CN116782323A

CN116782323A - Switching method and device in communication network

Info

Publication number: CN116782323A
Application number: CN202210216788.4A
Authority: CN
Inventors: 曾宇; 耿婷婷
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-03-07
Filing date: 2022-03-07
Publication date: 2023-09-19

Abstract

A handover method and apparatus in a communication network, where a first access network device and a second access network device are kept connected to a terminal device, the method comprising: the first access network equipment determines a switching request according to a prediction result of the terminal equipment; the first access network equipment sends a switching request to the second access network equipment; the first access network device receives first response information from the second access network device, wherein the first response information is used for indicating the second access network device to agree or reject the switching request. The method and the device can realize switching the access network equipment connected with the terminal equipment in the double-connection scene.

Description

Switching method and device in communication network

Technical Field

The embodiment of the application relates to the technical field of communication, in particular to a switching method and device in a communication network.

Background

In a mobile communication system, in a dual connectivity scenario, one terminal device may remain connected to a plurality of access network devices (e.g., base stations). The network side may provide communication services for the terminal device using a plurality of access network devices, thereby providing high-rate transmission for the terminal device. How to switch access network equipment in a double-connection scene is a problem to be solved.

Disclosure of Invention

The application provides a switching method and a switching device in a communication network, which are used for realizing switching of access network equipment in a double-connection scene.

In a first aspect, a method for handover in a communication network, where a first access network device and a second access network device are kept connected to a terminal device, where an execution body of the method is the first access network device, or a component configured in the first access network device, such as a processor, a chip, or other, or a software module, and the first access network device is taken as an example of the execution body, and the method includes: the first access network device sends a switching request to the second access network device, wherein the switching request is used for indicating the terminal device to be switched from the first access network device or the second access network device to a first target access network device, the switching request is determined by the first access network device according to a prediction result of the terminal device, and the prediction result comprises at least one of the following: predicted geographical location information of the terminal device, predicted traffic information of the terminal device, predicted measurement results of the terminal device, or predicted access or camping cell of the terminal device; alternatively, various information of the terminal device predicted included in the prediction result may be regarded as information of the terminal device predicted at a certain time or a certain period of time in the future, for example, geographical position information of the terminal device predicted at a certain time or a certain period of time in the future may be regarded as geographical position information of the terminal device predicted and the like. And the first access network equipment receives first response information from the second access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

By the method, the terminal equipment is in double connection with the first access network equipment and the second access network equipment, the first access network equipment can determine whether the first access network equipment or the second access network equipment is switched to the first target access network equipment according to the prediction result of the terminal equipment, and sends a switching request to the second access network equipment, the second access network equipment judges whether the switching request of the first access network equipment is reasonable or not, and sends first response information for indicating whether the switching request is agreed to the first access network equipment or not. Since in the current scheme, only the cell switching of the single connection scene of the terminal equipment is concerned, no corresponding solution exists for the access network equipment switching of the double connection scene of the terminal equipment. By adopting the scheme, any access network equipment in the double-connection scene can determine the switching request, the switching request can request to switch any access network equipment connected in the double-connection scene, the switching request is sent to the other access network equipment, and after the other access network equipment agrees, the switching of the access network equipment is executed, so that the switching of the terminal equipment in the access network equipment in the double-connection scene is realized.

In one design, the first access network device is an auxiliary access network device, the second access network device is a primary access network device, and the handover request is used for indicating that the terminal device is handed over from the auxiliary access network device to the first target access network device; or the first access network device is a primary access network device, the second access network device is a secondary access network device, and the switching request is used for indicating to switch the terminal device from the secondary access network device to the first target access network device; or the first access network device is an auxiliary access network device, the second access network device is a main access network device, and the switching request is used for requesting the terminal device to be switched from the main access network device to the first target access network device.

In one design, the handover request is to indicate at least one of: the switching reason, the first target access network device, the switching time, the prediction result, or the accuracy of the prediction result.

By the method, the switching request sent by the first access network device is used for indicating switching reasons, such as switching based on AI prediction, a predicted first target access network device to be switched, predicted switching time, a predicted result of the terminal device, or accuracy of the predicted result. When the second access network device receives the switching request, whether the prediction of the first access network device is reasonable or not can be determined according to the switching request, for example, whether the predicted first target access network device and the switching time are reasonable or not; and if the predicted result of the first access network device is the same as the predicted result of the second access network device, and if the predicted result of the first access network device is different from the predicted result of the second access network device, and when the predicted accuracy of the second access network device is higher, first response information for indicating rejection and the like can be sent, so that reasonable switching of the access network devices in a double-connection scene is realized.

In one design, before sending the handover request to the second access network device, the method further includes: the first access network equipment determines a prediction result according to the collected terminal equipment information; and the first access network equipment determines that the terminal equipment is switched to the first target access network equipment by the first access network equipment or the second access network equipment according to the prediction result.

By the method, the first access network device can determine the prediction result of the terminal device according to the information collected by the terminal device and the AI model. And determining that the first access network equipment or the second access network equipment needs to be switched to the first target access network equipment and the like according to the prediction result. The prediction result comprises at least one of the following: geographical location information of the predicted terminal device, traffic information of the predicted terminal device, measurement results of the predicted terminal device, or a cell in which the predicted terminal device is accessed or camping, etc. For example, the geographical location information of the predicted terminal device includes the altitude, longitude and latitude, and the like of the predicted terminal device. The first access network device may determine that the terminal device is handed over from the first access network device or the second access network device to the first target access network device based on a prediction of a future geographic location of the terminal device. For example, the first access network device determines, according to the predicted future geographic location of the terminal device, that the terminal device will go out of the coverage area of the first access network device or the second access network device in the future, and then the first access network device may determine, according to the prediction of the future geographic location of the terminal device, a first target access network device capable of providing services for the terminal device. Or, the first access network device determines, according to the prediction of the future service of the terminal device, that the current first access network device or the second access network device can no longer provide the service meeting the requirement of the future service, and then determines the first target access network device according to the requirement of the future service of the terminal device. Alternatively, the future measurement results of the terminal device include the predicted quality of the reference signal or the data signal measured by the terminal device in the future at each cell. The first access network device may determine, according to a future measurement result of the terminal device, a base station corresponding to a cell with a better reference signal or a better data signal, as the first target access network device. Alternatively, the first access network device may use the base station corresponding to the predicted future access or residence cell of the terminal device as the first target access network device, etc. With respect to a predicted future access or camping cell of a terminal device included in the prediction result, it may refer to a cell in which the terminal device is predicted to access or camp for a future period of time. For example, the predicted result may include a cell in which the predicted terminal device accesses or camps within 5 to 10 minutes in the future. The number of cells that the terminal device predicted in the prediction results may access or camp on in a future period of time may be one or more. For example, since the terminal device may move at a high speed in the future, the terminal device is predicted to access or camp on cell 1 in the future 5 minutes to 8 minutes, and the terminal device is predicted to access or camp on cell 2 in the future 8 minutes to 10 minutes, and so on. When the number of the predicted future access or residence cells of the terminal device is a plurality of, a cell meeting the condition can be selected from the plurality of cells, and the base station corresponding to the cell meeting the condition is the first target access network device indicated in the handover request message. For example, the cell closest to the current time may be selected, e.g., 5 minutes to 8 minutes into the future, cell 1 where the terminal device is predicted to be accessed or camped on, etc. Therefore, the access network equipment with double connection of the terminal equipment is ensured, reliable service can be provided for the terminal equipment, and the communication performance is improved.

In one design, when the first response information is used to instruct the second access network device to reject the handover request, the method further includes: and the first access network equipment determines second target access network equipment according to the first response information.

By the method, when the second access network equipment refuses the switching request of the first access network equipment, the second access network equipment and the like can be redetermined according to the content indicated by the second access network equipment in the first response information. For example, the response information may indicate a second target access network device and/or a recommended handover time, etc. recommended by the second access network device, and the first access network device notifies the terminal device of the second target access network device and the recommended handover time, etc. recommended by the second access network device. And the terminal equipment is switched to the second target access network equipment by the first access network equipment or the second access network equipment at the recommended switching time of the second access network equipment. Alternatively, the response information may indicate the AI model recommended by the second access network device, an intermediate variable of the AI model (e.g., a model gradient, etc.), and the first access network device may re-perform model reasoning according to the AI model recommended by the second access network device, the intermediate variable of the AI model, and the like, and re-determine the target access network device and/or the handover time, and the like. Or, the response information may indicate different parts in the prediction results of the second access network device and the first access network device on the terminal device, for example, future measurement results of the terminal device, future residence or access cells of the terminal device, or future service information of the terminal device, and the first access network device may redetermine the target access network device and/or the switching time according to the different parts in the prediction results and the same parts in the prediction results, so as to improve reliability and robustness of switching the access network device by the terminal device in the dual-connection scenario.

In one design, the method further comprises: the first access network equipment determines and modifies the service bearing distribution of the first access network equipment and the second access network equipment to the terminal equipment according to the prediction result; and the first access network equipment sends a resource modification request to the second access network equipment, wherein the resource modification request is used for requesting to modify service bearing distribution of the first access network equipment and the second access network equipment to the terminal equipment.

For example, the first access network device determines, according to a predicted future measurement result of the terminal device included in the predicted result of the terminal device, that the quality of an air interface between the first access network device and the terminal device will be poor, and then the first access network device may initiate a resource modification request to improve a proportion of the second access network device transmitted in the Split Bearer. By the method, the reliability of communication and the like can be improved.

In one design, the method further comprises: and the first access network equipment receives second response information from the second access network equipment, wherein the second response information is used for indicating the second access network equipment to agree or reject the resource modification request.

In one design, the first response information or the second response information is used to indicate at least one of:

the terminal equipment information collected by the second access network equipment; resource information of the second access network device; the second access network equipment predicts the result of the terminal equipment; the switching time recommended by the second access network equipment; the target access network equipment recommended by the second access network equipment; the second access network equipment recommends an artificial intelligence AI model; the second access network equipment recommends model intermediate parameters of the AI model; the prediction accuracy of the AI model recommended by the second access network equipment; the second access network equipment predicts the resource use condition of the first access network equipment; or the resource usage of the second access network device predicted by the second access network device.

