area, and the second base station is any auxiliary base station in the target area; sending a model deployment/update message to the first base station and the second base station, wherein the model deployment/update message is used for indicating the first base station and the second base station to report measurement information serving as model training data; performing online training, verification and testing on an artificial intelligent AI/machine learning ML model according to model training data reported by the first base station and the second base station to obtain a network mobility management optimization model; deploying/updating the network mobility management optimization model to the first base station, so that the first base station inputs model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning; the second base station performs network load balancing operation according to network mobility management optimization decision information output by model reasoning, the inter-base station interface is a data channel which is established between the first base station and the second base station and used for transmitting AI/ML model related data according to the IP address and port address of the first base station and the IP address and port address of the second base station, the first base station sends the IP address and port address of the first base station to the second base station through a model reasoning request message, and the second base station sends the IP address and port address of the second base station to the first base station through a model reasoning reply message.

According to another aspect of the present disclosure, there is also provided a network management apparatus including: a mobility optimization area determining module, configured to determine a target area range in which network mobility management optimization is to be performed, where a plurality of base stations exist in the target area range; the anchor base station and auxiliary base station determining module is used for determining a first base station and a second base station according to the computing capability information and the energy storage capability information of each base station in the target area, wherein the first base station is the anchor base station in the target area, and the second base station is any auxiliary base station in the target area; a model deployment/update message issuing module, configured to send a model deployment/update message to the first base station and the second base station, where the model deployment/update message is used to instruct the first base station and the second base station to report measurement information as model training data; the model training module is used for carrying out online training, verification and test on the artificial intelligent AI/machine learning ML model according to the model training data reported by the first base station and the second base station to obtain a network mobility management optimization model; the model deployment module is used for deploying/updating the network mobility management optimization model to the first base station so that the first base station inputs model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligence AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model; the second base station performs network load balancing operation according to network mobility management optimization decision information output by model reasoning, the inter-base station interface is a data channel which is established between the first base station and the second base station and used for transmitting AI/ML model related data according to the IP address and port address of the first base station and the IP address and port address of the second base station, the first base station sends the IP address and port address of the first base station to the second base station through a model reasoning request message, and the second base station sends the IP address and port address of the second base station to the first base station through a model reasoning reply message.

According to another aspect of the present disclosure, there is also provided an anchor base station including: the system comprises a model reasoning request message sending module, a model reasoning request message sending module and a network mobility management optimization module, wherein the model reasoning request message is used for sending a model reasoning request message to an auxiliary base station, the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into the network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, and outputting network mobility management optimization decision information; the model reasoning reply message receiving module is used for receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries an IP address and a port address of the auxiliary base station; the inter-base station data channel establishing module is used for establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the mobility optimization module is used for sending network mobility management optimization decision information which is inferred and output by a model to the auxiliary base station through a data channel which is established between the anchor base station and the auxiliary base station, the anchor base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model, and the auxiliary base station is also used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model.

According to another aspect of the present disclosure, there is also provided a secondary base station including: the model reasoning request message receiving module is used for reporting historical measurement information serving as model training data to the anchor base station; the model reasoning reply message sending module is used for reporting current measurement information serving as model reasoning data to the anchor base station; the inter-base station data channel establishing module is used for establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the load balancing module is used for receiving the network mobility management optimization decision information sent by the anchor base station through the data channel established between the anchor base station and the auxiliary base station, the anchor base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model, and the auxiliary base station is also used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model.

According to another aspect of the present disclosure, there is also provided a network mobility management optimization system, the system comprising: an OAM entity and a plurality of base stations located within a target area; the OAM entity is used for determining a target area range of network mobility management optimization to be executed, determining a first base station and a second base station according to calculation capability information and storage capability information of each base station in the target area range, sending model deployment/update information to the first base station and the second base station to instruct the first base station and the second base station to report measurement information serving as model training data, and carrying out online training, verification and testing on an artificial intelligent AI/machine learning ML model according to the model training data reported by the first base station and the second base station to obtain a network mobility management optimization model, and deploying/updating the network mobility management optimization model to the first base station, wherein the first base station is an anchor base station in the target area range, and the second base station is any auxiliary base station in the target area range; the first base station is used for inputting model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputting network mobility management optimization decision information, and sending the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the inter-base station interface is a data channel which is established between the first base station and the second base station and is used for transmitting AI/ML model related data according to an IP address and a port address of the first base station and the IP address and the port address of the second base station, and the first base station sends the IP address and the port address of the first base station to the second base station through a model reasoning request message and sends the IP address and the port address of the second base station to the first base station through a model reasoning reply message; the second base station is used for executing network load balancing operation according to the network mobility management optimization decision information which is output by the model reasoning; the first base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning.

According to another aspect of the present disclosure, there is also provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the network mobility management optimization method of any one of the above via execution of the executable instructions.

According to another aspect of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the network mobility management optimization method of any one of the above.

According to another aspect of the present disclosure, there is also provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the network mobility management optimization method of any one of the above.

According to the network mobility management optimization method, the base station, the device, the system and the related equipment provided by the embodiment of the disclosure, after an OAM entity determines a target area range to be subjected to network mobility management optimization and an anchor base station and an auxiliary base station, an AI/ML model is trained, verified and tested on line according to model training data reported by the anchor base station and the auxiliary base station to obtain a network mobility management optimization model, and the anchor base station and the auxiliary base station send own IP address and port address to each other through model reasoning request information and model reasoning reply respectively so as to establish a data channel for transmitting model related data between the anchor base station and the auxiliary base station; after the anchor base station utilizes the trained network mobility management optimization model to infer and output network mobility management optimization decision information, the anchor base station sends the network mobility management optimization decision information to the auxiliary base station through the established data channel, and finally the anchor base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information inferred and output by the model, and the auxiliary base station executes network load balancing operation according to the network mobility management optimization decision information inferred and output by the model.

Through the embodiment of the disclosure, different mobile scenes and switching mechanisms can be classified and identified based on the AL/M model, and the optimal switching parameters, resource allocation or mobility strategy information can be output so as to improve the network service quality.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.

Fig. 1 illustrates a network mobility management system architecture diagram in an embodiment of the present disclosure;

FIG. 2 illustrates a general architecture diagram of an AI/ML-based wireless network in an embodiment of the disclosure;

fig. 3 is a flowchart illustrating a method for network mobility management method applied to an anchor base station in an embodiment of the present disclosure;

fig. 4 is a flowchart of a method for network mobility management applied to a secondary base station in an embodiment of the disclosure;

Fig. 5 is a flowchart illustrating a method of network mobility management method applied to an OAM entity in an embodiment of the present disclosure;

fig. 6 illustrates an interaction flow between a terminal, an anchor base station, a secondary base station, and an OAM entity in an embodiment of the present disclosure;

fig. 7 is a schematic diagram showing internal components of a network management device according to an embodiment of the present disclosure;

fig. 8 is a schematic diagram illustrating internal components of an anchor base station according to an embodiment of the present disclosure;

fig. 9 is a schematic diagram illustrating internal components of a secondary base station according to an embodiment of the disclosure;

FIG. 10 shows a block diagram of an electronic device in an embodiment of the disclosure;

fig. 11 shows a schematic diagram of a computer-readable storage medium in an embodiment of the disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.

For ease of understanding, before describing embodiments of the present disclosure, several terms referred to in the embodiments of the present disclosure are first explained as follows:

OAM: operation Administration and Maintenance, operation maintenance management;

AI: artificial Intelligence, artificial intelligence;

ML: machine Learning;

UE: user Equipment, also called User terminal, called terminal for short;

IE: information Element, information element.

The following detailed description of embodiments of the present disclosure refers to the accompanying drawings.

Fig. 1 shows a schematic diagram of a network mobility management system architecture in an embodiment of the disclosure. As shown in fig. 1, the system architecture may include a first base station 10 as an anchor base station, a second base station 20 as a secondary base station, and an operation, maintenance and administration OAM entity 30. Wherein a first base station 10 communicates with one or more terminals 40 within its coverage area and a second base station 20 communicates with one or more terminals 40 within its coverage area.

The medium providing the communication link between the terminal 40 and the base station (the first base station 10 or the second base station 20) may be a wireless network.

Alternatively, the wireless network or wired network described above uses standard communication techniques and/or protocols. The Network is typically the internet, but may be any Network including, but not limited to, a local Area Network (LocAI Area Network, LAN), metropolitan Area Network (Metropolitan Area Network, MAN), wide Area Network (WAN), mobile, wired or wireless Network, private Network, or any combination of virtual private networks. In some embodiments, data exchanged over a network is represented using techniques and/or formats including HyperText Mark-up Language (HTML), extensible markup Language (Extensible MarkupLanguage, XML), and the like. All or some of the links may also be encrypted using conventional encryption techniques such as secure sockets layer (Secure Socket Layer, SSL), transport layer security (Transport Layer Security, TLS), virtual private network (VirtuAI Private Network, VPN), internet protocol security (Internet ProtocolSecurity, IPsec), etc. In other embodiments, custom and/or dedicated data communication techniques may also be used in place of or in addition to the data communication techniques described above.

The terminal 40 may be a variety of electronic devices including, but not limited to, smartphones, tablets, laptop portable computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, and the like.

Alternatively, the clients of the applications installed in different terminals 40 are the same or clients of the same type of application based on different operating systems. The specific form of the application client may also be different based on the different terminal platforms, for example, the application client may be a mobile phone client, a PC client, etc.

The first base station 10 and the second base station 20 may be, but are not limited to, 5G and later versions of base stations (e.g., 5G NR NB), or base stations in other communication systems (e.g., eNB base station), and it should be noted that the specific types of base stations are not limited in the embodiments of the present disclosure.

Those skilled in the art will appreciate that the number of base stations, OAM entities, and terminals in fig. 1 is merely illustrative, and that any number of base stations, OAM entities, and terminals may be provided as desired. The embodiments of the present disclosure are not limited in this regard.

It should be noted that the integration of the AI technology and the wireless network has become the necessity of the development of wireless communication, and the wireless network uses the artificial intelligence technology to better cope with more complex network architecture and various communication scenes, and the AI algorithm can classify, count and infer data based on massive data generated by the complex network, so as to further give conclusions such as analysis, prediction and recommendation.

Therefore, the embodiment of the disclosure provides a network mobility management scheme based on AI/ML, which performs model training on network measurement reporting data (such as information of radio resource status, cell load, service demand, handover success rate, handover history performance data, UE position, etc.) through AI/ML technology on processing capability of big data, classifies and identifies successful handover scenes and failure scenes and related handover mechanisms by using an algorithm, analyzes service experience and network performance in handover periods in different mobile scenes, and outputs optimal handover parameters, resource configuration and mobility policy related model reasoning analysis for corresponding operation of a network, thereby realizing minimization of call drop rate, RLF, unnecessary handover and ping-pong handover to ensure network service quality.

Fig. 2 shows a generic architecture of an AI/ML-based wireless network, in which the relevant functionalities defined and the data/information flows are described as follows:

1) The data collection function is used for providing input data for the model training function and the model reasoning function; the incoming data contains measurement or feedback information from the terminal or different network entities.

2) The model training functionality, for performing AI/ML model training, validation, and testing functions, is capable of generating model performance metrics as part of a model testing process. The model training function is also used for preprocessing, cleaning, formatting and converting data according to training data provided by the data collection function.

3) The model reasoning function body is used for providing model reasoning output based on the trained AI/ML model, and the model reasoning output comprises prediction and decision information for each node of the network to judge and execute. In addition, the model reasoning functional body also has the processing capability for data.

4) And the execution function body is used for receiving the output of the model reasoning function body and triggering or executing corresponding actions.

In order to optimize network mobility management and solve the problems of low switching success rate, poor switching robustness, high switching time delay and the like in the traditional mobility management, the AI/ML-based network mobility management scheme provided in the embodiment of the disclosure performs classification and identification of different mobility scenes and switching mechanisms through feature data training, and outputs optimal switching parameters, resource configuration and mobility policy related model reasoning analysis.

First, in the embodiments of the present disclosure, a network mobility management optimization method applied to an anchor base station is provided, and in principle, the method may be performed by any electronic device having computing processing capability.

Fig. 3 shows a flowchart of a network mobility management optimization method applied to an anchor base station in an embodiment of the present disclosure, and as shown in fig. 3, the network mobility management optimization method applied to an anchor base station provided in the embodiment of the present disclosure may include the following steps:

S302, a model reasoning request message is sent to an auxiliary base station, wherein the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, and outputting network mobility management optimization decision information;

s304, receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries the IP address and the port address of the auxiliary base station;

s306, establishing a data channel for transmitting related data of the AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

s308, transmitting the network mobility management optimization decision information output by the model reasoning to the auxiliary base station through a data channel established between the anchor base station and the auxiliary base station, wherein the anchor base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information output by the model reasoning, and the auxiliary base station is also used for executing network load balancing operation according to the network mobility management optimization decision information output by the model reasoning.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving a model deployment/update message from an OAM entity, wherein the model deployment/update message is used for indicating an anchor point base station to report measurement information used for carrying out online training on an AI/ML model; the method comprises the steps of reporting first anchor base station measurement information of an anchor base station and collected first auxiliary base station measurement information of an auxiliary base station to an OAM entity as model training data, so that the OAM entity carries out online training, verification and test on an AI/ML model which is trained offline in advance according to the model training data reported by the anchor base station and the auxiliary base station, and a network mobility management optimization model is obtained; deploying/updating an OAM entity trained network mobility management optimization model at an anchor base station; and taking the second anchor base station measurement information of the anchor base station and the collected second auxiliary base station measurement information of the auxiliary base station as model reasoning data, inputting the model reasoning data into a network mobility management optimization model, and outputting network mobility management optimization decision information.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: the following measurement configuration information is issued to one or more terminals within the coverage area of the anchor base station:

1) Terminal history mobility information;

2) The RRM measurement configuration information at least comprises: periodically measuring trigger information and terminal wireless measurement information;

3) MDT measurement configuration information at least comprises: trigger information and terminal position information and terminal moving speed are periodically measured.

In some embodiments, the method further comprises: each terminal in the coverage area of the receiving anchor base station measures and collects at least one of the following information after receiving measurement configuration information issued by the anchor base station: terminal location information, terminal reference signal received power RSRP, terminal reference signal received quality RSRQ, terminal signal to interference plus noise ratio SINR measurements.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving measurement information sent by each terminal in the coverage area of the anchor base station through a terminal measurement report message after receiving measurement configuration information issued by the anchor base station, wherein the terminal measurement report message comprises the following information:

1) Terminal history mobility information;

2) The radio resource management RRM measurement configuration information includes at least: terminal wireless measurement information and timestamp information;

3) The MDT measurement configuration information at least comprises: terminal position information, terminal movement speed, and time stamp information.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving measurement information reported by one or more terminals; the method comprises the steps that measurement information reported by each terminal and measurement information of an anchor base station are sent to an OAM entity through model training input information, and the OAM entity is used for carrying out online training, verification and test on an AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and an auxiliary base station, so that a network mobility management optimization model is obtained, and the network mobility management optimization model is deployed/updated to the anchor base station; the model training input message at least comprises the following characteristic input information:

(1) the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information, terminal position information, terminal movement speed, terminal wireless measurement information and time stamp information;

(2) the characteristic input information of the base station at least comprises: base station wireless measurement information, current terminal flow information and timestamp information;

(3) the feature input information of the adjacent base station at least comprises: history terminal information of the neighboring base station, wireless measurement information of the neighboring base station, history handover to neighboring terminal information, terminal handover success/unsuccessful information, and time stamp information.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: after receiving the model deployment/update message from the OAM entity, returning a model feedback message to the OAM entity so that the OAM entity optimizes the network mobility management optimization model according to the model feedback message, wherein the OAM entity is used for carrying out online training, verification and test on the AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and the auxiliary base station, obtaining the network mobility management optimization model, and deploying/updating the network mobility management optimization model to the anchor base station.

In some embodiments, the model feedback message includes at least one of the following information:

(1) calculation power overhead information of model training and reasoning;

(2) model predictive confidence;

(3) model training and reasoning is time consuming.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: and returning a first feedback message after the network mobility management optimization operation and/or the switching operation to the OAM entity so that the OAM entity optimizes the network mobility management optimization model according to the first feedback message, wherein the OAM entity is used for carrying out online training, verification and test on the AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and the auxiliary base station to obtain the network mobility management optimization model, and deploying/updating the network mobility management optimization model to the anchor base station.

Further, in some embodiments, the first feedback message includes at least the following information:

1) The measurement feedback information comprises at least one of the following: (1) the service quality QoS parameter information of the switching terminal at least comprises: throughput and packet delay; (2) the target base station resource status information at least comprises: the service condition of a downlink total physical resource block PRB of a cell; (3) the target base station wireless measurement information at least comprises: cell PRB utilization, average Radio Resource Control (RRC) connection number and packet loss rate;

2) Virtual resource consumption prediction information, including: a predicted value of the average consumption of computing power and storage power associated with the base station.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: and receiving a model training suspension message sent by an OAM entity, wherein the OAM entity is used for carrying out online training, verification and test on the AI/ML model which is trained offline in advance according to model training data reported by an anchor base station and an auxiliary base station, obtaining a network mobility management optimization model, deploying/updating the model training suspension message to the anchor base station, and sending the model training suspension message which is a message sent by the OAM entity when each base station in a target area range of network mobility management optimization to be executed meets preset target conditions, and is used for indicating the anchor base station and the auxiliary base station to stop transmitting data and signaling related to network mobility management optimization model training and reasoning.

Further, in some embodiments, the model training pause message includes at least the following information:

1) Model mobility optimization stop indication information;

2) Model mobility optimization stop reasons, including: network resource saving and terminal saving.

In some embodiments, the anchor base station is further configured to receive a model deployment/update message sent by the OAM entity, where the model deployment/update message includes the following information:

1) The anchor base station indication information is used for indicating the receiving base station as an anchor base station and is responsible for collecting and counting the measurement information of each auxiliary base station in the target area range of network mobility management optimization to be executed;

2) The auxiliary base station identification list in the target area comprises the identification of one or more auxiliary base stations, and each auxiliary base station provides data required by model training and reasoning for an anchor base station;

3) Model index information for indicating an applicable use case of the model and an algorithm used by the model;

4) The characteristic input information list is used for indicating the base station to collect one or more characteristic input information required by model training;

5) The feature input information request information element comprises the following values: start, stop and add;

6) Feature input information addition information element: measurement information or prediction information other than feature input information indicating that a new addition is required.

In some embodiments, the model index information includes at least: (1) the model use case is used for indicating various use cases required for realizing the target use case, and at least comprises: load prediction and terminal track prediction; (2) model class, which is used for indicating the adaptation model of the related use cases, at least comprises: linear regression, logistic regression models, decision tree models, support vector machine models, random forest models; (3) the model parameters, which are configuration variables inside the model and are carried in the model deployment/update message, at least comprise: weight information, bias information, learning rate, iteration number, support vector machine SVM support vector.

In some embodiments, the feature input information list includes at least: (1) the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information and terminal wireless measurement information; (2) the characteristic input information of the base station at least comprises: base station wireless measurement information and current terminal flow information; (3) the feature input information of the adjacent base station at least comprises: historical terminal information of adjacent base stations, wireless measurement information of adjacent base stations, historical terminal information of switching to adjacent base stations, and successful/unsuccessful terminal switching information.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: if the feature input information request information element is set to be started, the base station is instructed to start measurement according to the feature input information list; if the feature input information request information element is set to stop, instructing the base station to stop measurement and reporting; if the feature input information request information element is set to be added, adding the measurement quantity or the predicted value indicated in the feature input information addition information element to a previously given feature input information list to start measurement; if a measurement has been initiated by adding information indicated in the information element to the feature input information, the information is ignored.

In some embodiments, the anchor base station is further configured to receive measurement indication information sent by the OAM entity through the model deployment/update message, where the measurement indication information is configured to instruct the anchor base station to issue first measurement configuration information to one or more terminals within a coverage area of the anchor base station, so that each terminal within the coverage area of the anchor base station reports historical terminal measurement information according to the received first measurement configuration information.

In some embodiments, the model reasoning request message contains at least the following information: message type, anchor point base station measurement identification, auxiliary base station measurement identification, reporting cell list, reporting information of feature input information, model reasoning information list indication information, registration request information element of feature input information, and reporting feature information;

The message type is used for indicating that the request message is used for requesting data of model reasoning; the reported cell list is used for indicating the following information: the cell reports information and reporting period; the cell reporting information includes at least one of: cell identity, synchronization signal and physical broadcast channel block SSB report list, SSB index; reporting period indicates average window length of all measurement objects; the reported information of the characteristic input information is used for indicating a measurement object requested to the receiving base station, and the measurement object at least comprises: characteristic input information of a terminal, characteristic input information of a base station and characteristic input information of a neighbor base station; the model reasoning information list indicates information for indicating data required by newly added model reasoning.

In some embodiments, in the case where the measurement object includes feature input information of the terminal, the measurement object includes the following information: (1) terminal history movement information; (2) terminal position information; (3) terminal moving speed; (4) terminal wireless measurement information including at least one of: terminal reference signal received power RSRP, terminal reference signal received quality RSRQ.

In some embodiments, in case the measurement object comprises characteristic input information of a base station, the measurement object comprises characteristic input information of at least one cell of a secondary base station; wherein the characteristic input information of each of the at least one cell includes at least the following information: the current flow sum of the terminals in the cell and the wireless measurement information of the cell; the wireless measurement information of the cell at least comprises: physical Resource Block (PRB) utilization rate of a cell, average Radio Resource Control (RRC) connection number of the cell and packet loss rate of the cell.

In some embodiments, in the case where the measurement object includes the feature input information of the neighbor base station, the measurement object includes at least the following information; (1) history information of neighbor base station terminals; (2) the wireless measurement information of the adjacent base station at least comprises: the physical resource block PRB utilization rate of the cell, the average Radio Resource Control (RRC) connection number of the cell and the packet loss rate of the cell; (3) the history switching terminal information is used for indicating terminal related information of the current base station in history switching, and at least comprises: terminal location information, quality of service parameter information, terminal wireless measurement information, the quality of service parameter information including at least one of: packet loss rate and time delay; (4) and the terminal history is related information of success or unsuccessful switching.

In some embodiments, the model inference information list indication information includes at least the following information: (1) the IP address and the port address of the anchor base station indicate the auxiliary base station to feed back data through the user interface; (2) characteristic input information of at least one cell of the auxiliary base station; wherein the characteristic input information of each of the at least one cell comprises at least one of: the method comprises the steps of predicting a wireless measurement result of a cell, predicting a UE track in the cell, predicting a UE flow in the cell, predicting information of neighbor cell resource states, predicting a wireless measurement result of a neighbor cell, and unloading the flow to the UE wireless measurement information of the cell.

In some embodiments, the model inference reply message contains at least the following information: (1) the message type is used for indicating the reply message to be a model reasoning reply message; (2) the IP address and the port address of the auxiliary base station indicate the auxiliary base station to feed back data through the user interface; (3) an anchor point measurement identifier; (4) the auxiliary base station measures the identification; (5) and the first critical diagnosis indication information indicates an unintelligible or lost message in the messages received by the auxiliary base station.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving a model reasoning data request failure message sent by the auxiliary base station, wherein the model reasoning data request failure message is used for indicating that the auxiliary base station cannot provide information of measurement requested by the model reasoning request message; the model reasoning data request failure message at least comprises the following information: (1) message type, indicating failure of model reasoning data acquisition; (2) an anchor point base station measures an identifier; (3) the auxiliary base station measures the identification; (4) failure cause, indicating the cause of the XnAP protocol specific event; the failure cause includes at least one of: radio network layer reasons, transport layer reasons, and protocol reasons; (5) second critical diagnostic indication information indicating that the received message is not understood, lost or contains information of a logical error; (6) waiting for a retransmission time indicating the time at which the anchor base station re-initiates the request.