In a second aspect, a handover method in a communication network is provided, where a first access network device and a second access network device are kept connected to a terminal device, and the method is implemented by using the second access network device, or a component, such as a processor, a chip, or other, or may be a software module, etc., configured in the second access network device, where the second access network device is taken as an implementation main example, and the method includes: the second access network equipment receives a switching request from the first access network equipment, wherein the switching request is used for indicating the terminal equipment to be switched from the first access network equipment or the second access network equipment to first target access network equipment; and the second access network equipment sends first response information to the first access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

According to the method, in the double-connection scene, the first access network device triggers the switching of the double-connection base station of the terminal device based on AI prediction, and sends a switching request to the second access network device. When the second access network equipment agrees to the switching request, the first access network equipment informs the terminal equipment of the predicted first target base station. When the second access network equipment refuses the switching request, the first access network equipment re-predicts the target base station according to the response information fed back by the second access network equipment, and realizes the base station switching of the terminal equipment in a double-connection scene.

In one design, the method further comprises: the second access network equipment determines the first response information according to a prediction result of the terminal equipment, wherein the prediction result comprises at least one of the following: the predicted geographical location information of the terminal device, the predicted traffic information of the terminal device, the predicted measurement result of the terminal device, or the predicted cell to which the terminal device accesses or camps.

In one design, the determining the first response information according to the prediction result of the terminal device includes: determining that the terminal equipment is switched from the first access network equipment or the second access network equipment to second target access network equipment according to the prediction result; when the first target access network device is different from the second target access network device and the prediction accuracy of the second access network device is higher than that of the first access network device, determining that the first response information is used for indicating to reject the switching request; otherwise, determining that the first response information is used for indicating agreement of the switching request.

By the method, the second access network equipment predicts the second target access network equipment to be switched according to the prediction result of the terminal equipment. And determining whether to agree with the switching request of the first access network equipment according to the accuracy rate of the prediction of the first access network equipment and the second access network equipment, thereby improving the switching reliability of the access network equipment in the double-connection scene.

In one design, the first access network device is an auxiliary access network device, the second access network device is a primary access network device, and the handover request is used for indicating that the terminal device is handed over from the auxiliary access network device to the first target access network device; or the first access network device is a primary access network device, the second access network device is a secondary access network device, and the switching request is used for indicating to switch the terminal device from the secondary access network device to the first target access network device; or the first access network device is an auxiliary access network device, the second access network device is a main access network device, and the switching request is used for indicating to switch the terminal device from the main access network device to the first target access network device.

In one design, the method further comprises: and the second access network equipment receives a resource modification request from the first access network equipment, wherein the resource modification request is used for requesting to modify service bearing distribution of the first access network equipment and the second access network equipment to the terminal equipment.

In one design, the method further comprises: and the second access network equipment sends second response information to the first access network equipment, wherein the second response information is used for indicating the second access network equipment to agree or reject the resource modification request.

In one design, the first response information or the second response information is used to indicate at least one of: the terminal equipment information collected by the second access network equipment; resource information of the second access network device; the second access network equipment predicts the result of the terminal equipment; the switching time recommended by the second access network equipment; the second access network equipment recommends a target access network equipment for switching; the second access network equipment recommends an artificial intelligence AI model; the second access network equipment recommends model intermediate parameters of the AI model; the prediction accuracy of the AI model recommended by the second access network equipment; the second access network equipment predicts the resource use condition of the first access network equipment; or the resource usage of the second access network device predicted by the second access network device.

In a third aspect, there is provided an apparatus, the beneficial effects of which may be seen in the description of the first aspect, the apparatus being either an access network device, or an apparatus deployed in an access network device, or an apparatus capable of being used in match with an access network device.

In one design, the apparatus includes a unit for performing the method/operation/step/action described in the first aspect, where the unit may be a hardware circuit, or software, or a combination of hardware circuits and software implementation. For example, the apparatus may comprise a processing unit and a communication unit, and the processing unit and the communication unit may perform the respective functions in any of the design examples of the first aspect described above, in particular:

a communication unit, configured to send a handover request to the second access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device, and the handover request is determined according to a prediction result of the terminal device, and the prediction result includes at least one of the following: predicted geographical location information of the terminal device, predicted traffic information of the terminal device, predicted measurement results of the terminal device, or predicted access or camping cell of the terminal device; and receiving first response information from the second access network device, wherein the first response information is used for indicating the second access network device to agree or reject the handover request.

Optionally, the processing unit is configured to determine a handover request, and/or process the first response information.

The specific implementation process of the processing unit and the communication unit may refer to the first aspect, and will not be described herein.

In another design, the apparatus includes a processor to implement the method described in the first aspect above. The apparatus may also include a memory to store instructions and/or data. The memory is coupled to the processor, and the processor may implement the method described in the first aspect when executing the program instructions stored in the memory. The apparatus may also include a communication interface for communicating with the apparatus and other devices. Illustratively, the communication interface may be a transceiver, circuit, bus, module, pin or other type of communication interface, and the other device may be a terminal device or a second access network device, etc. In one possible design, the apparatus includes:

a memory for storing program instructions;

a communication interface, configured to send a handover request to the second access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device, and the handover request is determined according to a prediction result of the terminal device, and the prediction result includes at least one of the following: predicted geographical location information of the terminal device, predicted traffic information of the terminal device, predicted measurement results of the terminal device, or predicted access or camping cell of the terminal device; and receiving first response information from the second access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

Optionally, the processor is configured to determine a handover request, and/or process the first response information.

For specific execution of the communication interface and the processor, refer to the description of the first aspect, and are not repeated.

In a fourth aspect, there is provided an apparatus, the beneficial effects of which may be seen in the second aspect, the apparatus may be an access network device, or an apparatus configured in the access network device, or an apparatus capable of being used in cooperation with the access network device.

In one design, the apparatus includes a unit for performing the one-to-one correspondence of the method/operation/step/action described in the second aspect, where the unit may be a hardware circuit, or software, or a combination of hardware circuits and software implementation. Illustratively, the apparatus may comprise a processing unit and a communication unit, and the processing unit and the communication unit may perform the respective functions in any of the design examples of the second aspect described above, in particular:

a communication unit, configured to receive a handover request from a first access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device; and sending first response information to the first access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

Optionally, the processing unit is configured to process the handover request, and/or determine response information, etc.

The specific implementation process of the processing unit and the communication unit may refer to the second aspect, and will not be described herein.

In another design, the apparatus includes a processor to implement the method described in the second aspect above. The apparatus may also include a memory to store instructions and/or data. The memory is coupled to the processor, and the processor, when executing the program instructions stored in the memory, may implement the method described in the second aspect. The apparatus may also include a communication interface for communicating with the apparatus and other devices. Illustratively, the communication interface may be a transceiver, circuit, bus, module, pin or other type of communication interface, and the other device may be a terminal device or a first access network device, etc. In one possible design, the apparatus includes:

a memory for storing program instructions;

a communication interface, configured to receive a handover request from a first access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device; and sending first response information to the first access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

Optionally, the processor is configured to process the handover request, and/or determine response information, etc.

For specific execution of the communication interface and the processor, reference may be made to the description of the second aspect, and details are not repeated.

In a fifth aspect, the application also provides a computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first or second aspects.

In a sixth aspect, the present application also provides a chip system comprising a processor, and possibly a memory, for implementing the method of any one of the first or second aspects. The chip system may be formed of a chip or may include a chip and other discrete devices.

In a seventh aspect, the application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first or second aspects.

In an eighth aspect, the present application also provides a system comprising the apparatus of the third aspect, and the apparatus of the fourth aspect.

Drawings

Fig. 1 is a schematic diagram of a communication system provided by the present application;

FIGS. 2 and 3 are schematic diagrams of model deployments provided by the application;

Fig. 4a and fig. 4b are schematic diagrams of the architecture of a communication system according to the present application;

FIG. 5 is a schematic diagram of an application of the AI model provided by the application;

FIG. 6 is a schematic diagram of a neuron provided by the present application;

FIG. 7 is a schematic diagram of a neural network provided by the present application;

fig. 8 is a schematic diagram of Qos flow transmission in a dual connectivity scenario provided in the present application;

FIG. 9 is a schematic diagram of a dual connection provided by the present application;

fig. 10 to 13 are switching flowcharts provided in the present application;

fig. 14 and 15 are schematic structural views of the device provided by the present application.

Detailed Description

Fig. 1 is a schematic architecture diagram of a communication system 1000 to which the present application can be applied. As shown in fig. 1, the communication system comprises a radio access network 100 and a core network 200, and optionally the communication system 1000 may further comprise the internet 300. The radio access network 100 may include at least one access network device (e.g., 110a and 110b in fig. 1) and may also include at least one terminal device (e.g., 120a-120j in fig. 1). The terminal equipment is connected with the access network equipment in a wireless mode, and the access network equipment is connected with the core network in a wireless or wired mode. The core network device and the access network device may be separate and different physical devices, or may be a physical device in which the functions of the core network device and the logic functions of the access network device are integrated, or may be a physical device in which the functions of a part of the core network device and the functions of a part of the access network device are integrated. The terminal device and the access network device can be connected with each other in a wired or wireless manner. Fig. 1 is only a schematic diagram, and other network devices may be further included in the communication system, for example, a wireless relay device, a wireless backhaul device, etc., which are not shown in fig. 1.

The access network device may be a base station (base station), an evolved NodeB (eNodeB), a transmission and reception point (transmission reception point, TRP), a next generation NodeB (gNB) in a fifth generation (5th generation,5G) mobile communication system, an access network device in an open radio access network (open radio access network, O-RAN), a next generation base station in a sixth generation (6th generation,6G) mobile communication system, a base station in a future mobile communication system, or an access node in a wireless fidelity (wireless fidelity, wiFi) system, etc.; or may be a module or unit that performs part of the function of the base station, for example, a Centralized Unit (CU), a Distributed Unit (DU), a centralized control plane (CU-CP) module, or a centralized user plane (CU-UP) module. The access network device may be a macro base station (e.g. 110a in fig. 1), a micro base station or an indoor station (e.g. 110b in fig. 1), a relay node or a donor node, etc. The specific technology and specific device configuration employed for the access network device in the present application are not limited.

In the present application, the means for implementing the function of the access network device may be the access network device; or means, such as a system-on-chip, a hardware circuit, a software module, or a hardware circuit plus a software module, capable of supporting the access network device to perform this function, which may be installed in the access network device or may be used in cooperation with the access network device. In the present application, the chip system may be constituted by a chip, and may include a chip and other discrete devices. For convenience of description, the following describes the technical solution provided by the present application, taking an access network device as an example, and taking an access network device as a base station as an implementation device for implementing a function of the access network device.

(1) Protocol layer structure.

The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure. For example, the control plane protocol layer structure may include the functions of protocol layers such as a radio resource control (radio resource control, RRC) layer, a packet data convergence layer protocol (packet data convergence protocol, PDCP) layer, a radio link control (radio link control, RLC) layer, a medium access control (media access control, MAC) layer, and a physical layer. For example, the user plane protocol layer structure may include the functions of protocol layers such as PDCP layer, RLC layer, MAC layer, and physical layer, and in one possible implementation, a service data adaptation protocol (service data adaptation protocol, SDAP) layer may be further included above the PDCP layer.

Optionally, the protocol layer structure between the access network device and the terminal device may further comprise an artificial intelligence (artificial intelligence, AI) layer for transmitting AI-function related data.

(2) A Central Unit (CU) and a Distributed Unit (DU).

The access device may include CUs and DUs. Multiple DUs may be centrally controlled by one CU. As an example, the interface between a CU and a DU may be referred to as an F1 interface. The Control Plane (CP) interface may be F1-C, and the User Plane (UP) interface may be F1-U. The application is not limited to the specific names of the interfaces. CUs and DUs may be divided according to the protocol layers of the wireless network: for example, the PDCP layer and above protocol layer functions are provided on the CU, and the PDCP layer below protocol layer functions (e.g., RLC layer, MAC layer, etc.) are provided on the DU; for example, the functions of the PDCP layer and the above protocol layers are set in the CU, and the functions of the PDCP layer and the below protocol layers are set in the DU, without limitation.

The above-described partitioning of CU and DU processing functions by protocol layers is only an example, and may be partitioned in other ways. For example, a CU or a DU may be divided into functions having more protocol layers, and for example, a CU or a DU may be further divided into partial processing functions having protocol layers. In one design, part of the functions of the RLC layer and the functions of the protocol layers above the RLC layer are set at CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set at DU. In another design, the functions of the CU or the DU may be further divided according to a service type or other system requirements, for example, the functions that the processing time needs to meet the delay requirement are set in the DU, and the functions that do not need to meet the delay requirement are set in the CU. In another design, a CU may also have one or more functions of the core network. Illustratively, the CUs may be provided on the network side for centralized management. In another design, a Radio Unit (RU) of the DU is set remotely. Alternatively, the RU may have radio frequency functions.

Alternatively, the DU and RU may be divided at a physical layer (PHY). For example, a DU may implement higher layer functions in the PHY layer, and an RU may implement lower layer functions in the PHY layer. Wherein, when used for transmitting, the functions of the PHY layer may include at least one of: cyclic redundancy check (cyclic redundancy check, CRC) codes, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, resource mapping, physical antenna mapping, or radio frequency transmission functions are added. For receiving, the functions of the PHY layer may include at least one of: CRC check, channel decoding, de-rate matching, descrambling, demodulation, de-layer mapping, channel detection, resource de-mapping, physical antenna de-mapping, or radio frequency reception functions. Wherein higher layer functions in the PHY layer may include a portion of functions of the PHY layer, e.g., the portion of functions closer to the MAC layer, and lower layer functions in the PHY layer may include another portion of functions of the PHY layer, e.g., the portion of functions closer to the radio frequency function. For example, higher layer functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, and layer mapping, and lower layer functions in the PHY layer may include precoding, resource mapping, physical antenna mapping, and radio frequency transmission functions; alternatively, higher layer functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, layer mapping, and precoding, and lower layer functions in the PHY layer may include resource mapping, physical antenna mapping, and radio frequency transmission functions. For example, higher layer functions in the PHY layer may include CRC checking, channel decoding, de-rate matching, decoding, demodulation, and de-layer mapping, and lower layer functions in the PHY layer may include channel detection, resource de-mapping, physical antenna de-mapping, and radio frequency reception functions; alternatively, higher layer functions in the PHY layer may include CRC checking, channel decoding, de-rate matching, decoding, demodulation, de-layer mapping, and channel detection, and lower layer functions in the PHY layer may include resource de-mapping, physical antenna de-mapping, and radio frequency reception functions.

The functionality of a CU may be implemented by one entity, or by a different entity, for example. For example, the functionality of the CU may be further divided, i.e. the control plane and the user plane are separated and implemented by different entities, namely a control plane CU entity (i.e. CU-CP entity) and a user plane CU entity (i.e. CU-UP entity), respectively. The CU-CP entity and the CU-UP entity may be coupled to a DU to together perform the functions of the access network device.

Alternatively, any one of the above DUs, CUs, CU-CPs, CU-UPs, and RUs may be a software module, a hardware structure, or a software module+hardware structure, without limitation. The existence forms of different entities can be different, and are not limited. For example, DU, CU-CP, CU-UP are software modules, RU is a hardware structure. Such modules and methods of performing the same are also within the scope of the present application.

In one possible implementation, an access network device includes a CU-CP, a CU-UP, a DU, and a RU. For example, the execution body of the present application includes, without limitation, a DU, or includes a DU and an RU, or includes a CU-CP, a DU and an RU, or includes a CU-UP, a DU and an RU. The methods performed by the modules are also within the scope of the application.

The terminal device may also be referred to as a terminal, user Equipment (UE), mobile station, mobile terminal device, etc. The terminal device may be widely used for communication in various scenarios, including, but not limited to, at least one of the following: device-to-device (D2D), vehicle (vehicle to everything, V2X), machine-type communication (MTC), internet of things (internet of things, IOT), virtual reality, augmented reality, industrial control, autopilot, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, or smart city, etc. The terminal equipment can be a mobile phone, a tablet personal computer, a computer with a wireless receiving and transmitting function, a wearable device, a vehicle, an unmanned aerial vehicle, a helicopter, an airplane, a ship, a robot, a mechanical arm, or intelligent household equipment and the like. The application does not limit the specific technology and the specific equipment form adopted by the terminal equipment.

In the present application, the means for realizing the functions of the terminal device may be the terminal device; or means, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module, capable of supporting the terminal device to implement the function, which means may be installed in the terminal device or may be used in cooperation with the terminal device. For convenience of description, the following describes the technical solution provided by the present application, taking a device for implementing a function of a terminal device as a terminal device, and taking a UE as an example.

The base station and the terminal device may be fixed in location or may be movable. The base station and/or terminal equipment may be deployed on land, including indoors or outdoors, hand-held or vehicle-mounted; the device can be deployed on the water surface; but also on aerial planes, balloons and satellites. The application does not limit the application scenes of the base station and the terminal equipment. The base station and the terminal device may be deployed in the same scenario or in different scenarios, e.g. the base station and the terminal device are deployed on land at the same time; alternatively, the base station is deployed on land, the terminal device is deployed on water, etc., which are not exemplified one by one.

The roles of base station and terminal device may be relative, e.g., helicopter or drone 120i in fig. 1 may be configured as a mobile base station, terminal device 120i being a base station for those terminal devices 120j that access radio access network 100 through 120 i; but for base station 110a 120i is a terminal device, i.e. communication between 110a and 120i is via a wireless air interface protocol. The communication between 110a and 120i may be performed by an interface protocol between the base stations, and in this case, 120i is also a base station with respect to 110 a. Thus, both the base station and the terminal device may be collectively referred to as a communication apparatus, 110a and 110b in fig. 1 may be referred to as a communication apparatus having a base station function, and 120a-120j in fig. 1 may be referred to as a communication apparatus having a terminal device function.

In the present application, an independent network element, such as an AI network element, or an AI node, etc., may be introduced into the communication system shown in fig. 1 to implement AI-related operations, and the AI network element may be directly connected to an access network device in the communication system, or may implement indirect connection through a third party network element and the access network device. The third party network element may be a core network element such as an authentication management function (authentication management function, AMF) or a user plane function (user plane function, UPF); alternatively, the AI function, AI module, or AI entity may be configured within another network element in the communication system to implement the AI-related operation, e.g., an access network device (e.g., a gNB), a core network device, or a network management (administration and maintenance, OAM), etc., where the network element performing the AI-related operation is a network element with the AI function built-in. The OAM is used for operating, managing, maintaining, and the like, with respect to the access network device and/or the core network device.

In the present application, as shown in fig. 2 or fig. 3, at least one device of a core network device, an access network device, a terminal device, or OAM, etc. may be deployed with an AI model, and a corresponding function is implemented using the AI model. In the present application, AI models deployed in different nodes may be the same or different. The model differences include at least one of the following differences: the model has different structural parameters, for example, the number of layers and/or weights of the model are different; the input parameters of the model are different; or different output parameters of the model, etc. Wherein the input parameters of the model and/or the output parameters of the model are different, which may be described as the functional differences of the model. Unlike fig. 2 described above, in fig. 3, the function of the access network device is split into CUs and DUs. Alternatively, the CUs and DUs may be CUs and DUs under an O-RAN architecture. One or more AI models may be deployed in a CU. And/or one or more AI models may be deployed in the DU. Optionally, the CUs in FIG. 3 can be further split into CU-CP and CU-UP. Alternatively, one or more AI models may be deployed in the CU-CP. And/or one or more AI models may be deployed in the CU-UP. Alternatively, in fig. 2 or fig. 3, the OAM of the access network device and the OAM of the core network device may be deployed separately.

Optionally, fig. 4a is a schematic diagram of a communication system according to the present application. As shown in fig. 4a, in a first design, a near real-time access network intelligent control (RAN intelligent controller, RIC) module is included in the access network device for model training and reasoning. For example, near real-time RIC may be used to train an AI model with which to reason. For example, the near real-time RIC may obtain information on the network side and/or the terminal device side from at least one of the CU, DU or RU, which may be training data or reasoning data. Alternatively, the near real-time RIC may submit the inference results to at least one of a CU, DU, RU, or terminal device. Alternatively, the inference results may be interacted between CU and DU. Alternatively, the inference results may be interacted between the DU and the RU, e.g., near real-time RIC submits the inference results to the DU, which is forwarded to the RU.

Alternatively, in a second design, as shown in fig. 4a, a non-real-time RIC is included outside the access network device (alternatively, the non-real-time RIC may be located in the OAM or in the core network device) for model training and reasoning. For example, non-real-time RIC is used to train an AI model with which to reason. For example, the non-real-time RIC may obtain information on the network side and/or the terminal device side from at least one of the CU, DU or RU, which may be as training data or reasoning data, which reasoning results may be submitted to at least one of the CU, DU, RU or terminal device. Alternatively, the inference results may be interacted between CU and DU. Alternatively, the inference results may be interacted between the DU and the RU, e.g., the non-real-time RIC submits the inference results to the DU, which is forwarded to the RU.