Based on the same inventive concept, the embodiment of the disclosure also provides a network mobility management optimization method applied to the secondary base station, and in principle, the method can be executed by any electronic device with calculation processing capability.

Fig. 4 shows a flowchart of a network mobility management optimization method applied to a secondary base station in an embodiment of the present disclosure, and as shown in fig. 4, the network mobility management optimization method applied to a secondary base station provided in the embodiment of the present disclosure may include the following steps:

s402, receiving a model reasoning request message from an anchor base station, wherein the model reasoning request message carries an IP address and a port address of the anchor base station and is used for indicating an auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information;

s404, returning a model reasoning reply message to the anchor base station, wherein the model reasoning reply message carries the IP address and the port address of the auxiliary base station;

s406, establishing a data channel for transmitting related data of the AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

S408, receiving network mobility management optimization decision information sent by an anchor base station through a data channel established between the anchor base station and an auxiliary base station, wherein the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by a model, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: and receiving a model deployment/update message from the OAM entity, wherein the model deployment/update message is used for indicating the auxiliary base station to report measurement information serving as model training data.

In some embodiments, the above method provided in embodiments of the present disclosure may further include the steps of: and sending a second feedback message for the auxiliary base station to execute the network load balancing operation to the OAM entity, so that the OAM entity optimizes the network mobility management optimization model according to the second feedback message.

In some embodiments, the second feedback message includes at least the following information: the measurement feedback information comprises at least one of the following: the service quality QoS parameter information of the switching terminal at least comprises: throughput and packet delay; the target base station resource status information at least comprises: the service condition of a downlink total physical resource block PRB of a cell; the target base station wireless measurement information at least comprises: cell PRB utilization, average Radio Resource Control (RRC) connection number and packet loss rate; virtual resource consumption prediction information, including: a predicted value of the average consumption of computing power and storage power associated with the base station.

In some embodiments, the above method provided in embodiments of the present disclosure may further include the steps of: and receiving a model training suspension message sent by the OAM entity, wherein the model training suspension message is a message sent by the OAM entity when each base station in a target area range where network mobility management optimization is to be executed meets a preset target condition, and is used for indicating an anchor base station and an auxiliary base station to stop transmitting data and signaling related to network mobility management optimization model training and reasoning.

In some embodiments, the model training pause message contains at least the following information: (1) model mobility optimization stop indication information; (2) model mobility optimization stop reasons, including: network resource saving and terminal saving.

In some embodiments, the secondary base station is further configured to receive a model deployment/update message sent by the OAM entity, where the model deployment/update message includes the following information:

1) Model index information for indicating an applicable use case of the model and an algorithm used by the model;

2) The characteristic input information list is used for indicating the base station to collect one or more characteristic input information required by model training;

3) The feature input information request information element comprises the following values: start, stop and add;

4) Feature input information addition information element: measurement information or prediction information other than feature input information indicating that a new addition is required.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving measurement information reported by one or more terminals; the method comprises the steps that measurement information reported by each terminal and measurement information of an auxiliary base station are sent to an OAM entity through model training input information, and the OAM entity is used for carrying out online training, verification and test on an AI/ML model which is trained offline in advance according to model training data reported by an anchor base station and the auxiliary base station, so that a network mobility management optimization model is obtained, and the network mobility management optimization model is deployed/updated to the anchor base station; the model training input message at least comprises the following characteristic input information:

(1) The characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information, terminal position information, terminal movement speed, terminal wireless measurement information and time stamp information; (2) the characteristic input information of the base station at least comprises: base station wireless measurement information, current terminal flow information and timestamp information; (3) the feature input information of the adjacent base station at least comprises: history terminal information of the neighboring base station, wireless measurement information of the neighboring base station, history handover to neighboring terminal information, terminal handover success/unsuccessful information, and time stamp information.

In some embodiments, the model reasoning request message sent by the anchor base station to the auxiliary base station is further used for indicating the auxiliary base station to issue second measurement configuration information to one or more terminals in the coverage area of the auxiliary base station, so that each terminal in the coverage area of the auxiliary base station reports current terminal measurement information according to the received second measurement configuration information.

In some embodiments, the model reasoning request message contains at least the following information: message type, anchor point base station measurement identification, auxiliary base station measurement identification, reporting cell list, reporting information of feature input information, model reasoning information list indication information, registration request information element of feature input information, and reporting feature information; the message type is used for indicating that the request message is used for requesting data of model reasoning; the reported cell list is used for indicating the following information: the cell reports information and reporting period; the cell reporting information includes at least one of: cell identity, synchronization signal and physical broadcast channel block SSB report list, SSB index; reporting period indicates average window length of all measurement objects; the reported information of the characteristic input information is used for indicating a measurement object requested to the receiving base station, and the measurement object at least comprises: characteristic input information of a terminal, characteristic input information of a base station and characteristic input information of a neighbor base station; the model reasoning information list indicates information for indicating data required by newly added model reasoning.

In some embodiments, the model inference reply message contains at least the following information: (1) the message type is used for indicating the reply message to be a model reasoning reply message;

(2) the IP address and the port address of the auxiliary base station indicate the auxiliary base station to feed back data through the user interface;

(3) an anchor point measurement identifier;

(4) the auxiliary base station measures the identification;

(5) and the first critical diagnosis indication information indicates an unintelligible or lost message in the messages received by the auxiliary base station.

Based on the same inventive concept, the embodiment of the disclosure also provides a network mobility management optimization method applied to an operation, maintenance and management OAM entity, and in principle, the method can be executed by any electronic device with computing processing capability.

Fig. 5 is a flowchart of a network mobility management optimization method applied to an OAM entity in an embodiment of the present disclosure, as shown in fig. 5, where the network mobility management optimization method applied to an OAM entity provided in the embodiment of the present disclosure may include the following steps:

s502, determining a target area range for network mobility management optimization to be executed, wherein a plurality of base stations exist in the target area range;

s504, determining a first base station and a second base station according to the calculation capability information and the energy storage capability information of each base station in the target area, wherein the first base station is an anchor base station in the target area, and the second base station is any auxiliary base station in the target area;

s506, sending a model deployment/update message to the first base station and the second base station, wherein the model deployment/update message is used for indicating the first base station and the second base station to report measurement information serving as model training data;

S508, performing online training, verification and test on the artificial intelligent AI/machine learning ML model according to model training data reported by the first base station and the second base station to obtain a network mobility management optimization model;

s510, deploying/updating a network mobility management optimization model to a first base station, so that the first base station inputs model reasoning data reported by the first base station and an auxiliary base station into the network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to a second base station through an interface between the base stations, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model; the second base station performs network load balancing operation according to network mobility management optimization decision information which is output by model reasoning, an interface between the base stations is a data channel which is established between the first base station and the second base station and is used for transmitting AI/ML model related data according to the IP address and the port address of the first base station and the IP address and the port address of the second base station, the first base station sends the IP address and the port address of the first base station to the second base station through model reasoning request information, and the second base station sends the IP address and the port address of the second base station to the first base station through model reasoning reply information.

In some embodiments, after deploying/updating the network mobility management optimization model to the first base station, the above-described method provided in embodiments of the present disclosure may further include the steps of: receiving a model feedback message returned by the first base station; and optimizing the network mobility management optimization model according to the model feedback message.

In some embodiments, the model feedback message includes at least one of the following information: (1) calculation power overhead information of model training and reasoning; (2) model predictive confidence; (3) model training and reasoning is time consuming.

In some embodiments, the method further comprises: receiving a first feedback message returned after the first base station executes network mobility management optimization operation and/or switching operation; and optimizing the network mobility management optimization model according to the first feedback message.

In some embodiments, the first feedback message includes at least the following information:

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: receiving a second feedback message returned by the second base station for executing the network load balancing operation; and optimizing the network mobility management optimization model according to the second feedback message.

In some embodiments, the second feedback message includes at least the following information:

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: and when each base station in the target area meets the preset target condition, sending a model training suspension message to the first base station and the second base station, wherein the model training suspension message is used for indicating the first base station and the second base station to stop transmitting data and signaling related to the network mobility management optimization model training and reasoning.

Further, in some embodiments, the model training pause message includes at least the following information: (1) model mobility optimization stop indication information; (2) model mobility optimization stop reasons, including: network resource saving and terminal saving.

In some embodiments, training, verifying and testing the AI/ML model according to model training data reported by the first base station and the second base station to obtain a network mobility management optimization model, including: dividing model training data reported by a first base station and a second base station into a training data set, a verification data set and a test data set; training the AI/ML model according to the training data set; and carrying out parameter adjustment on the trained AI/ML model according to the verification data set and the test data set to obtain a network mobility management optimization model meeting preset convergence conditions.

In some embodiments, the model deployment/update message sent to the first base station includes the following information:

1) The anchor base station indication information is used for indicating the receiving base station as an anchor base station and is responsible for collecting and counting the measurement information of each auxiliary base station in the target area range;

In some embodiments, the model deployment/update message sent to the second base station includes the following information: 1) Model index information for indicating an applicable use case of the model and an algorithm used by the model; 2) The characteristic input information list is used for indicating the base station to collect one or more characteristic input information required by model training; 3) The feature input information request information element comprises the following values: start, stop and add; 4) Feature input information addition information element: measurement information or prediction information other than feature input information indicating that a new addition is required.

In some embodiments, after receiving the model deployment/update message, the first base station issues the following measurement configuration information to one or more terminals within the coverage area of the first base station: (1) terminal history mobility information; (2) the RRM measurement configuration information at least comprises: periodically measuring trigger information and terminal wireless measurement information; (3) MDT measurement configuration information at least comprises: trigger information and terminal position information and terminal moving speed are periodically measured.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: acquiring at least one of the following information measured and collected by each terminal in the coverage area of the first base station after receiving measurement configuration information issued by the first base station: terminal location information, terminal reference signal received power RSRP, terminal reference signal received quality RSRQ, terminal signal to interference plus noise ratio SINR measurements.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: acquiring measurement information sent to the first base station by each terminal in the coverage area of the first base station through a terminal measurement report message, wherein the terminal measurement report message comprises the following information: (1) terminal history mobility information; (2) the radio resource management RRM measurement configuration information includes at least: terminal wireless measurement information and timestamp information; (3) the MDT measurement configuration information at least comprises: terminal position information, terminal movement speed, and time stamp information.

In some embodiments, the method further comprises: after receiving measurement information reported by one or more terminals, the first base station receives the measurement information reported by each terminal and the measurement information of the first base station, wherein the measurement information is sent by the first base station through model training input information; the model training input message at least comprises the following characteristic input information: the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information, terminal position information, terminal movement speed, terminal wireless measurement information and time stamp information; the characteristic input information of the base station at least comprises: base station wireless measurement information, current terminal flow information and timestamp information; the feature input information of the adjacent base station at least comprises: history terminal information of the neighboring base station, wireless measurement information of the neighboring base station, history handover to neighboring terminal information, terminal handover success/unsuccessful information, and time stamp information.

In some embodiments, the above method provided in the embodiments of the present disclosure may further include the steps of: after receiving measurement information reported by one or more terminals, the second base station receives the measurement information reported by each terminal and the measurement information of the second base station, wherein the measurement information is sent by the second base station through model training input information; the model training input message at least comprises the following characteristic input information: the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information, terminal position information, terminal movement speed, terminal wireless measurement information and time stamp information; the characteristic input information of the base station at least comprises: base station wireless measurement information, current terminal flow information and timestamp information; the feature input information of the adjacent base station at least comprises: history terminal information of the neighboring base station, wireless measurement information of the neighboring base station, history handover to neighboring terminal information, terminal handover success/unsuccessful information, and time stamp information.