Alternatively, in a third design, as shown in fig. 4a, a near real-time RIC is included in the access network device, and a non-real-time RIC is included outside the access network device (alternatively, the non-real-time RIC may be located in the OAM or in the core network device). As with the second design described above, non-real-time RICs may be used for model training and reasoning. Alternatively, as with the first design described above, near real-time RIC may be used for model training and reasoning. Alternatively, the non-real-time RIC performs model training, and the near-real-time RIC may obtain AI model information from the non-real-time RIC, and obtain information on the network side and/or the terminal device side from at least one of the CU, the DU, or the RU, and obtain an inference result using the information and the AI model information. Alternatively, the near real-time RIC may submit the inference results to at least one of a CU, DU, RU, or terminal device. Alternatively, the inference results may be interacted between CU and DU. Alternatively, the inference results may be interacted between the DU and the RU, e.g., near real-time RIC submits the inference results to the DU, which is forwarded to the RU. For example, near real-time RIC is used to train model a, with reasoning on model a. For example, a non-real-time RIC is used to train model B, with model B being used for reasoning. For example, a non-real-time RIC is used to train model C, and information of model C is sent to a near-real-time RIC, which uses model C for reasoning.

Fig. 4b is a schematic diagram of another communication system according to the present application. In contrast to fig. 4a, fig. 4b separates CUs into CU-CP and CU-UP, etc.

An AI model is a specific implementation of the AI function, which characterizes the mapping between the input and output of the model. The AI model may be a neural network, a linear regression model, a decision tree model, a support vector machine (support vector machine, SVM), a bayesian network, a Q learning model, or other machine learning model, etc. In the present application, the AI function may include at least one of: data collection (collecting training data and/or reasoning data), data preprocessing, model training (or referred to as model learning), model information publishing (configuring model information), model verification, model reasoning, or reasoning results publishing. Where inference can also be referred to as prediction. In the present application, the AI model may be simply referred to as a model.

Fig. 5 is a schematic diagram of an application architecture of the AI model. A data source (data source) is used to store training data and reasoning data. The model training node (model trainning host) obtains an AI model by analyzing or training data (training data) provided by the data source, and deploys the AI model in the model inference node (model inference host). Optionally, the model training node may also update the AI model that has been deployed at the model reasoning node. The model inference node may also feed back relevant information of the deployed model to the model training node, so that the model training node optimizes or updates the deployed AI model, etc.

The AI model is obtained through model training node learning, which is equivalent to obtaining the mapping relation between the input and the output of the model through model training node learning by using training data. And the model reasoning node uses an AI model to conduct reasoning based on the reasoning data provided by the data source, so as to obtain a reasoning result. The method can also be described as: the model reasoning node inputs the reasoning data into the AI model, and obtains output through the AI model, wherein the output is the reasoning result. The inference results may indicate: configuration parameters used (performed) by the execution object, and/or operations performed by the execution object. The inference results may be uniformly formulated by an execution (actor) entity and sent to one or more execution objects (e.g., network entities) for execution. Alternatively, the executing entity or object may feed back the parameters or measurements it collects to the data source, a process which may be referred to as performance feedback, the parameters fed back may be as training data or reasoning data. Optionally, the executing entity or the executing object may further determine feedback information related to the performance of the model according to the reasoning result output by the model reasoning node, and feed the feedback information back to the model reasoning node, where the model reasoning node may feed back performance information of the model to the model training node according to the feedback information, so that the model training node optimizes or updates the deployed AI model, which may be referred to as model feedback.

The AI model may be a neural network or other machine learning model. Taking neural networks as an example, neural networks are one specific implementation of machine learning techniques. According to the general approximation theorem, the neural network can theoretically approximate any continuous function, so that the neural network has the capability of learning any mapping. Therefore, the neural network can accurately model the complex high-dimensional problem.

The idea of neural networks derives from the neuronal structure of brain tissue. Each neuron performs a weighted summation operation on its input value, and the weighted summation result is passed through an activation function to produce an output. As shown in fig. 6, a schematic diagram of the neuron structure is shown. Let the input of the neuron be x= [ x ₀ ,x ₁ ,…,x _n ]The weights corresponding to the inputs are w= [ w, w ₁ ,…,w _n ]The bias of the weighted sum is b. The form of the activation function may vary, assuming that the activation function of a neuron is: y=f (z) =max (0, z), the output of the neuron is:for another example, the activation function of a neuron is: y=f (z) =z, and the output of the neuron is: /> x _i 、w _i And b may be a decimal, integer (including 0, positive or negative integer, etc.), or complex number, among other possible values. The activation functions of different neurons in a neural network may be the same or different.

Neural networks generally include a multi-layer structure, each layer may include one or more neurons. Increasing the depth and/or width of the neural network may increase the expressive power of the neural network, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of the neural network may refer to the number of layers included in the neural network, and the number of neurons included in each layer may be referred to as the width of the layer. As shown in fig. 7, a layer relationship diagram of the neural network is shown. In one implementation, a neural network includes an input layer and an output layer. The input layer of the neural network transmits the result to the output layer after the received input is processed by the neurons, and the output layer obtains the output result of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network transmits the received input to the middle hidden layer after the received input is processed by the neurons, the hidden layer transmits the calculation result to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network. A neural network may include, without limitation, one or more hidden layers connected in sequence. During the training of the neural network, a loss function may be defined. The loss function describes the gap or difference between the output value of the neural network and the ideal target value, and the application is not limited to the specific form of the loss function. The training process of the neural network is a process of adjusting parameters of the neural network, such as the layer number, the width, the weight of the neurons, and/or parameters in the activation function of the neurons, so that the value of the loss function is smaller than a threshold value or meets the target requirement.

In release 17 in the third generation partnership project (3rd generation partnership project,3GPP), the discussion of AI-based UE mobility enhancements primarily focused on optimizing handover of UEs between cells. For example, the switching time and the reasonable target cell of the UE are judged in advance through the track prediction of the UE, so that switching resources are planned in advance, the time delay and the switching failure probability of the UE in the switching process are reduced, and the channel quality of the UE in the source cell and the target cell is improved. At present, for the mobility enhancement of the UE based on AI, the scene of the connection between the UE and the single base station is mainly considered, and the switching problem of the double-connection scene is not considered.

The dual connection (dual connectivity, DC), which may also be referred to as multi-radio dual connection (multi-radio dual connectivity, MR-DC), may also be replaced by a link. In a dual connectivity scenario, one UE may communicate with multiple base stations. The plurality of base stations may be base stations belonging to the same system, for example, the plurality of base stations are all 4G base stations, or 5G base stations. Alternatively, the plurality of base stations may be base stations belonging to different standards, for example, one base station of the plurality of base stations is a 4G base station, another base station is a 5G base station, and so on. The network side may provide communication services for the UE using resources of the plurality of base stations, thereby providing high rate transmission for the UE. The base station in DC that has control plane signaling interaction with the core network is called a Master Node (MN), and the other base stations are called Secondary Nodes (SNs). The serving cell under the MN is referred to as a primary cell group (master cell group, MCG) consisting of a primary cell and optionally one or more secondary cells. The serving cell under SN is called secondary cell group (secondary cell group, SCG) consisting of primary and secondary cells and optionally one or more secondary cells. Each base station of the dual connection has a different RLC/MAC entity. As shown in fig. 8, the data radio bearers (data radio Bearer, DRB) in the dual connection are divided into a primary cell group Bearer (MCG Bearer), a secondary cell group Bearer (SCG Bearer), and a Split Bearer (Split Bearer). Wherein, MCG beer is that RCL/MAC entity of the DRB is only on the main base station, SCG beer is that RLC/MAC entity of the DRB is only on the auxiliary base station, split beer is that RLC/MAC entity of the DRB is on both the main base station and the auxiliary base station. Some quality of service (Qos) packets are Qos flows that each base station can transmit, for example, by Split Bearer. Some Qos flow packets are transmitted in only one base station, for example, MCG Bearer or SCG Bearer carried Qos flow. When a base station receives a Qos flow packet from a core network, the base station needs to have an SDAP entity, and if the base station receives the packet through a PDCP entity of another base station, the base station does not need to have the SDAP entity. Alternatively, as shown in fig. 9, in the dual connection formed between different standards, both the primary base station and the secondary base station have RRC entities, and both the primary base station and the secondary base station may generate RRC messages (such as measurement messages). The secondary base station may directly send the RRC message generated by the secondary base station to the UE, in which case the RRC message sent by the UE to the secondary base station is also directly sent to the secondary base station, and the RRC message between the secondary base station and the UE is called signaling bearer No. 3 (signalling radio bearer, srb 3). Or the auxiliary base station can inform the main base station of the RRC message generated by the auxiliary base station, and the main base station transmits the RRC message to the auxiliary base station through the main base station, namely the UE transmits the RRC message to the main base station, and the main base station transmits the RRC message to the auxiliary base station. In fig. 9, the interface between the main base station or the auxiliary base station and the UE is Uu interface, the interface between the main base station and the auxiliary base station is Xn-C, and the interface between the main base station and the core network is NG-C.

In the present application, the UE may communicate with the primary base station and the secondary base station. The dual connectivity may include: an evolved universal terrestrial radio access-new air interface dual connection (evolved UMTS terrestrial radio access network, EUTRAN, universal mobile telecommunications system, UMTS, new radio, NR, EUTRA-NR dual connection, EN-DC), a next generation radio access new air interface-evolved universal terrestrial radio access dual connection (NG-RAN EUTRA-NR dual connectivity, NGEN-DC), a new air interface-evolved universal terrestrial radio access dual connection (NR-EUTRA dual connectivity, NE-DC), or a new air interface dual connection (NR dual connectivity, NR-DC), and the like. In EN-DC the primary base station is an LTE base station (e.g. eNB) connected to the 4G core network and the secondary base station is an NR base station (e.g. gNB). The main base station in NGEN-DC is an LTE base station connected with a 5G core network, and the auxiliary base station is an NR base station. The primary base station in NE-DC is an NR base station connected to a 5G core network, and the secondary base station is an LTE base station. The primary base station in NR-DC is an NR base station connected to the 5G core network, and the secondary base station is an NR base station.