In some embodiments, the model deployment/update message is further configured to instruct the first base station to issue first measurement configuration information to one or more terminals within the coverage area of the first base station, so that each terminal within the coverage area of the first base station reports historical terminal measurement information according to the received first measurement configuration information; the model reasoning request message is further used for indicating the second base station to send second measurement configuration information to one or more terminals in the coverage area of the second base station, so that each terminal in the coverage area of the second base station reports current terminal measurement information according to the received second measurement configuration information.

In some embodiments, the above method provided in embodiments of the present disclosure may further include the steps of: and performing offline training on the AI/ML model based on the historical measurement information, and determining a machine learning algorithm, parameters and required characteristic input information adopted by model training.

From the above, it can be seen that, in the AI/ML-based network mobility management method provided in the embodiments of the present disclosure, model training is performed by the network management side based on the historical data, and according to factors such as the base station switching request frequency, the base station computing power and the storage capacity in the management range, a mobility optimization range and an anchor base station responsible for collecting the relevant data of AI/ML model training of each auxiliary base station are determined. The anchor base station (i.e. the first base station) transmits the self-measurement data and the collected information about the radio resource state, the cell load, the service requirement, the switching success rate, the switching history performance data, the UE position and the like of the auxiliary base station (i.e. the second base station) to the OAM. OAM carries out online model training based on the data set, and the trained model is updated and deployed in the base station in the optimization range. The anchor base station continues to collect the model reasoning related data and outputs the model reasoning analysis including the optimal switching parameters, the resource allocation and the mobility strategy for the network to execute. The network management side further trains the model according to the network performance feedback information of each base station node after the operation is executed, so that the accuracy of the model is improved, and intelligent network mobility management is realized.

Fig. 6 shows an interaction flow between a terminal, an anchor base station (first base station), a secondary base station (second base station), and an OAM entity, specifically including:

s602, OAM triggers an AI/ML-based mobility management optimization mechanism to improve network performance aiming at the problems of low success rate of switching, poor robustness, high switching time delay and the like of network reporting. The OAM calls a pre-configured mobility management use case model, and an anchor base station and a mobility optimization range are determined according to the more base stations reported by the switching problem in the management range and the consideration of factors such as the calculation power and the storage capacity of the base stations. The first base station node is used as an anchor base station and is responsible for collecting data required by the training of the related models of the auxiliary base stations in the optimization range, and the anchor base station has a model reasoning function.

And S604, performing offline training on the pre-configuration model by the OAM based on historical data, wherein the historical data is data such as network wireless resource state, cell load, UE position information, switching success rate, switching historical performance and the like reported by a base station in an effective area range of OAM storage, and the data set is divided into a training data set, a verification data set and a test data set through processing. OAM carries out model training based on the data set, and determines the information such as a learning algorithm, parameters, required characteristic input and the like of a related model.

S606a, according to the offline training of the obtained model, the OAM sends a model deployment message to the first base station node, indicating AI/ML model related configuration information, indicating the base station to turn on measurement and collection of related feature input information, where the information includes but is not limited to:

-anchor base station indication information: and the Boolean or enumeration type is used for indicating the receiving base station node as an anchor base station and is responsible for collecting and counting measurement report information of each base station node.

-list of secondary base station IDs within mobility optimization: the method comprises one or more base station node IDs, which are used for indicating effective auxiliary base station nodes in a mobility optimization range so as to provide data required by model training and reasoning for an anchor base station and facilitate the subsequent operations such as model updating on related base station nodes.

-a model index for indicating applicable use cases for deploying the model and algorithms used by the model:

■ Model use case: the enumeration type terminal comprises at least load prediction, terminal track prediction and the like, and is used for indicating various use cases required for realizing the target use cases.

■ Model class: the enumeration type model at least comprises linear regression, logistic regression, decision trees, support vector machines, random forests and the like and is used for indicating an adaptation model of a related use case.

■ Model parameters: configuration variables inside the model, carried in a model deployment or update message, are used to update model parameters to improve model training accuracy and confidence, including but not limited to:

weight;

bias;

learning rate;

the number of iterations;

SVM support vector.

-feature input information list: for instructing the base station to collect one or more characteristic inputs required for model training, the required information including, but not limited to:

■ The UE's feature input information, including but not limited to:

UE location information;

UE historical mobility information;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.

■ Base station characteristic input information including, but not limited to:

base station radio measurement information: including but not limited to cell PRB utilization, average RRC connection number, packet loss rate, etc.;

current terminal traffic.

■ Neighbor base station node characteristic input information including, but not limited to:

neighbor base station UE history information;

neighbor base station wireless measurement information;

history switch terminal information indicating terminal related information of history switch to the base station, including at least one or more or combination of the following information: UE location information, packet loss rate, delay, and other OoS parameter information, UE wireless measurement information, and the like.

UE success/unsuccessful history handover: past successful and unsuccessful UE handovers, including early handover, too late handover, and false handover, counted based on existing SON/RLF reporting mechanisms.

-a feature input information request IE:

if the feature input information request IE is set to "Start", the base station shall initiate measurements according to the indication in the feature input information list; or alternatively

If the feature input information request IE is set to "stop", the base station shall stop measurement and reporting; or alternatively

If the feature input information request IE is set to "add", the measurement quantity or predicted value indicated in the "feature input information add IE" should be added to the measurement initiated by the previously given feature input information list. If the measurement has been initiated with the information indicated in the "feature input information addition IE", this information will be ignored.

-feature input information addition IE: measurement information or prediction information other than feature input information indicating that a new addition is required.

S606b, according to the offline training model, the OAM sends a model deployment message to the second base station node, indicating AI/ML model related configuration information, and indicating that it starts related measurements, where the included indication information includes but is not limited to:

weight;

bias;

learning rate;

the number of iterations;

SVM support vector;

■ The UE's feature input information, including but not limited to:

UE location information;

UE historical mobility information;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

current terminal traffic;

neighbor base station UE history information;

neighbor base station wireless measurement information;

-a feature input information request IE:

S608, the first base station node receives the model deployment message from the OAM, determines the first base station node to be an anchor base station, calls a pre-configured model according to the indication information and updates model parameters, and collects relevant data of the terminal according to the characteristic input information required by the use case model. The first base station node performs measurement configuration on the terminal in the area, wherein part of position information and the like adopt MDT measurement configuration, and the information comprises but is not limited to:

-UE historical mobility information;

-RRM measurement configurations including, but not limited to:

■ Support periodic measurement triggers: the method comprises a triggering period and a recording period;

■ UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

-MDT measurement configurations including, but not limited to:

■ UE location information;

■ UE movement speed;

s610, the terminal performs corresponding measurement according to the first base station configuration information, collects the indicated measurement information such as UE position information, UE RSRP, RSRQ, SINR measurement value and the like, and completes recording and collection of corresponding measurement quantity according to MDT measurement.

S612, the terminal transmits the measurement information such as the historical mobility information, the location information, the RSRP, the RSRQ and the like required by the model training to the first base station through the UE measurement report message, wherein the information comprises but is not limited to:

-UE historical mobility information;

-RRM measurement configurations including, but not limited to:

■ A time stamp.

-MDT measurement configurations including, but not limited to:

■ UE location information;

■ UE movement speed;

■ A time stamp.

S614a, if the first base station node can provide the feature input information indicated in the model deployment message, the first base station node starts measurement and performs feedback according to the corresponding request. The first base station reports data by receiving and processing measurements from one or a group of terminals, and sends measurement statistics results of the data and the base station to the OAM through a model training input message, wherein the information comprises but is not limited to:

-feature input information: data information required for model training indicated by the model deployment message, including, but not limited to:

■ UE feature input information including, but not limited to:

UE historical mobility information;

UE location information;

UE movement speed;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

time stamp;

current terminal traffic: indicating one or a group of terminal traffic totals counted by the base station;

time stamp;

neighbor base station UE history information;

neighbor base station radio measurement information: including but not limited to cell PRB utilization, average RRC connection number, packet loss rate, etc.;

historical handover terminal information: terminal related information indicating a history of handover to the base station, comprising at least one or more or a combination of the following information: UE location information, ooS parameter information such as packet loss rate, time delay and the like, UE wireless measurement information and the like;

UE success/unsuccessful history handover: past successful and unsuccessful UE switching counted based on the existing SON/RLF reporting mechanism comprises the situations of early switching, too late switching, error switching and the like;

time stamp;

and S614b, the second base station node inputs an information request according to the characteristics indicated in the model deployment message, and performs corresponding measurement and feedback. The second base station reports data by receiving and processing measurements from one or a group of terminals, and sends measurement statistics results of the second base station and the base station to the OAM through a model training input message, wherein the information comprises but is not limited to:

■ UE feature input information including, but not limited to:

UE historical mobility information;

UE location information;

UE movement speed;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

time stamp.

neighbor base station UE history information;

UE success/unsuccessful history handover: past successful and unsuccessful UE handovers counted based on existing SON/RLF reporting mechanisms, including premature handover, too late handover, and false handover, etc.;

Time stamp.

S616, OAM receives the data information from the base station statistics in the mobility management optimization scope, processes the data of the related data set and divides the data set to form a training data set, a verification data set and a test data set. OAM carries out online model training based on the data set, and parameter adjustment and feature optimization are carried out through model training, verification and testing processes so as to obtain a more accurate model.

At S618a, the OAM updates the AI/ML model after online training, verification and testing to the first base station node, where the information contained in the message includes, but is not limited to:

-feature input information list

■ UE feature input information including, but not limited to:

UE location information;

UE historical mobility information;

UE radio measurement information;

base station wireless measurement information;

current terminal traffic;

neighbor base station UE history information;

neighbor base station wireless measurement information;

historical handover terminal information;

UE success/unsuccessful history handover;

-a feature input information request IE:

if the feature input information request IE is set to "start", the receiving base station node shall start measurement according to the indication in the feature input information list; or alternatively

If the feature input information request IE is set to "stop", the receiving base station node should stop measuring and reporting; or alternatively

-reporting the feature, if the feature input information request indicates "start", to indicate the measurement object reported by the second base station node requested for each position in the bitmap.

-a reporting period indicating a reporting period of the periodic measurement;

-feature input information addition IE: indicating newly added required feature input measurements;

-secondary base station adding IE:

if the message carries the auxiliary base station adding IE, if the message supports the auxiliary base station adding IE, the first base station node should add the relevant base station to the auxiliary base station ID list according to the indication information and is responsible for collecting and storing the measurement information from the base station as model training information.

Model use case change IE:

if the message carries the model use case change IE, the first base station node should increase or decrease the call of the use case model according to the indication message to change the model use case if supported. The model use case can be represented by enumerated values, at least comprising UE mobility prediction, UE flow prediction and the like, and is used for improving the accuracy of the target use case or reducing the computational complexity so as to save network resources.

Model class change IE:

if the message carries the model category changing IE, the first base station changes the model category according to the indication information, and selects a model with more proper and accurate algorithm. Model classes, which may be represented by enumerated values, include at least linear regression, logistic regression, decision trees, and the like.

Model parameter change IE:

if the message carries the parameter change IE, the first base station should change the model parameter information according to the instruction to obtain a more accurate model.

S618b, the OAM updates the AI/ML model after online training, verification and testing to the second base station node, and the information contained in the message includes, but is not limited to:

-feature input information list

■ UE feature input information including, but not limited to:

UE location information;

UE historical mobility information;

UE radio measurement information;

base station wireless measurement information;

current terminal traffic;

neighbor base station UE history information;

neighbor base station wireless measurement information;

historical handover terminal information;

UE success/unsuccessful history handover;

-a feature input information request IE;

-feature input information addition IE;

-reporting a feature;

-a reporting period indicating a reporting period of the periodic measurement;

-the secondary base station adding an IE;

-model use case change IE;

-model class change IE;

-a model parameter change IE;

s620, the first base station node receives the model deployment/update message from the OAM, and obtains the data required for model reasoning from the second base station node according to the latest model indication information and the auxiliary base station ID list in the mobility management optimization area. The first base station node instructs the second base station to start, stop or add the measurement procedure in the model-based deployment/update message by sending a model inference data request message to the second base station node.