As shown in fig. 10, a handover method in a communication network is provided, which is applicable to handover of a primary base station or a secondary base station in a dual connectivity scenario. For example, the communication network is configured to include a first base station and a second base station, where the first base station and the second base station are both connected for the UE, i.e. the UE is in a dual-connection scenario, and simultaneously communicates with the first base station and the second base station. Wherein, optionally, the first base station is a main base station, the second base station is an auxiliary base station, or the first base station is an auxiliary base station, and the second base station is a main base station, and the method at least comprises:

Step 1000: the first base station sends a handover request to the second base station.

The switching request is used for indicating the UE to be switched to the first target base station from the first base station or the second base station. The handover request is determined according to a prediction result for the UE. For example, the first base station has an AI model disposed therein that is trained by the first base station or that is obtained by the first base station from other third party nodes that train the AI model. And the first base station determines a prediction result of the UE according to the AI model and the collected UE information. The first base station determines that the first base station or the second base station needs to be switched to the first target base station according to the prediction result of the UE. The prediction result comprises at least one of the following: geographical location information of the predicted UE, traffic information of the predicted UE, measurement results of the predicted UE, or cells in which the predicted UE accesses or camps, etc. For example, the geographic location information of the UE includes the predicted altitude, longitude and latitude, etc. of the UE at a time or time period in the future. The first base station may determine, based on the predicted UE geographical location information, that the UE is handed over from the first base station or the second base station to the first target base station. For example, the first base station determines, according to the predicted geographic location information of the UE, that the UE will go out of coverage of the first base station or the second base station at a certain future time, and then the first base station may determine, according to the prediction of the geographic location of the UE, a first target base station capable of providing services for the UE. Or, the first base station determines, according to the prediction of the service of a certain time point or time period in the future of the UE, that the current first base station or the second base station can no longer provide the service meeting the requirement of the future service, and then determines the first target base station according to the requirement of the future service of the UE. Alternatively, the future measurement results of the UE include the quality of the reference signal or data signal measured at the respective cell by the predicted UE at a time or a time period in the future. The first base station may determine, according to a future measurement result of the UE, a base station corresponding to a cell with a better reference signal or data signal, as the first target base station. Alternatively, the first base station may use a base station corresponding to the predicted future access or camping cell of the UE as the first target base station, etc. With respect to a predicted future access or camping cell of a UE included in the prediction result, it may refer to a cell in which the UE accesses or camps for a future period of time. For example, the predicted result may include a cell in which the predicted UE accesses or camps within 5 to 10 minutes in the future. The number of cells that the UE predicted in the prediction results may access or camp on in a future period of time may be one or more. For example, since the UE may move at a high speed in the future, the UE is predicted to access or camp on cell 1 in the future 5 to 8 minutes, and the UE is predicted to access or camp on cell 2 in the future 8 to 10 minutes, and so on. When the number of the predicted future access or camping cells of the UE is plural, one cell satisfying the condition may be selected from the plural cells, and the base station corresponding to the cell satisfying the condition is the first target base station indicated in the handover request message. For example, the cell closest to the current time may be selected, e.g., 5 minutes to 8 minutes into the future, cell 1 where the predicted UE is accessed or camped, etc.

Optionally, before step 1000, the method may further include: the first base station collects UE information. For example, the UE information may be reported by the UE to the first base station, or the first base station may be acquired by a third party device. For example, the UE reports UE information to a third party device, through which the first base station obtains UE information, etc., which may be a trace data collection entity (trace collection entity, TCE). And the first base station determines a prediction result of the UE according to the UE information. For example, the first base station determines a prediction result according to the UE information and the AI model, and this process may be referred to as an inference process of the AI model. For example, the UE information is input as an AI model, or information after processing the UE information is input as an AI model. The output of the AI model is used as a prediction result for the UE, or information after the output processing of the AI model is used as a prediction result for the UE, or the like. The first base station determines that the first base station or the second base station needs to be switched to the first target base station according to the prediction result of the UE, and the specific process can be seen from the above.

Step 1001: and the second base station sends response information to the first base station, wherein the response information is used for indicating the second base station to agree or reject the switching request. Alternatively, the response information may be referred to as first response information.

For example, the second base station may determine whether the handover request of the first base station is reasonable after receiving the handover request of the first base station. If so, the second base station sends agreeable response information to the first base station; otherwise, the refused response information is sent to the second base station. Optionally, the response information is used to indicate at least one of the following:

the UE information collected by the second base station may be, but not limited to, UE information reported to the second base station by the UE, or obtained by the second base station through a third party device.

The resource information of the second base station, for example, the central processing unit (central processing unit, CPU) occupancy rate, the physical resource block (physical resource block, PRB) occupancy rate, the system power consumption, and the like of the second base station.

And the second base station predicts the UE. For example, the second base station determines a prediction result for the UE, etc., based on the AI model and the UE information. It should be noted that, in the present application, the second base station may indicate the whole result of the second base station's prediction for the UE, or indicate the partial result of the second base station's prediction for the UE, etc. in the response information, without limitation. For example, the first base station may determine a prediction result for the UE based on the AI model and the collected UE information. The second base station may indicate a different portion of the response information than the predicted result of the first base station. That is, in the present application, the second base station may additionally transmit a different part of the predicted result from the first base station to the first base station in the response information.

A second base station recommended switching time;

a target base station recommended by the second base station; in the present application, the second base station may determine the target base station according to the prediction result of the UE.

The second base station recommends AI models. The AI model may be, without limitation, used by the second base station or not.

The second base station recommends model intermediate parameters of the AI model, such as gradient parameters and the like.

Recommending the prediction accuracy of the AI model by the second base station;

the second base station predicts the resource use condition of the first base station;

or the resource usage of the second base station predicted by the second base station, etc.

Optionally, before step 1001, the method may further include: and the second base station determines a prediction result of the UE according to the collected UE information. For example, an AI model is set in the second base station, and the second base station determines a prediction result for the UE according to the collected UE information and the AI model. For example, the second base station uses the collected UE information or the information obtained by processing the collected UE information as an input of an AI model, and outputs the AI model as a prediction result of the UE by the second base station, or uses the information obtained by processing the output of the AI model as a prediction result of the UE, or the like. Similar to the foregoing, the UE may report UE information to the second base station, or the UE may report UE information to the third party device, where the second base station obtains UE information through the third party device, and so on. The AI model in the second base station may be trained for the second base station, or for a third party device, etc. And the second base station determines a response message according to the predicted result of the UE. For example, the number of the cells to be processed,

And the second base station determines that the UE is switched to the second target base station from the first base station or the second base station according to the prediction result of the UE. The second base station judges whether a second target base station predicted by the second base station is the same as a first target base station predicted by the first base station; it should be noted that the second target base station predicted by the second base station may be the same as the first target base station predicted by the first base station, being one base station. When the first target base station is different from the second target base station and the prediction accuracy of the second base station is higher than that of the first base station, response information sent by the second base station to the first base station is used for indicating to reject the switching request of the first base station; otherwise, the response information sent by the second base station to the first base station is used for indicating to agree to the switching request of the first base station.

Optionally, if the response information is used to instruct the second base station to agree to the handover request, the first base station may notify the UE of the first target base station. Optionally, the second base station may also notify the UE of the handover time corresponding to the first target base station. And the UE is switched to the first target base station by the first base station or the second base station at the switching time. Or if the response information is used for indicating the second base station to reject the switching request, the first base station re-determines the target base station according to the response information. For example, the response information may indicate a second target base station recommended by the second base station and/or a recommended handover time, etc., and the first base station informs the UE of the second target base station recommended by the second base station and the recommended handover time, etc. And the UE is switched to the second target base station at the switching time recommended by the second base station by the first base station or the second base station. Or,

The response information may indicate an intermediate variable (e.g., a model gradient, etc.) of the AI model and the AI model recommended by the second base station, and the first base station may re-perform model reasoning according to the intermediate variable (e.g., the model gradient, etc.) of the AI model and the AI model recommended by the second base station, re-determine the target base station and/or the handover time, etc. Or,

the response information may indicate different parts of the prediction results of the second base station and the first base station on the UE, for example, future measurement results of the UE, cells where the UE resides or accesses in the future, or future service information of the UE, and the first base station may redetermine the target base station and/or the handover time according to the different parts of the prediction results and the same part of the prediction results.

Optionally, the first base station may further perform the following operations: the first base station determines to modify the service bearing distribution of the first base station and the second base station to the UE according to the prediction result of the UE; the method comprises the steps that a first base station sends a resource modification request to a second base station, wherein the resource modification request is used for requesting to modify service bearing distribution of the first base station and the second base station to UE. For example, the first base station determines that the quality of the air interface between the first base station and the UE will be poor according to the predicted future measurement result of the UE included in the predicted result of the UE, and then the first base station may initiate a resource modification request to increase the proportion of the second base station for transmission in the Split Bearer, so as to increase the reliability. See the description of fig. 8 above for Split Bearer. Optionally, the second base station may further send response information to the first base station, where the response information is used to instruct the second base station to agree to or reject the resource modification request. Alternatively, the response information may be referred to as second response information, and the description in the aforementioned first response information may be referred to as to the content indicated in the second response information. For example, the second base station may determine response information of the resource modification request according to the prediction result. For example, the second base station may determine, according to the prediction result, whether the service bearer allocation predicted by the second base station is the same as the service bearer allocation predicted by the first base station; if the two are different, and the accuracy rate of the service bearer allocation predicted by the first base station is higher than that predicted by the second base station, the response information sent by the second base station to the first base station is used for indicating to agree with the resource modification request; otherwise, the response information sent by the second base station to the first base station is used for indicating that the resource modification request is refused, and the like. It should be noted that, the scheme of determining, by the first base station, the service bearer allocation for the UE and sending the resource modification request to the second base station according to the prediction result, and the foregoing processes of step 1100 and step 1101 may be decoupled, for example, the foregoing scheme in fig. 10 may be used alone, or the scheme of modifying the service bearer of the UE may be used alone, or both may be used in combination, without limitation.

By the method, in the double-connection scene of the UE, the first base station triggers the switching of the double-connection base station of the UE based on AI prediction, and sends a switching request to the second base station. When the second base station agrees to the handover request, the first base station informs the UE of the predicted first target base station. When the second base station refuses the switching request, the first base station re-predicts the target base station according to the response information fed back by the second base station, and realizes the base station switching of the UE in the double-connection scene.

As shown in fig. 11, a handover method in a communication network is provided, which is applicable to a base station handover in a UE dual connectivity scenario. In a dual connectivity scenario, one UE may communicate with multiple base stations, including a MN and SN. In the flow of fig. 11, the case where the SN transmits the handover request and the MN transmits the response information is described as an example where the first base station is SN and the second base station is MN in the flow of fig. 10. The process at least comprises the following steps:

step 1100: the MN and SN collect UE information. This step 1100 is optional.