The model inference data request message needs to be fed back through the control plane and/or the user plane, and the information includes, but is not limited to:

-a message type;

-a first base station node measurement ID;

-a second base station node measures an ID;

-a first base station IP address and port address: if the message contains the IE, the second base station node is instructed to feed back data through the user interface;

-reporting cell list

■ Cell reporting information: including but not limited to cell ID, SSB report list, SSB index, etc.

■ Reporting period: may be used to indicate the average window length of all measurement objects.

-feature input information reporting: indicating a measurement object requested from a receiving base station node

■ UE feature input information including, but not limited to:

UE historical mobility information;

UE location information;

UE movement speed;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

neighbor base station UE history information;

-a model reasoning information list IE to indicate data required for the newly added model reasoning, including but not limited to:

■ The first base station node is provided with characteristic input information of one or more cells, wherein the characteristic input information of each cell at least comprises one or a combination of the following:

predicting radio resource status: the downlink total PRB service condition of the cell;

predicting terminal traffic: sum of terminal flow in the cell;

■ The second base station node is configured to receive feature input information of one or more cells, where the feature input information of each cell includes at least one or a combination of the following:

-feature input information registration request

If the registration request IE is set to "start", the receiving base station node should initiate measurement according to the indication in the feature input information list; or alternatively

If the registration request IE is set to "stop", the receiving base station node should stop measuring and reporting; or alternatively

If the registration request IE is set to "add", the measurement quantity or predicted value indicated in the "model inference information list IE" should be added to the measurement initiated by the previously given feature input information report list. If a measurement has been initiated on the information indicated in the "model inference information list IE", this information will be ignored.

S622a, the second base station node receives the model inference data request message from the first base station node, and indicates, through the model inference data reply message, measurement object information for the requested measurement object, which can successfully initiate measurement. The information contained includes, but is not limited to:

-a second base station IP address and port address: indicating the second base station node to perform data feedback through the user interface;

-a message type;

-a first base station measurement ID;

-a second base station measurement ID;

critical diagnostic IE: the message carries this IE to indicate which IEs are not understood or lost in the received message.

S622b, if no measurement can be provided for any request, the second base station node should send a model reasoning data failure message with appropriate cause values, including but not limited to:

-a message type;

-a first base station measurement ID;

-a second base station measurement ID;

Failure cause: the reasons for the XnAP protocol specific event at least comprise a wireless network layer reason, a transmission layer reason, a protocol reason and the like;

-critical diagnostics: when a partially received message is not understood or lost, or the message contains a logical error, the IE is used for information indicating which IEs are not understood or lost;

-waiting for a retransmission time indicating the time to reinitiate the request.

S624, the second base station node sends an inference data report message to the first base station node for reporting the requested measurement information, including but not limited to:

-a message type;

-a first base station measurement ID;

-a second base station measurement ID;

-cell measurements;

■ Cell measurement project

Cell ID

-cell characteristic input information reporting: and indicating the characteristic input information to be reported by one or more cells of the base station, wherein the characteristic input information comprises measurement information configured in a model deployment/update message and measurement information required by newly added model reasoning, and the characteristic input information of each cell at least comprises one or a combination of the following components:

-UE feature input information including, but not limited to:

UE historical mobility information;

UE location information;

UE movement speed;

UE radio measurement information: including one or more of RSRP, RSRQ, etc.;

time stamp;

-base station characteristic input information including, but not limited to:

current/predicted base station radio measurement information: including but not limited to cell PRB utilization, average RRC connection number, packet loss rate, etc.;

current/predicted terminal traffic: indicating one or a group of terminal traffic totals counted by the base station;

terminal trajectory prediction;

time stamp;

neighboring base station node characteristic input information including, but not limited to:

neighbor base station UE history information;

neighbor current/predicted wireless measurement information: including but not limited to cell PRB utilization, average RRC connection number, packet loss rate, etc.;

Time stamp.

Mobility management optimization mechanism: the base station classifies and identifies the switching mechanism related to mobility management optimization through model training and reasoning, and the IE is used for indicating the switching mechanism currently related to the base station, and the enumeration type at least comprises one or more of DAPS, CHO, non-RACH switching, SON MRO and the like.

-mobility management mechanism related parameters: indicating handover-related parameter information including, but not limited to, handover compensation range, handover trigger point, etc.

S626, the terminal in the range of the first base station continues to periodically report measurement information to the anchor base station according to the measurement configuration, wherein the information comprises but is not limited to:

-UE historical mobility information;

-RRM measurement configurations including, but not limited to:

■ A time stamp.

-MDT measurement configurations including, but not limited to:

■ UE location information;

■ UE movement speed;

■ A time stamp.

S628, the first base station reports the information through the model reasoning data and the periodic measurement result of the terminal in the area, obtains the needed model reasoning related data and executes the model reasoning function, and generates AI/ML model reasoning output containing the prediction information and the decision information for the network to analyze or execute operation.

S630, after the first base station node executes the model reasoning function, the model reasoning output message including the prediction and decision information is sent to the second base station node through the Xn interface control plane and/or the user plane, wherein the model reasoning output message is used for indicating the model reasoning output including the prediction information or the energy-saving decision information, and the information included in the message includes but is not limited to:

-mobile performance problem identification: an identifier indicating a mobile performance problem analysis;

mobile performance problem root cause: the root cause of the mobility performance problem is indicated, for example, the mobility interruption time of the delay sensitive service is too long, the cell edge coverage is poor, the success rate of the handover is low, and the handover parameters are improper, so that the handover is performed too early/too late/ping-pong.

Mobility optimization strategy: and indicating a switching mechanism suitable for the corresponding mobility optimization scenario, wherein the switching mechanism comprises one or more of base station triggering, DAPS, CHO, RACH-free switching, SON MRO and the like.

■ Switching mechanism priority

■ Switching mechanism related parameters: indicating handover-related parameter information including, but not limited to, handover compensation range, handover trigger point, etc.

■ Probability of switching mechanism: indicating the arrival probability and the relevant confidence interval of a predicted switching mechanism such as DAPS, CHO and the like;

■ Predicting a target handover cell: indicating the predicted target switching cell and the confidence coefficient under the corresponding switching strategy;

■ Predicting resource reservation time window

■ Time of execution of handover

-model reasoning output valid time: the effective time of the output information is inferred for each model.

S632, the first base station node sends model performance feedback to the OAM to optimize the AI/ML model and evaluate the network AI/ML quality of service. The information carried in the message includes, but is not limited to:

-power consumption overhead: the system is used for indicating the computational power consumption overhead based on the processes of AI/ML model training, reasoning and the like;

model prediction confidence: indicating accuracy of predictions about measurement data;

training/reasoning time-consuming

S634, the first base station node and the second base station node perform related operations based on the model reasoning analysis, including network mobility management optimization operations and handover operations.

S636, after the first base station node performs the network mobility management optimization operation and the handover operation, sends a measurement feedback message to the OAM to provide the data needed to monitor the network performance to further optimize the model. The information contained in the message includes, but is not limited to:

-feedback measurements, the required information including but not limited to:

■ Switching terminal QoS parameters: enumeration, at least including throughput, packet delay and other information;

■ Target base station resource status information: the downlink total PRB service condition of the cell;

■ Target base station wireless measurement information: including but not limited to cell PRB utilization, average RRC connection count, packet loss rate, etc

Virtual resource consumption prediction: representing the prediction of the related calculation power and the average consumption of the memory of the base station node;

s638, after performing the load balancing operation, the second base station node sends a feedback message to the OAM to provide the data needed to monitor the network performance to further optimize the model, where the information included in the message includes, but is not limited to:

-feedback measurements, the required information including but not limited to:

s618 to S638 are repeated.

S640, when the network achieves the goal of zero handover failure, in order to save network resources, the OAM sends an AI/ML model training pause message to the anchor base station and other base station nodes in the range of the effective area, so as to instruct the network to temporarily exit the mobility optimization mechanism based on the AI/ML technology, and stop the transmission of signaling and data about model training input, model reasoning output and the like. The information contained in the message includes, but is not limited to:

-AI/ML mobility optimization stop indication;

-cause, cause indication information including but not limited to:

■ Network resource conservation

■ The UE saves power.

Based on the same inventive concept, a network management device is also provided in the embodiments of the present disclosure, as described in the following embodiments. Because the principle of solving the problem of the network management device embodiment is similar to that of the method embodiment, the implementation of the network management device embodiment can refer to the implementation of the method embodiment, and the repetition is omitted.

Fig. 7 is a schematic diagram showing an internal composition module of a network management device according to an embodiment of the disclosure, as shown in fig. 7, where the network management device includes: a mobility optimization area determination module 71, an anchor base station and secondary base station determination module 72, a model deployment/update message delivery module 73, a model training module 74, and a model deployment module 75.

Wherein, the mobility optimization area determining module 71 is configured to determine a target area range in which network mobility management optimization is to be performed, where a plurality of base stations exist in the target area range;

an anchor base station and auxiliary base station determining module 72, configured to determine a first base station and a second base station according to the computing capability information and the storage capability information of each base station in the target area, where the first base station is an anchor base station in the target area, and the second base station is any auxiliary base station in the target area;

A model deployment/update message issuing module 73, configured to send a model deployment/update message to the first base station and the second base station, where the model deployment/update message is used to instruct the first base station and the second base station to report measurement information as model training data;

the model training module 74 is configured to perform online training, verification and test on the artificial intelligent AI/machine learning ML model according to model training data reported by the first base station and the second base station, so as to obtain a network mobility management optimization model;

the model deployment module 75 is configured to deploy/update a network mobility management optimization model to a first base station, so that the first base station inputs model reasoning data reported by itself and an auxiliary base station into the network mobility management optimization model obtained by training, verifying and testing an artificial intelligence AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to a second base station through an inter-base station interface, wherein the first base station performs network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model; the second base station performs network load balancing operation according to network mobility management optimization decision information which is output by model reasoning, an interface between the base stations is a data channel which is established between the first base station and the second base station and is used for transmitting AI/ML model related data according to the IP address and the port address of the first base station and the IP address and the port address of the second base station, the first base station sends the IP address and the port address of the first base station to the second base station through model reasoning request information, and the second base station sends the IP address and the port address of the second base station to the first base station through model reasoning reply information.

It should be noted that, the mobility optimization area determining module 71, the anchor base station and the secondary base station determining module 72, the model deployment/update message issuing module 73, the model training module 74 and the model deployment module 75 correspond to S502 to S510 in the method embodiment, and the foregoing modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the foregoing method embodiment. It should be noted that the modules described above may be implemented as part of an apparatus in a computer system, such as a set of computer-executable instructions.

Based on the same inventive concept, an anchor base station is also provided in the embodiments of the present disclosure, as described in the following embodiments. Since the principle of the anchor base station embodiment for solving the problem is similar to that of the above method embodiment, the implementation of the anchor base station embodiment can be referred to the implementation of the above method embodiment, and the repetition is omitted.

Fig. 8 is a schematic diagram illustrating internal composition modules of an anchor base station according to an embodiment of the disclosure, where, as shown in fig. 8, the anchor base station includes: a model reasoning request message sending module 81, a model reasoning reply message receiving module 82, an inter-base station data channel establishing module 83 and a mobility optimizing module 84.

The model reasoning request message sending module 81 is configured to send a model reasoning request message to the auxiliary base station, where the model reasoning request message carries an IP address and a port address of an anchor base station and is used to instruct the auxiliary base station to report model reasoning data, and the anchor base station is further configured to input the model reasoning data reported by itself and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, and output network mobility management optimization decision information;

the model reasoning reply message receiving module 82 is configured to receive a model reasoning reply message returned by the secondary base station, where the model reasoning reply message carries an IP address and a port address of the secondary base station;

the inter-base station data channel establishing module 83 is configured to establish a data channel for transmitting data related to the AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

the mobility optimization module 84 is configured to send network mobility management optimization decision information that is inferred and output by a model to the auxiliary base station through a data channel that is established between the anchor base station and the auxiliary base station, where the anchor base station is further configured to perform network mobility management optimization operation and/or handover operation according to the network mobility management optimization decision information that is inferred and output by the model, and the auxiliary base station is further configured to perform network load balancing operation according to the network mobility management optimization decision information that is inferred and output by the model.

It should be noted that, the above-mentioned model reasoning request message sending module 81, model reasoning reply message receiving module 82, inter-base station data channel establishing module 83 and mobility optimizing module 84 correspond to S302 to S308 in the method embodiment, and the above-mentioned modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in the above-mentioned method embodiment. It should be noted that the modules described above may be implemented as part of an apparatus in a computer system, such as a set of computer-executable instructions.

Based on the same inventive concept, an auxiliary base station is also provided in the embodiments of the present disclosure, as described in the following embodiments. Since the principle of the solution of the problem of the secondary base station embodiment is similar to that of the method embodiment described above, the implementation of the secondary base station embodiment can be referred to the implementation of the method embodiment described above, and the repetition is omitted.

Fig. 9 is a schematic diagram illustrating internal composition modules of a secondary base station according to an embodiment of the disclosure, where, as shown in fig. 9, the secondary base station includes: the model reasoning request message receiving module 91, the model reasoning reply message sending module 92, the inter-base station data channel establishing module 93 and the load balancing module 94.

The model reasoning request message receiving module 91 is configured to report historical measurement information serving as model training data to an anchor base station;

the model reasoning reply message sending module 92 is configured to report current measurement information serving as model reasoning data to the anchor base station;

the inter-base station data channel establishing module 93 is configured to establish a data channel for transmitting data related to the AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

the load balancing module 94 is configured to receive, through a data channel established between the anchor base station and the auxiliary base station, network mobility management optimization decision information sent by the anchor base station, where the anchor base station is further configured to perform network mobility management optimization operations and/or handover operations according to the network mobility management optimization decision information that is inferred and output by the model, and the auxiliary base station is further configured to perform network load balancing operations according to the network mobility management optimization decision information that is inferred and output by the model.

It should be noted that, the above-mentioned model reasoning request message receiving module 91, model reasoning reply message sending module 92, inter-base station data channel establishing module 93 and load balancing module 94 correspond to S402 to S408 in the method embodiment, and the above-mentioned modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to those disclosed in the above-mentioned method embodiment. It should be noted that the modules described above may be implemented as part of an apparatus in a computer system, such as a set of computer-executable instructions.

Based on the same inventive concept, a network mobility management optimization system is also provided in the embodiments of the present disclosure, as described in the following embodiments. Since the principle of solving the problem of the system embodiment is similar to that of the method embodiment, the implementation of the system embodiment can be referred to the implementation of the method embodiment, and the repetition is omitted.

There is also provided in an embodiment of the present disclosure a network mobility management optimization system that may include: an OAM entity and a plurality of base stations located within a target area;

the OAM entity is used for determining a target area range of network mobility management optimization to be executed, determining a first base station and a second base station according to calculation capability information and storage capability information of each base station in the target area range, sending model deployment/update information to the first base station and the second base station to instruct the first base station and the second base station to report measurement information serving as model training data, carrying out online training, verification and testing on an artificial intelligent AI/machine learning ML model according to the model training data reported by the first base station and the second base station to obtain a network mobility management optimization model, and deploying/updating the network mobility management optimization model to the first base station, wherein the first base station is an anchor base station in the target area range, and the second base station is any auxiliary base station in the target area range; the first base station is used for inputting model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputting network mobility management optimization decision information, sending the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the inter-base station interface is a data channel which is established between the first base station and the second base station and is used for transmitting related data of the AI/ML model according to an IP address and a port address of the first base station and the IP address and the port address of the second base station, and the first base station sends the IP address and the port address of the first base station to the second base station through a model reasoning request message and the second base station sends the IP address and the port address of the second base station to the first base station through a model reasoning reply message; the second base station is used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model; the first base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning.

Those skilled in the art will appreciate that the various aspects of the present disclosure may be implemented as a system, method, or program product. Accordingly, various aspects of the disclosure may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.

An electronic device 1000 according to such an embodiment of the present disclosure is described below with reference to fig. 10. The electronic device 1000 shown in fig. 10 is merely an example and should not be construed as limiting the functionality and scope of use of the disclosed embodiments.

As shown in fig. 10, the electronic device 1000 is embodied in the form of a general purpose computing device. Components of electronic device 1000 may include, but are not limited to: the at least one processing unit 1010, the at least one memory unit 1020, and a bus 1030 that connects the various system components, including the memory unit 1020 and the processing unit 1010.

Wherein the storage unit stores program code that is executable by the processing unit 1010 such that the processing unit 1010 performs steps according to various exemplary embodiments of the present disclosure described in the above section of the present specification.

In some embodiments, when the electronic device 1000 is an anchor base station, the processing unit 1010 may perform the following steps of the method embodiment: the method comprises the steps of sending a model reasoning request message to an auxiliary base station, wherein the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information; receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries an IP address and a port address of the auxiliary base station; establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by the model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by the model reasoning.

In some embodiments, when the electronic device 1000 is a secondary base station, the processing unit 1010 may perform the following steps of the method embodiment: receiving a model reasoning request message from an anchor base station, wherein the model reasoning request message carries an IP address and a port address of the anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information; returning a model reasoning reply message to the anchor base station, wherein the model reasoning reply message carries the IP address and the port address of the auxiliary base station; establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station; the network mobility management optimization decision information sent by the anchor base station is received through a data channel established between the anchor base station and the auxiliary base station, the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by model reasoning.

In some embodiments, when the electronic device 1000 is an OAM entity, the processing unit 1010 may perform the following steps of the method embodiment: determining a target area range for network mobility management optimization to be executed, wherein a plurality of base stations exist in the target area range; determining a first base station and a second base station according to the computing capability information and the energy storage capability information of each base station in the target area, wherein the first base station is an anchor point base station in the target area, and the second base station is any auxiliary base station in the target area; sending a model deployment/update message to the first base station and the second base station, wherein the model deployment/update message is used for indicating the first base station and the second base station to report measurement information serving as model training data; performing online training, verification and testing on an artificial intelligent AI/machine learning ML model according to model training data reported by the first base station and the second base station to obtain a network mobility management optimization model; deploying/updating the network mobility management optimization model to the first base station, so that the first base station inputs model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning; the second base station performs network load balancing operation according to network mobility management optimization decision information output by model reasoning, the inter-base station interface is a data channel which is established between the first base station and the second base station and used for transmitting AI/ML model related data according to the IP address and port address of the first base station and the IP address and port address of the second base station, the first base station sends the IP address and port address of the first base station to the second base station through a model reasoning request message, and the second base station sends the IP address and port address of the second base station to the first base station through a model reasoning reply message.

The memory unit 1020 may include readable media in the form of volatile memory units such as Random Access Memory (RAM) 10201 and/or cache memory unit 10202, and may further include Read Only Memory (ROM) 10203.

The storage unit 1020 may also include a program/utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Bus 1030 may be representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1000 can also communicate with one or more external devices 1040 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1000, and/or with any device (e.g., router, modem, etc.) that enables the electronic device 1000 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1050. Also, electronic device 1000 can communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 1060. As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 over the bus 1030. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 1000, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RA identification systems, tape drives, data backup storage systems, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device performs the inactive state security configuration information issuing method of any of the above.

In an exemplary embodiment of the present disclosure, a computer-readable storage medium, which may be a readable signal medium or a readable storage medium, is also provided. Fig. 11 illustrates a schematic diagram of a computer-readable storage medium in an embodiment of the present disclosure, as shown in fig. 11, on which a program product capable of implementing the method of the present disclosure is stored 1100. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal.

More specific examples of the computer readable storage medium in the present disclosure may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In this disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Alternatively, the program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

In particular implementations, the program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

From the description of the above embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A network mobility management optimization method, applied to an anchor base station, comprising:

the method comprises the steps of sending a model reasoning request message to an auxiliary base station, wherein the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information;

Receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries an IP address and a port address of the auxiliary base station;

establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by the model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by the model reasoning.

2. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

receiving a model deployment/update message from an OAM entity, wherein the model deployment/update message is used for indicating the anchor point base station to report measurement information for performing online training on an AI/ML model;

The method comprises the steps that first anchor base station measurement information of an anchor base station and collected first auxiliary base station measurement information of an auxiliary base station are used as model training data and reported to an OAM entity, so that the OAM entity carries out online training, verification and testing on an AI/ML model which is trained offline in advance according to the model training data reported by the anchor base station and the auxiliary base station, and a network mobility management optimization model is obtained;

deploying/updating a network mobility management optimization model trained by the OAM entity at the anchor base station;

and taking the second anchor base station measurement information of the anchor base station and the collected second auxiliary base station measurement information of the auxiliary base station as model reasoning data, inputting the model reasoning data into the network mobility management optimization model, and outputting network mobility management optimization decision information.

3. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

the following measurement configuration information is issued to one or more terminals within the coverage area of the anchor base station:

terminal history mobility information;

the RRM measurement configuration information at least comprises: periodically measuring trigger information and terminal wireless measurement information;

MDT measurement configuration information at least comprises: trigger information and terminal position information and terminal moving speed are periodically measured.

4. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

receiving at least one of the following information measured and collected by each terminal in the coverage area of the anchor base station after receiving measurement configuration information issued by the anchor base station:

terminal location information, terminal reference signal received power RSRP, terminal reference signal received quality RSRQ, terminal signal to interference plus noise ratio SINR measurements.

5. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

receiving measurement information sent by each terminal in the coverage area of the anchor base station through a terminal measurement report message after receiving measurement configuration information issued by the anchor base station, wherein the terminal measurement report message comprises the following information:

terminal history mobility information;

the radio resource management RRM measurement configuration information includes at least: terminal wireless measurement information and timestamp information;

the MDT measurement configuration information at least comprises: terminal position information, terminal movement speed, and time stamp information.

6. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

receiving measurement information reported by one or more terminals;

the method comprises the steps that measurement information reported by each terminal and measurement information of an anchor base station are sent to an OAM entity through model training input information, and the OAM entity is used for carrying out online training, verification and testing on an AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and an auxiliary base station, so that a network mobility management optimization model is obtained, and the network mobility management optimization model is deployed/updated to the anchor base station; the model training input message at least comprises the following characteristic input information:

the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information, terminal position information, terminal movement speed, terminal wireless measurement information and time stamp information;

the characteristic input information of the base station at least comprises: base station wireless measurement information, current terminal flow information and timestamp information;

the feature input information of the adjacent base station at least comprises: history terminal information of the neighboring base station, wireless measurement information of the neighboring base station, history handover to neighboring terminal information, terminal handover success/unsuccessful information, and time stamp information.

7. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

after receiving the model deployment/update message from the OAM entity, returning a model feedback message to the OAM entity so that the OAM entity optimizes the network mobility management optimization model according to the model feedback message, wherein the OAM entity is used for carrying out online training, verification and test on the AI/ML model which is trained offline in advance according to the model training data reported by the anchor base station and the auxiliary base station, obtaining a network mobility management optimization model, and deploying/updating the network mobility management optimization model to the anchor base station.

8. The network mobility management optimization method according to claim 7, wherein the model feedback message contains at least one of the following information:

calculation power overhead information of model training and reasoning;

model predictive confidence;

model training and reasoning is time consuming.

9. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

and returning a first feedback message after the network mobility management optimization operation and/or the switching operation to an OAM entity so that the OAM entity optimizes a network mobility management optimization model according to the first feedback message, wherein the OAM entity is used for carrying out online training, verification and test on an AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and the auxiliary base station to obtain the network mobility management optimization model, and deploying/updating the network mobility management optimization model to the anchor base station.

10. The network mobility management optimization method according to claim 9, wherein the first feedback message at least contains the following information:

the measurement feedback information comprises at least one of the following:

the service quality QoS parameter information of the switching terminal at least comprises: throughput and packet delay;

the target base station resource status information at least comprises: the service condition of a downlink total physical resource block PRB of a cell;

the target base station wireless measurement information at least comprises: cell PRB utilization, average Radio Resource Control (RRC) connection number and packet loss rate;

virtual resource consumption prediction information, including: a predicted value of the average consumption of computing power and storage power associated with the base station.

11. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

and receiving a model training suspension message sent by an OAM entity, wherein the OAM entity is used for carrying out online training, verification and test on an AI/ML model which is trained offline in advance according to model training data reported by the anchor base station and the auxiliary base station, obtaining a network mobility management optimization model, and deploying/updating the model training suspension message to the anchor base station, and the model training suspension message is a message sent by the OAM entity when each base station in a target area range of network mobility management optimization to be executed meets preset target conditions and is used for indicating the anchor base station and the auxiliary base station to stop transmitting data and signaling related to network mobility management optimization model training and reasoning.

12. The network mobility management optimization method of claim 11, wherein the model training suspension message comprises at least the following information:

model mobility optimization stop indication information;

model mobility optimization stop reasons, including: network resource saving and terminal saving.

13. The network mobility management optimization method according to claim 1, wherein the anchor base station is further configured to receive a model deployment/update message sent by an OAM entity, where the model deployment/update message includes the following information:

the anchor base station indication information is used for indicating the receiving base station as an anchor base station and is responsible for collecting and counting the measurement information of each auxiliary base station in the target area range of network mobility management optimization to be executed;

the auxiliary base station identification list in the target area comprises the identification of one or more auxiliary base stations, and each auxiliary base station provides data required by model training and reasoning for an anchor base station;

model index information for indicating an applicable use case of the model and an algorithm used by the model;

the characteristic input information list is used for indicating the base station to collect one or more characteristic input information required by model training;

The feature input information request information element comprises the following values: start, stop and add;

feature input information addition information element: measurement information or prediction information other than feature input information indicating that a new addition is required.

14. The network mobility management optimization method according to claim 13, wherein the model index information includes at least:

the model use case is used for indicating various use cases required for realizing the target use case, and at least comprises: load prediction and terminal track prediction;

model class, which is used for indicating the adaptation model of the related use cases, at least comprises: linear regression, logistic regression models, decision tree models, support vector machine models, random forest models;

the model parameters, which are configuration variables inside the model and are carried in the model deployment/update message, at least comprise: weight information, bias information, learning rate, iteration number, support vector machine SVM support vector.

15. The network mobility management optimization method of claim 13, wherein the feature input information list comprises at least:

the characteristic input information of the terminal at least comprises: terminal position information, terminal history movement information and terminal wireless measurement information;

The characteristic input information of the base station at least comprises: base station wireless measurement information and current terminal flow information;

the feature input information of the adjacent base station at least comprises: historical terminal information of adjacent base stations, wireless measurement information of adjacent base stations, historical terminal information of switching to adjacent base stations, and successful/unsuccessful terminal switching information.

16. The network mobility management optimization method of claim 13, wherein the method further comprises:

if the feature input information request information element is set to be started, the base station is instructed to start measurement according to the feature input information list;

if the feature input information request information element is set to stop, instructing the base station to stop measurement and reporting;

if the feature input information request information element is set to be added, adding the measurement quantity or the predicted value indicated in the feature input information addition information element to a previously given feature input information list to start measurement; if a measurement has been initiated by adding information indicated in the information element to the feature input information, the information is ignored.

17. The network mobility management optimization method according to claim 1, wherein the anchor base station is further configured to receive measurement indication information sent by an OAM entity through a model deployment/update message, where the measurement indication information is configured to instruct the anchor base station to issue first measurement configuration information to one or more terminals within a coverage area of the anchor base station, so that each terminal within the coverage area of the anchor base station reports historical terminal measurement information according to the received first measurement configuration information.

18. The network mobility management optimization method according to claim 1, wherein the model reasoning request message at least contains the following information:

message type, anchor point base station measurement identification, auxiliary base station measurement identification, reporting cell list, reporting information of feature input information, model reasoning information list indication information, registration request information element of feature input information, and reporting feature information;

wherein the message type is used for indicating that the request message is used for requesting data of model reasoning;

the reported cell list is used for indicating the following information: the cell reports information and reporting period; the cell reporting information comprises at least one of the following: cell identity, synchronization signal and physical broadcast channel block SSB report list, SSB index; the reporting period indicates the average window length of all the measurement objects;

the reported information of the feature input information is used for indicating a measurement object requested to a receiving base station, and the measurement object at least comprises: characteristic input information of a terminal, characteristic input information of a base station and characteristic input information of a neighbor base station;

the model reasoning information list indication information is used for indicating data required by newly added model reasoning.

19. The network mobility management optimization method according to claim 18, wherein in the case where the measurement object includes characteristic input information of a terminal, the measurement object includes the following information:

terminal history movement information;

terminal position information;

terminal moving speed;

terminal wireless measurement information including at least one of: terminal reference signal received power RSRP, terminal reference signal received quality RSRQ.

20. The network mobility management optimization method according to claim 18, wherein in the case where the measurement object includes characteristic input information of a base station, the measurement object includes characteristic input information of at least one cell of a secondary base station;

wherein the characteristic input information of each cell of the at least one cell includes at least the following information: the current flow sum of the terminals in the cell and the wireless measurement information of the cell;

the wireless measurement information of the cell at least comprises: physical Resource Block (PRB) utilization rate of a cell, average Radio Resource Control (RRC) connection number of the cell and packet loss rate of the cell.

21. The network mobility management optimization method according to claim 18, wherein in the case where the measurement object includes characteristic input information of a neighbor base station, the measurement object includes at least the following information;

History information of neighbor base station terminals;

the wireless measurement information of the adjacent base station at least comprises: the physical resource block PRB utilization rate of the cell, the average Radio Resource Control (RRC) connection number of the cell and the packet loss rate of the cell;

the history switching terminal information is used for indicating terminal related information of the current base station in history switching, and at least comprises: terminal position information, service quality parameter information and terminal wireless measurement information, wherein the service quality parameter information comprises at least one of the following components: packet loss rate and time delay;

and the terminal history is related information of success or unsuccessful switching.

22. The network mobility management optimization method of claim 18, wherein the model inference information list indication information includes at least the following information:

the IP address and the port address of the anchor base station indicate the auxiliary base station to feed back data through the user interface;

characteristic input information of at least one cell of the auxiliary base station;

wherein the characteristic input information of each of the at least one cell includes at least one of: the method comprises the steps of predicting a wireless measurement result of a cell, predicting a UE track in the cell, predicting a UE flow in the cell, predicting information of neighbor cell resource states, predicting a wireless measurement result of a neighbor cell, and unloading the flow to the UE wireless measurement information of the cell.

23. The network mobility management optimization method according to claim 1, wherein the model reasoning reply message at least contains the following information:

the message type is used for indicating the reply message to be a model reasoning reply message;

the IP address and the port address of the auxiliary base station indicate the auxiliary base station to feed back data through the user interface;

an anchor point measurement identifier;

the auxiliary base station measures the identification;

and the first critical diagnosis indication information indicates an unintelligible or lost message in the messages received by the auxiliary base station.

24. The network mobility management optimization method according to claim 1, characterized in that the method further comprises:

receiving a model reasoning data request failure message sent by an auxiliary base station, wherein the model reasoning data request failure message is used for indicating that the auxiliary base station cannot provide information of measurement requested by the model reasoning request message;

the model reasoning data request failure message at least comprises the following information:

message type, indicating failure of model reasoning data acquisition;

an anchor point base station measures an identifier;

the auxiliary base station measures the identification;

failure cause, indicating the cause of the XnAP protocol specific event; the failure cause comprises at least one of the following: radio network layer reasons, transport layer reasons, and protocol reasons;

Second critical diagnostic indication information indicating that the received message is not understood, lost or contains information of a logical error;

waiting for a retransmission time indicating the time at which the anchor base station re-initiates the request.

25. The network mobility management optimization method is characterized by being applied to a secondary base station and comprising the following steps:

receiving a model reasoning request message from an anchor base station, wherein the model reasoning request message carries an IP address and a port address of the anchor base station and is used for indicating the auxiliary base station to report model reasoning data, and the anchor base station is also used for inputting the model reasoning data reported by the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance and outputting network mobility management optimization decision information;

returning a model reasoning reply message to the anchor base station, wherein the model reasoning reply message carries the IP address and the port address of the auxiliary base station;

The network mobility management optimization decision information sent by the anchor base station is received through a data channel established between the anchor base station and the auxiliary base station, the anchor base station is further used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning, and the auxiliary base station is further used for executing network load balancing operation according to the network mobility management optimization decision information which is output by model reasoning.

26. The network mobility management optimization method of claim 25, wherein the method further comprises:

and receiving a model deployment/update message from an OAM entity, wherein the model deployment/update message is used for indicating the auxiliary base station to report measurement information serving as model training data.

27. The network mobility management optimization method of claim 25, wherein the method further comprises:

and sending a second feedback message for the auxiliary base station to execute network load balancing operation to an OAM entity, so that the OAM entity optimizes a network mobility management optimization model according to the second feedback message.

28. The network mobility management optimization method according to claim 27, wherein said second feedback message contains at least the following information:

The measurement feedback information comprises at least one of the following:

29. The network mobility management optimization method of claim 25, wherein the method further comprises:

and receiving a model training suspension message sent by an OAM entity, wherein the model training suspension message is a message sent by the OAM entity when each base station in a target area range where network mobility management optimization is to be executed meets a preset target condition, and is used for indicating an anchor base station and an auxiliary base station to stop transmitting data and signaling related to network mobility management optimization model training and reasoning.

30. The network mobility management optimization method of claim 29, wherein the model training suspension message comprises at least the following information:

Model mobility optimization stop indication information;

31. The network mobility management optimization method according to claim 25, wherein the secondary base station is further configured to receive a model deployment/update message sent by an OAM entity, where the model deployment/update message includes the following information:

32. The network mobility management optimization method of claim 31, wherein the model index information comprises at least:

33. The network mobility management optimization method of claim 31, wherein the feature input information list comprises at least:

34. The network mobility management optimization method of claim 31, wherein the method further comprises:

35. The network mobility management optimization method of claim 25, wherein the method further comprises:

receiving measurement information reported by one or more terminals;

the method comprises the steps that measurement information reported by each terminal and measurement information of an auxiliary base station are sent to an OAM entity through model training input information, and the OAM entity is used for carrying out online training, verification and testing on an AI/ML model which is trained offline in advance according to model training data reported by an anchor base station and the auxiliary base station, so that a network mobility management optimization model is obtained, and the network mobility management optimization model is deployed/updated to the anchor base station; the model training input message at least comprises the following characteristic input information:

36. The network mobility management optimization method according to claim 25, wherein the model reasoning request message sent by the anchor base station to the secondary base station is further used for indicating the secondary base station to issue second measurement configuration information to one or more terminals in the coverage area of the secondary base station, so that each terminal in the coverage area of the secondary base station reports current terminal measurement information according to the received second measurement configuration information.