In the application, the UE can report the UE information to the MN or the SN, or the MN or the SN can acquire the information reported by the UE from the TCE. Optionally, the UE may report UE information to the TCE in a minimization of drive tests (minimization of drive test, MDT) manner. By way of example, the MN and SN may acquire UE information in the same or different manners, either simultaneously or at different times, without limitation.

By way of example, the UE information includes at least one of: geographical location information of the UE, traffic information of the UE, data service information of the UE, quality of reference signals or data signals measured by the UE, or identity of a cell in which the UE is accessing or camping, etc. Geographic location information of the UE, such as longitude and latitude and altitude of the UE, and the like. The data service information of the UE includes at least one of: qos information, service type, or data size of various types of services, etc. The quality of the reference signal or data signal measured by the UE includes: reference signal received power (reference signal receiving power, RSRP) of a reference signal or data signal measured by the UE, reference signal received quality (reference signal receiving quality, RSRQ), or the like. Alternatively, the UE may measure the quality of the reference signal or the data signal in a cell unit, the reference signal or the data signal measured by the UE is in a cell level, or the UE may measure the quality of the reference signal or the data signal in a beam unit, the reference signal or the data signal measured by the UE is in a beam level, or the like. It will be appreciated that the above description of UE information including content is not intended to be limiting of the application. Any information that helps to obtain the UE prediction result may be referred to as UE information.

Step 1101: the MN and SN interact with the AI model used by each. This step 1101 is optional.

In the application, the MN and the SN are internally provided with AI models for predictive reasoning, and the MN and the SN can interact the AI models used by the MN and the SN through an X2 interface, an Xn interface and the like. For MN and SN, the AI model may be trained in a third party device such as an OAM, cloud server, core network device, etc., and MN or SN may request the trained AI model from the third party device. Alternatively, the MN or SN may train the AI model itself, and then make predictive reasoning directly with the trained AI model. Alternatively, the MN and the SN may interact with each collected data information in addition to the AI model used by each.

In one design, the content of the MN and SN interactions includes: each using an identification of the AI model. For example, the identification of the AI model may be represented by a bit code, e.g., the identification of the AI model is 00001, etc. Optionally, the MN and SN may also interact with at least one of the following information, each using an AI model: types of AI models are used each; prediction accuracy rates each using an AI model; the prediction accuracy of the AI model is expressed as a percentage, for example, the prediction accuracy of the AI model is 95%. The prediction accuracy of the AI model may be a historical prediction accuracy of the AI model, or a prediction accuracy that can be achieved based on currently collected data, etc. A confidence interval representing the probability of a UE entering a certain cell coverage over a period of time. Or the data information collected by each of the MN and the SN, where the data information may include, in addition to the UE information in the foregoing step 1100: the MN and SN correspond to information of the base station, such as an occupancy rate of a central processing unit (central processing unit, CPU) of the base station, an occupancy rate of physical resource blocks (physical resource block, PRB), and system power consumption.

Step 1102: and the MN and the SN predict the UE according to the AI model and the UE information to obtain a prediction result. This step 1102 is optional.

In the present application, the MN or SN may input the respective collected UE information as an input into an AI model, which outputs are referred to as prediction results. Alternatively, the MN or SN processes the collected UE information, and the processed information is input to the AI model, and the output of the AI model is processed, and the processed information is called a prediction result or the like. Alternatively, the inputs of the AI model are processed and the outputs are not processed, the outputs of the AI model being referred to as the prediction results. Alternatively, the input of the AI model is not processed, the output of the AI model is processed, and the processed information is called a prediction result or the like. The predicted result may include geographical location information of the predicted UE, measurement results of the predicted UE, a cell in which the predicted UE camps or accesses, traffic information of the predicted UE, and the like. The predicted geographic location information of the UE includes: and the predicted height, longitude and latitude and other information of the UE at a certain moment or in a certain time period of the future UE. The measurement result of the predicted UE may be a quality of a reference signal or a data signal of a cell level or a beam level measured by the UE at each cell, etc. at a future point of time or a time interval. The predicted service information of the UE may be a future time point or time interval, a service type of the UE, a data size and Qos requirements of various types of services, and the like. It is to be appreciated that the UE information collected by the MN or SN in the foregoing step 1100 can be collected UE history information, current information of the UE, or the like. For example, the UE geographical location information collected in the foregoing step 1100 may be collected UE historical geographical location information, and/or UE current geographical location information, etc.

Step 1103: the SN may determine a target SN, which is an SN to be switched for SN prediction, according to a prediction result of the UE. This step 1103 is optional.

Optionally, the SN may also determine a handover time, etc. according to a prediction result for the UE. For example, the predicted outcome for the UE represents: after a subsequent period of time, e.g. after 5S, the UE may leave the coverage of good channel quality of the current connection SN or move into the coverage of a target SN, which is the predicted SN to which the UE moves, the SN may determine that the handover time is a point in time before 5S. Alternatively, the predicted outcome of the UE represents: next, the future service requirement of the UE, the current SN cannot meet the requirement or the two cells of the current dual connection cannot meet, etc. The SN may determine a handover time according to a time of handover of the UE for future traffic. The SN selects a base station capable of satisfying the service requirement according to the future service requirement of the UE as a target SN, etc.

Step 1104: the SN sends a handoff request to the MN.

The handover request is used for indicating that the UE is handed over from the SN to the target SN, and the handover request is used for indicating at least one of the following: the reason for handover, the target SN, the time for handover, the predicted result, or the accuracy of the predicted result, etc. The reason for the handover may be that the SN needs to be switched based on AI prediction, the target SN is the SN to be switched of the UE determined according to the prediction result, for example, the prediction result includes the geographical location information of the predicted UE, and according to the geographical location information of the predicted UE, it is determined that the UE will enter into the coverage area of a certain SN in a period of time, and then the certain SN is the target SN. For details of the prediction results, reference may be made to the description in step 1102.

Step 1105: the MN sends response information to the SN indicating that the MN agrees or denies the handover request.

Illustratively, the MN can determine the prediction based on the collected UE information and AI model. For example, the MN takes UE information as input of an AI model, the output of which is a prediction result. The MN determines a target SN, which may be referred to as a MN predicted target SN, based on the prediction. The target SN determined by the SN in step 1103 may be referred to as an SN predicted target SN. In one design, the handover request includes indication information of an SN predicted target SN, and the MN determines the SN predicted target SN when receiving the handover request of the SN. The MN may also obtain the accuracy of SN prediction. The SN prediction accuracy rate, the MN may be obtained through a handover request sent by the SN, that is, the handover request in step 1104 further includes indication information of the SN prediction accuracy rate. Alternatively, in the foregoing step 1101, the MN and the SN have interacted in advance with each using the accuracy of the AI model, or the like. The MN compares the target SN predicted by the MN with the target SN predicted by the SN, and whether the target SN predicted by the MN and the target SN are identical; if the two are the same, the response information sent by the MN to the SN is used for indicating the MN to agree with the switching request; if the two are different, comparing the accuracy of MN prediction with the accuracy of SN prediction. If the accuracy of the MN prediction is high, the response information sent by the MN to the SN is used to instruct the MN to reject the handover request. If the accuracy of the SN prediction is high, the response information sent by the SN to the MN is used for indicating the MN to agree to the handover request. If the accuracy of the two is the same, the response information sent by the MN to the SN may indicate that the MN agrees with the handover request, or may indicate that the MN refuses the handover request, etc., without limitation. Optionally, the MN may also consider the predicted handoff time when determining the response information: for example, the SN predicted handoff time may also be indicated in the handoff request sent by the SN to the MN. The MN determines, based on the prediction, a predicted handoff time, which may be referred to as a MN predicted handoff time, in addition to the target SN. The MN can judge whether the difference between the SN predicted switching time and the MN predicted switching time is within a preset threshold range or not; if the response information is within the threshold range, the MN sends response information for indicating agreement to the SN; otherwise, the MN sends response information for indicating rejection to the SN.

In another design, the MN may determine the MN's prediction based on its own collected UE information and AI model. When receiving a switching request of the SN, the MN comprises indication information of an SN prediction result, and acquires the SN prediction result in the switching request. If the predicted result of the MN is consistent with the predicted result of the SN, the MN sends agreeable response information to the SN; if the prediction results of the two are inconsistent, for example, the predicted target SN is inconsistent, and the prediction accuracy of the MN is higher than that of the SN, the MN sends refused response information to the SN; otherwise, MN sends agreed response information to SN. For the procedure of MN obtaining the prediction accuracy of SN, see the foregoing.

Optionally, if the MN agrees to the SN handover request, the MN may supplement the SN with indication information of at least one of the following: UE information collected by MN, resource information of MN, or prediction result of MN, etc. I.e. when the response information sent by the MN to the SN is used to indicate that the MN agrees to the handover request of the SN, then the response information is used to indicate at least one of: UE information collected by MN, resource information of MN, or prediction result of MN, etc. Optionally, if the MN agrees to the handover request of the SN, the SN sends the SN predicted target SN and the handover time to the UE. And when the UE reaches the switching time, switching the SN in the dual connection to the target SN. UE information collected by the MN which is supplemented to the SN by the MN, resource information of the MN or prediction results of the MN and the like are used as reserves and can be used later. For example, when continuing model reasoning using the AI model, the subsequent SN may consider not only UE information collected by the SN itself as input, but also UE information collected by the MN as input, and the like.