37. The network mobility management optimization method of claim 25, wherein the model reasoning request message includes at least the following information:

38. The network mobility management optimization method according to claim 37, wherein in the case where the measurement object includes characteristic input information of a terminal, the measurement object includes the following information:

terminal history movement information;

terminal position information;

terminal moving speed;

39. The network mobility management optimization method according to claim 37, wherein in the case where the measurement object includes characteristic input information of a base station, the measurement object includes characteristic input information of at least one cell of a secondary base station;

40. The network mobility management optimization method according to claim 37, wherein in the case where the measurement object includes characteristic input information of a neighbor base station, the measurement object includes at least the following information;

history information of neighbor base station terminals;

41. The network mobility management optimization method of claim 37, wherein the model inference information list indication information includes at least the following information:

42. The network mobility management optimization method of claim 25, wherein the model reasoning reply message includes at least the following information:

an anchor point measurement identifier;

The auxiliary base station measures the identification;

43. The network mobility management optimization method of claim 25, wherein the method further comprises:

message type, indicating failure of model reasoning data acquisition;

an anchor point base station measures an identifier;

the auxiliary base station measures the identification;

44. A network mobility management optimization method, applied to an operation maintenance management OAM entity, comprising:

Determining a target area range for network mobility management optimization to be executed, wherein a plurality of base stations exist in the target area range;

determining a first base station and a second base station according to the computing capability information and the energy storage capability information of each base station in the target area, wherein the first base station is an anchor point base station in the target area, and the second base station is any auxiliary base station in the target area;

sending a model deployment/update message to the first base station and the second base station, wherein the model deployment/update message is used for indicating the first base station and the second base station to report measurement information serving as model training data;

performing online training, verification and testing on an artificial intelligent AI/machine learning ML model according to model training data reported by the first base station and the second base station to obtain a network mobility management optimization model;

deploying/updating the network mobility management optimization model to the first base station, so that the first base station inputs model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning; the second base station performs network load balancing operation according to network mobility management optimization decision information output by model reasoning, the inter-base station interface is a data channel which is established between the first base station and the second base station and used for transmitting AI/ML model related data according to the IP address and port address of the first base station and the IP address and port address of the second base station, the first base station sends the IP address and port address of the first base station to the second base station through a model reasoning request message, and the second base station sends the IP address and port address of the second base station to the first base station through a model reasoning reply message.

45. The network mobility management optimization method of claim 44, wherein after deploying/updating said network mobility management optimization model to said first base station, said method further comprises:

receiving a model feedback message returned by the first base station;

and optimizing the network mobility management optimization model according to the model feedback message.

46. The network mobility management optimization method of claim 45, wherein the model feedback message comprises at least one of the following information:

calculation power overhead information of model training and reasoning;

model predictive confidence;

model training and reasoning is time consuming.

47. The network mobility management optimization method of claim 44, wherein said method further comprises:

receiving a first feedback message returned after the first base station executes network mobility management optimization operation and/or switching operation;

and optimizing the network mobility management optimization model according to the first feedback message.

48. The network mobility management optimization method of claim 47, wherein the first feedback message comprises at least the following information:

The measurement feedback information comprises at least one of the following:

49. The network mobility management optimization method of claim 44, wherein said method further comprises:

receiving a second feedback message returned by the second base station for executing the network load balancing operation;

and optimizing the network mobility management optimization model according to the second feedback message.

50. The network mobility management optimization method of claim 49, wherein the second feedback message comprises at least the following information:

the measurement feedback information comprises at least one of the following:

51. The network mobility management optimization method of claim 44, wherein said method further comprises:

and when each base station in the target area meets a preset target condition, sending a model training suspension message to a first base station and a second base station, wherein the model training suspension message is used for indicating the first base station and the second base station to stop transmitting data and signaling related to network mobility management optimization model training and reasoning.

52. The network mobility management optimization method of claim 51, wherein the model training suspension message comprises at least the following information:

model mobility optimization stop indication information;

53. The method of optimizing network mobility management as set forth in claim 44, wherein training, verifying and testing the AI/ML model based on model training data reported by the first base station and the second base station to obtain a network mobility management optimization model comprises:

dividing model training data reported by the first base station and the second base station into a training data set, a verification data set and a test data set;

training an AI/ML model according to the training data set;

and carrying out parameter adjustment on the trained AI/ML model according to the verification data set and the test data set to obtain a network mobility management optimization model meeting preset convergence conditions.

54. The network mobility management optimization method of claim 44, wherein the model deployment/update message sent to the first base station comprises the following information:

the anchor base station indication information is used for indicating the receiving base station as an anchor base station and is responsible for collecting and counting the measurement information of each auxiliary base station in the target area range;

55. The network mobility management optimization method of claim 54, wherein the model index information comprises at least:

56. The network mobility management optimization method of claim 54, wherein said list of feature input information comprises at least:

57. The network mobility management optimization method of claim 54, wherein said method further comprises:

58. The network mobility management optimization method of claim 44, wherein the model deployment/update message sent to the second base station comprises the following information:

59. The network mobility management optimization method of claim 58, wherein the model index information comprises at least:

60. The network mobility management optimization method of claim 58, wherein said list of feature input information comprises at least:

61. The network mobility management optimization method of claim 58, wherein said method further comprises:

62. The network mobility management optimization method of claim 44, wherein said first base station, upon receiving a model deployment/update message, issues to one or more terminals within the coverage area of said first base station the following measurement configuration information:

terminal history mobility information;

63. The network mobility management optimization method of claim 44, wherein said method further comprises:

acquiring at least one of the following information measured and collected by each terminal in the coverage area of the first base station after receiving measurement configuration information issued by the first base station:

64. The network mobility management optimization method of claim 44, wherein said method further comprises:

acquiring measurement information sent to the first base station by each terminal in the coverage area of the first base station through a terminal measurement report message, wherein the terminal measurement report message comprises the following information:

Terminal history mobility information;

65. The network mobility management optimization method of claim 44, wherein said method further comprises:

after receiving measurement information reported by one or more terminals, the first base station receives measurement information reported by each terminal and measurement information of the first base station, wherein the measurement information is sent by each terminal and sent by a model training input message; the model training input message at least comprises the following characteristic input information:

66. The network mobility management optimization method of claim 44, wherein said method further comprises:

after receiving measurement information reported by one or more terminals, the second base station receives measurement information reported by each terminal and measurement information of the second base station, wherein the measurement information is sent by each terminal and sent by a model training input message; the model training input message at least comprises the following characteristic input information:

67. The network mobility management optimization method of claim 44, wherein,

the model deployment/update message is further used for indicating a first base station to send first measurement configuration information to one or more terminals in the coverage area of the first base station, so that each terminal in the coverage area of the first base station reports historical terminal measurement information according to the received first measurement configuration information;

The model reasoning request message is further used for indicating a second base station to send second measurement configuration information to one or more terminals in the coverage area of the second base station, so that each terminal in the coverage area of the second base station reports current terminal measurement information according to the received second measurement configuration information.

68. The network mobility management optimization method of claim 44, wherein prior to sending a model deployment/update message to said first base station and said second base station, said method further comprises:

and performing offline training on the AI/ML model based on the historical measurement information, and determining a machine learning algorithm, parameters and required characteristic input information adopted by model training.

69. A network management apparatus, comprising:

a mobility optimization area determining module, configured to determine a target area range in which network mobility management optimization is to be performed, where a plurality of base stations exist in the target area range;

the anchor base station and auxiliary base station determining module is used for determining a first base station and a second base station according to the computing capability information and the energy storage capability information of each base station in the target area, wherein the first base station is the anchor base station in the target area, and the second base station is any auxiliary base station in the target area;

A model deployment/update message issuing module, configured to send a model deployment/update message to the first base station and the second base station, where the model deployment/update message is used to instruct the first base station and the second base station to report measurement information as model training data;

the model training module is used for carrying out online training, verification and test on the artificial intelligent AI/machine learning ML model according to the model training data reported by the first base station and the second base station to obtain a network mobility management optimization model;

the model deployment module is used for deploying/updating the network mobility management optimization model to the first base station so that the first base station inputs model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligence AI/machine learning ML model in advance, outputs network mobility management optimization decision information, and sends the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the first base station executes network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model; the second base station performs network load balancing operation according to network mobility management optimization decision information output by model reasoning, the inter-base station interface is a data channel which is established between the first base station and the second base station and used for transmitting AI/ML model related data according to the IP address and port address of the first base station and the IP address and port address of the second base station, the first base station sends the IP address and port address of the first base station to the second base station through a model reasoning request message, and the second base station sends the IP address and port address of the second base station to the first base station through a model reasoning reply message.

70. An anchor base station, characterized by being applied to an anchor base station, comprising:

the system comprises a model reasoning request message sending module, a model reasoning request message sending module and a network mobility management optimization module, wherein the model reasoning request message is used for sending a model reasoning request message to an auxiliary base station, the model reasoning request message carries an IP address and a port address of an anchor base station and is used for indicating the auxiliary base station to report model reasoning data, the anchor base station is also used for inputting the model reasoning data reported by the anchor base station and the auxiliary base station into the network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, and outputting network mobility management optimization decision information;

the model reasoning reply message receiving module is used for receiving a model reasoning reply message returned by the auxiliary base station, wherein the model reasoning reply message carries an IP address and a port address of the auxiliary base station;

the inter-base station data channel establishing module is used for establishing a data channel for transmitting related data of an AI/ML model between the anchor base station and the auxiliary base station according to the IP address and the port address of the anchor base station and the IP address and the port address of the auxiliary base station;

the mobility optimization module is used for sending network mobility management optimization decision information which is inferred and output by a model to the auxiliary base station through a data channel which is established between the anchor base station and the auxiliary base station, the anchor base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model, and the auxiliary base station is also used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model.

71. A secondary base station, comprising:

the model reasoning request message receiving module is used for reporting historical measurement information serving as model training data to the anchor base station;

the model reasoning reply message sending module is used for reporting current measurement information serving as model reasoning data to the anchor base station;

the load balancing module is used for receiving the network mobility management optimization decision information sent by the anchor base station through the data channel established between the anchor base station and the auxiliary base station, the anchor base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is inferred and output by the model, and the auxiliary base station is also used for executing network load balancing operation according to the network mobility management optimization decision information which is inferred and output by the model.

72. A network mobility management optimization system, comprising: an OAM entity and a plurality of base stations located within a target area;

The OAM entity is used for determining a target area range of network mobility management optimization to be executed, determining a first base station and a second base station according to calculation capability information and storage capability information of each base station in the target area range, sending model deployment/update information to the first base station and the second base station to instruct the first base station and the second base station to report measurement information serving as model training data, and carrying out online training, verification and testing on an artificial intelligent AI/machine learning ML model according to the model training data reported by the first base station and the second base station to obtain a network mobility management optimization model, and deploying/updating the network mobility management optimization model to the first base station, wherein the first base station is an anchor base station in the target area range, and the second base station is any auxiliary base station in the target area range;

the first base station is used for inputting model reasoning data reported by the first base station and the auxiliary base station into a network mobility management optimization model obtained by training, verifying and testing an artificial intelligent AI/machine learning ML model in advance, outputting network mobility management optimization decision information, and sending the network mobility management optimization decision information to the second base station through an inter-base station interface, wherein the inter-base station interface is a data channel which is established between the first base station and the second base station and is used for transmitting AI/ML model related data according to an IP address and a port address of the first base station and the IP address and the port address of the second base station, and the first base station sends the IP address and the port address of the first base station to the second base station through a model reasoning request message and sends the IP address and the port address of the second base station to the first base station through a model reasoning reply message;

The second base station is used for executing network load balancing operation according to the network mobility management optimization decision information which is output by the model reasoning;

the first base station is also used for executing network mobility management optimization operation and/or switching operation according to the network mobility management optimization decision information which is output by model reasoning.

73. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the network mobility management optimization method of any one of claims 1-68 via execution of the executable instructions.

74. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the network mobility management optimization method of any one of claims 1-68.