If the MN rejects the handover request of the SN, the MN may send to the SN indication information of at least one of: the method comprises the steps of switching time recommended by the MN, target SN recommended by the MN, a prediction result of the MN, an AI model recommended by the MN, a model intermediate variable of the AI model recommended by the MN, prediction accuracy of the AI model recommended by the MN, resource use condition of the MN for predicting the MN, or SN resource application condition predicted by the MN and the like. That is, when response information sent by the MN to the SN is used to instruct the MN to reject the handover request of the SN, the response information is used to instruct at least one of: the method comprises the steps of switching time recommended by the MN, target SN recommended by the MN, a prediction result of the MN, an AI model recommended by the MN, a model intermediate variable of the AI model recommended by the MN, prediction accuracy of the AI model recommended by the MN, resource use condition of the MN for predicting the MN, or SN resource application condition predicted by the MN and the like. The SN may re-determine the target SN based on the response information sent by the MN. For example, in a scenario where the MN rejects the handover request of the SN, when the above-mentioned response information is used to indicate the MN recommended handover time and the MN recommended target SN, the SN may notify the UE of the MN's pushed handover time and the MN recommended target SN as truly predicted handover time and target SN. Alternatively, when the above-mentioned response information is used to indicate the MN recommended AI model and the model intermediate variable of the recommended AI model, the SN may perform model reasoning again according to the MN recommended AI model and the model intermediate variable (e.g., model gradient, etc.), determine the switching time, the target SN, etc., and notify the UE. Note that the AI model recommended to the SN with respect to the MN may be an AI model used by the MN, or another AI model suitable for SN prediction recommended by the MN, or the like, without limitation. In one design, when the MN recommends an AI model to the SN, the SN may request a specific AI model from a third party device that trains the AI model. The above process can be described as: when the MN refuses the switching request of the SN, the SN redetermines the target SN according to the response information of the MN. The foregoing ways in which the SN re-determines the target SN according to the response information of the MN, and in the schematic diagram of fig. 11, the process of re-performing model reasoning according to the information indicated in the response information is described with emphasis. As an example, one use for MN notification SN, predicted resource usage of MN, or predicted SN resource usage is: as described above, the resource usage cases regarding MN or SN include CPU occupancy, PRB occupancy, system power, and the like of the corresponding base station. In a dual connectivity scenario, the MN and SN may simultaneously carry the traffic of the UE. The traffic bearer allocation of the MN and SN to the UE may be adjusted according to the predicted MN resource usage, and/or the predicted SN resource usage, etc. For example, according to the prediction result, in a future period, the MN resource usage is higher, and the SN resource usage is lower, so that the proportion of the MN to carry UE services can be increased, and the proportion of the SN to carry UE services can be reduced. For example, for the Split Bearer in fig. 8, the transmission ratio of the Bearer in the primary base station MN may be increased, and the transmission ratio of the Bearer in the secondary base station SN may be reduced. Alternatively, in a dual connectivity scenario, the MN and SN may independently carry the traffic of the UE. Also, according to the prediction result, in a future period, the MN resource usage is higher, and the SN resource usage is lower, so that the MN can be adjusted to not bear UE traffic any more, and only SN bears UE traffic, etc. For example, for traffic in the UE, it may be transmitted only in the secondary cell group Bearer SCG Bearer, and no longer in the primary cell group Bearer MCG Bearer.

For example, the handover request in the foregoing step 1104 may be S node change request (S-node change required) signaling described in the standard of the 3GPP protocol 38.423, the response information in the foregoing step 1105 may be S node change acknowledgement (S-node change confirm) in the foregoing standard when the MN agrees to the handover request, or the response information in the foregoing step 1105 may be S node change rejection (S-node change refuse) in the foregoing standard when the MN rejects the handover request.

Alternatively, in the present application, the SN may initiate a resource modification (resource modification) request based on predictions of traffic information for the UE, channel quality variations, resource conditions for the SN and MN, etc. For example, the SN may determine to modify the assignment of MN and SN to UE traffic bearers based on the prediction of the UE. The SN may send a resource modification request to the MN requesting modification of traffic bearers of the MN and SN to the UE. For example, according to the prediction result, if it is determined that the air interface quality of the SN-UE will be poor, the SN may initiate a resource modification request to increase the proportion of MN to transmission in Split Bearer, so as to improve reliability. Or, according to the prediction result, it is determined that the dual-connection resource of the SN is limited, a resource modification request may be initiated to the MN to request the MN to carry more beaters or protocol data units (protocol data unit, PDU) sessions, or according to the prediction result, it is determined that two cells currently dual-connected by the UE cannot satisfy the service request of the UE, then a resource modification request may be initiated to the MN to request to change the two cells currently dual-connected by the UE, and so on. After receiving the resource modification request sent by the SN, the MN may send response information to the MN. The response information may grant or deny the resource modification request of the SN. For example, if the MN is consistent with the SN according to the prediction result of the UE, the obtained service bearer allocation is consistent with the SN; or the two are inconsistent, but the accuracy of the SN is higher, the MN agrees to the resource modification request of the SN; otherwise, the MN refuses the resource modification request of the SN. The resource modification request and the handover request in step 1104 may be reported together, for example, both may be carried in the same information for reporting, or both may be reported separately, for example, the SN sends different information to the MN, and reports the handover request and the resource modification request separately. Similarly, the response information to the resource modification request, together with the response information in step 1105 described above, may be sent by MN to SN, or the MN may separately send two response information to SN, respectively, and the like, without limitation.

Alternatively, for the SN initiated resource modification request, it may be an S node modification request (S-node modification required) described in the 3GPP protocol 38.423 standard. If the MN agrees with the resource modification request, the response message replied to by the MN may modify the acknowledgement for the S node (S-node modification confirm). Alternatively, if the MN rejects the resource modification request, the response message replied to by the MN may modify the rejection for the S node (S-node modification refuse).

Illustratively, the SN receives the response information of the MN. If the response information indicates that the MN agrees with the handover request, or if the response information indicates that the MN refuses the handover request, the target SN is redetermined according to the response information. The SN may send an SN switch request, such as an S-node change request (S-node change required), to the determined target SN to request that the dual-connected SN be switched from the original SN to the target SN, etc.

The prediction accuracy of MN and SN is described as follows: the SN determines a prediction result according to the AI model and the UE information. And the SN determines the target SN according to the prediction result. The accuracy of the SN prediction result may be considered as the accuracy of the SN predicted target SN, or the accuracy of the SN predicted modified traffic bearer, or as the SN prediction accuracy. Similarly, the accuracy of the MN prediction result may be considered as the accuracy of the MN predicted target SN, or the accuracy of the MN predicted modified service bearer, or the accuracy of the MN prediction. The process of machine learning, for example, includes:

1. Model training is performed by using the training set to obtain an AI model, and the process is called model training.

Model training is one of the important parts in machine learning, which is the essence of learning certain features of the training set from its training samples so that the difference between the output of the AI model and the ideal target value is as small as possible under the training of the training set. In general, the weights and/or outputs of AI models trained using different training sets may not be the same, even with the same network architecture. Therefore, the composition and selection of the training set determines, to some extent, the performance of the AI model.

2. The AI model is validated using a validation set, a process known as model validation.

Model verification typically occurs during model training. For example, each time the model is trained over one or more iterations (epochs), the current AI model can be validated with a validation set to monitor the state of model training, e.g., to verify whether the model has been under-fitted, over-fitted, or has converged, etc., to determine whether to end the training. Optionally, during the model verification process, the super-parameters of the model may also be adjusted, where the super-parameters may refer to at least one of the following parameters of the model: the number of layers of the neural network, the number of neurons, the activation function, or the loss function, etc.

3. AI models are tested using a test set, a process called model testing.

After model training is completed, the trained AI model can be tested using a test set. For example, evaluating generalization ability of an AI model, judging whether AI model performance satisfies a requirement or not, or deciding whether an AI model is available or not, or the like.

In one design, the performance index of the AI model may be determined during the model test, where the performance index of the AI model includes the prediction accuracy of the AI model, which is the accuracy of the prediction result. Taking supervised learning as an example, the device for testing the AI model can compare the output of the AI model with the corresponding label (namely accurate output) and determine the error of the output of the AI model and the corresponding label; and determining the performance index of the AI model according to the error of the AI model and the AI model. In the case of unsupervised learning or reinforcement learning, no tag of the AI model exists, and the performance index of the AI model may be determined from the output of the AI model. For example, when the output of the AI model is a predicted result for the UE. At a future point in time or within a certain period of time, the UE may compare the predicted information for the UE with the actual information of the UE, determine a performance index of the AI model, etc. The prediction accuracy of the AI model may refer to a historical prediction accuracy of the AI model, or a prediction accuracy that can be achieved based on the currently collected UE data, and the like.

According to the method, the SN is introduced into the dual-connection, the target SN of switching is predicted according to the geographic information or service information of the UE, and the switching request or the service adjustment request is initiated to the MN, and the SN is switched or the service is adjusted according to the feedback of the MN, so that the robustness (namely the stability) and the accuracy of the AI in the dual-connection DC scene are improved, the switching efficiency of the UE is improved, the switching failure probability is reduced, and the service experience of the UE is improved.

As shown in fig. 12, a flow of a handover method in a communication network is provided, and unlike the method of fig. 11, in fig. 12, a handover request of an SN is initiated by an MN, and the SN feeds back response information to the MN, and the like, and includes at least:

step 1200: the MN and SN collect UE information. This step 1200 is optional.

Step 1201: the MN interacts with the SN with the AI model used respectively.

Optionally, the MN and the SN may also interact with each other using at least one of the following information of the AI model: the type of each AI model used, the prediction accuracy of each AI model used, the confidence interval, or the data each collected, etc. The data used by each MN and SN may further include, in addition to the UE information collected in the foregoing step 1200: the MN and the SN respectively correspond to the information of the base station. This step 1201 is optional.

Step 1202: the MN and the SN determine a prediction result for predicting the UE according to the AI model and the UE information. This step 1202 is optional.

Step 1203: the MN may determine the target SN based on the prediction of the UE. The target SN is the MN predicted SN to be handed off. This step 1203 is optional.

Step 1204: the MN sends a handover request to the SN, the handover request indicating that the SN to which the UE is connected is handed over from the SN to the target SN.

Step 1205: the SN sends response information to the MN indicating that the SN agrees or denies the handover request.

Similar to the flow in fig. 11 described above, the SN may determine a prediction result based on the collected UE collection information; and determining the target SN according to the prediction result. In contrast, the SN can determine whether the target SN requested by the MN is reasonable. For example, the SN may compare whether the SN predicted target SN is the same as the MN predicted target SN; if the target SN predicted by the MN is the same or different, but the accuracy of the target SN predicted by the MN is higher, the MN is considered to be reasonable in prediction, and consent response information is sent to the SN; otherwise, the prediction of the MN is considered unreasonable, and refused response information is sent to the SN.

In the flow shown in fig. 12, if the response information indicates that the SN agrees with the handover request, the MN notifies the UE of the target SN predicted by the MN, the handover time, and the like. And when the UE reaches the switching time, switching from the SN to the target SN. If the response information indicates that the MN refuses the handover request, the MN may perform model reasoning again according to the recommended AI model and the recommended model intermediate parameter indicated in the response information, and determine the target SN.

Similar to the flow shown in fig. 11, the MN may determine, according to the prediction result of the UE, allocation of the MN and SN service bearers; the MN sends a resource modification request to the SN, the resource modification request indicating modification of the allocation of MN and SN traffic bearers. The SN sends response information to the MN, the response information being used to instruct the SN to agree to the modification of the service bearer allocation requested by the MN, or instruct the SN to refuse the modification of the service bearer allocation requested by the MN. Illustratively, the SN may determine whether the traffic bearer allocation requested by the MN is appropriate; if the service bearer allocation determined by the MN and the SN is the same or the service bearer allocation determined by the MN and the SN is different, but the accuracy of the service bearer allocation determined by the MN is higher, the MN sends agreeable response information to the SN; otherwise, MN sends refused response information to SN. The resource modification request and the handover request may be reported together or separately, without limitation. The response information of the resource modification request and the response information of the previous handover request may be reported together or separately, etc.

Alternatively, for the MN initiated resource modification request, it may be an S node modification request (S-node modification required) described in the 3GPP protocol 38.423 standard. If the SN agrees with the resource modification request, the response information of the SN reply may be an S-node modification request acknowledgement (S-node modification request acknowledge). Alternatively, if the SN rejects the resource modification request, the response message replied to by the MN may be an S-node modification request rejection (S-node modification request reject).

For example, after receiving the response information of the SN, if the response information indicates that the SN agrees with the handover request, or the response information indicates that the SN refuses the handover request, the MN re-determines the target SN according to the response information. The MN sends a cancel connection request, e.g., an S-node cancel request, to the SN of the original connection (S-node release request). If the SN of the original connection agrees to the request to cancel the connection, the MN sends a new SN connection request to the target SN, which may be an S node addition request (S-node addition request).

According to the method, in the dual-connection, the MN predicts the target SN of switching according to the geographic position or service information of the UE and the like, sends a switching request to the SN, and determines the target SN to be switched according to feedback of the SN, so that the robustness and the accuracy of using the AI in the dual-connection scene are improved, the switching efficiency of the UE is improved, the switching failure probability is reduced, and the service experience of the UE is improved.

As shown in fig. 13, there is provided a flow of a handover method in a communication network, unlike the foregoing fig. 11 and 12, in fig. 13, a handover request for handing over an MN is initiated by an SN, and the MN feeds back response information of the handover request to the SN, including at least:

Step 1300: the MN and SN collect UE information. This step 1300 is optional.

Step 1301: the MN interacts with the SN with the AI model used respectively. This step 1301 is optional.

Step 1302: the MN and the SN determine a prediction result for predicting the UE according to the AI model and the UE information. This step 1302 is optional.

Step 1303: the SN may determine the target MN based on the prediction of the UE. The target MN is a dual connectivity MN to which the UE needs to be handed over. This step 1303 is optional.

Step 1304: the SN sends a handover request to the MN, the handover request indicating handover of the UE-connected MN to the target MN.

Step 1305: the MN sends response information to the SN indicating that the MN agrees or denies the handover request.

The flow shown in fig. 13 is similar to the flow shown in fig. 11 described above, except that in the flow shown in fig. 13, SN determines a target MN to be handed over in dual connectivity based on the prediction result. Similarly, the SN sends a handoff request to the MN, the MN determines whether the SN predicted target MN is appropriate, and sends response information to the SN.

Through the method, the SN in the dual connection can initiate switching or service adjustment requirements of the MN according to the geographic position of the UE, the service and the like, and the MN feeds back the switching or service adjustment requirements, so that the robustness and the accuracy of using the AI in a dual connection scene are improved, the switching efficiency of the UE is improved, the probability of switching failure is reduced, and the service experience of the UE is improved.

It will be appreciated that, in order to implement the functions in the above method, the base station includes corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the elements and method steps of the various examples described herein may be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application scenario and design constraints imposed on the solution.

Fig. 14 and 15 are schematic structural diagrams of possible communication devices provided by the present application. These communication devices can be used to implement the functions of the base station in the above method, and thus can also realize the advantageous effects provided by the above method. In the present application, the communication device may be the base station 115a or 115b as shown in fig. 1, or may be a module (e.g., a chip) applied to the base station.

As shown in fig. 14, the communication apparatus 1400 includes a processing unit 1410 and a transceiving unit 1420. The communication device 1400 is configured to implement the functions of the first base station or the second base station in the method illustrated in fig. 10.

When the communication apparatus 1400 is used to implement the function of the first base station in the method shown in fig. 10, the first base station and the second base station in fig. 10 may be referred to as a first access network device and a second access network device, respectively, in the communication network, where the first access network device and the second access network device are kept connected to the terminal device: the transceiver unit 1420 is configured to send a handover request to the second access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device, and the handover request is determined according to a prediction result of the terminal device, and the prediction result includes at least one of the following: predicted geographical location information of the terminal device, predicted traffic information of the terminal device, predicted measurement results of the terminal device, or predicted access or camping cell of the terminal device; and receiving first response information from the second access network device, wherein the first response information is used for indicating the second access network device to agree or reject the handover request. Optionally, the processing unit 1410 is configured to determine the handover request, and/or process the first response information.

When the communication apparatus 1400 is used to implement the function of the second base station in the method shown in fig. 10, the first base station and the second base station in fig. 10 may be referred to as a first access network device and a second access network device, respectively, in the communication network, where the first access network device and the second access network device are kept connected to the terminal device: the transceiver unit 1420 is configured to receive a handover request from a first access network device, where the handover request is used to instruct handover of the terminal device from the first access network device or the second access network device to a first target access network device, and send first response information to the first access network device, where the first response information is used to instruct the second access network device to agree to or reject the handover request. Optionally, the processing unit 1410 is configured to: processing the switching request and/or determining the first response information.

A more detailed description of the processing unit 1410 and the transceiver unit 1420 may be directly obtained by referring to the related description in the method shown in fig. 10, and will not be repeated here.

As shown in fig. 15, the communication device 1500 includes a processor 1510 and an interface circuit 1520. The processor 1510 and the interface circuit 1520 are coupled to each other. It is understood that the interface circuit 1520 may be a transceiver or an input-output interface. Optionally, the communication device 1500 may further comprise a memory 1530 for storing instructions to be executed by the processor 1510 or for storing input data required by the processor 1510 to run instructions or for storing data generated after the processor 1510 runs instructions.

When the communication device 1500 is used to implement the above method, the processor 1510 is used to implement the functions of the processing unit 1410, and the interface circuit 1520 is used to implement the functions of the transceiver unit 1420.

When the communication device is a module applied to a base station, the base station module realizes the function of the base station in the method. The base station module receives information from other modules (such as radio frequency modules or antennas) in the base station, the information being sent by the terminal device to the base station; alternatively, the base station module transmits information to other modules (e.g., radio frequency modules or antennas) in the base station, which the base station transmits to the terminal device. The base station module may be a baseband chip of a base station, or may be a DU or other module, where the DU may be a DU under an open radio access network (open radio access network, O-RAN) architecture.

It is to be appreciated that the processor of the present application may be a central processing unit (central processing unit, CPU), other general purpose processor, digital signal processor (digital signal processor, DSP), application specific integrated circuit (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. The general purpose processor may be a microprocessor, but in the alternative, it may be any conventional processor.

The memory in the present application may be random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. The storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. In addition, the ASIC may reside in a base station or terminal device. The processor and the storage medium may reside as discrete components in a base station or terminal device.

The methods of the present application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions of the present application are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user device, a core network device, an OAM, or other programmable apparatus. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; but also optical media such as digital video discs; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage medium.

In the present application, if there is no special description or logic conflict, terms and/or descriptions between different embodiments have consistency and may mutually refer, and technical features in different embodiments may be combined to form new embodiments according to their inherent logic relationships.

In the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. In the text description of the present application, the character "/", generally indicates that the associated objects are an or relationship; in the formula of the present application, the character "/" indicates that the front and rear associated objects are a "division" relationship. "comprising at least one of A, B or C" may mean: comprises A; comprises B; comprising C; comprises A and B; comprises A and C; comprises B and C; including A, B and C.

It will be appreciated that the various numerical numbers referred to in this disclosure are merely for ease of description and are not intended to limit the scope of the present application. The sequence number of each process does not mean the sequence of the execution sequence, and the execution sequence of each process should be determined according to the function and the internal logic.

Claims

1. A method of handover in a communication network, wherein a first access network device and a second access network device in the communication network remain connected to a terminal device, the method comprising:

the first access network device sends a switching request to the second access network device, where the switching request is used to instruct to switch the terminal device from the first access network device or the second access network device to a first target access network device, the switching request is determined by the first access network device according to a prediction result of the terminal device, and the prediction result includes at least one of the following: predicted geographical location information of the terminal device, predicted traffic information of the terminal device, predicted measurement results of the terminal device, or predicted access or camping cell of the terminal device;

the first access network device receives first response information from the second access network device, where the first response information is used to instruct the second access network device to agree or reject the handover request.

2. The method of claim 1, wherein the first access network device is a secondary access network device and the second access network device is a primary access network device, the handover request being for indicating a handover of the terminal device from the secondary access network device to the first target access network device; or,

The first access network device is a primary access network device, the second access network device is a secondary access network device, and the switching request is used for indicating to switch the terminal device from the secondary access network device to the first target access network device; or,

the first access network device is an auxiliary access network device, the second access network device is a main access network device, and the switching request is used for requesting the terminal device to be switched from the main access network device to the first target access network device.

3. The method of claim 1 or 2, wherein the handover request is to indicate at least one of:

the switching reason, the first target access network device, the switching time, the prediction result, or the accuracy of the prediction result.

4. A method according to any of claims 1 to 3, wherein before sending a handover request to the second access network device, the method further comprises:

the first access network equipment determines a prediction result according to the collected terminal equipment information;

and the first access network device determines that the terminal device is switched to the first target access network device by the first access network device or the second access network device according to the prediction result.

5. The method of any of claims 1 to 4, wherein when the first response information is used to instruct the second access network device to reject the handover request, the method further comprises:

and the first access network equipment determines second target access network equipment according to the first response information.

6. The method of any one of claims 1 to 5, wherein the method further comprises:

the first access network device determines to modify service bearer allocation of the first access network device and the second access network device to the terminal device according to the prediction result;

the first access network device sends a resource modification request to the second access network device, where the resource modification request is used to request modification of service bearer allocation of the first access network device and the second access network device to the terminal device.

7. The method of claim 6, wherein the method further comprises:

the first access network device receives second response information from the second access network device, where the second response information is used to instruct the second access network device to agree or reject the resource modification request.

8. The method of any one of claims 1 to 7, wherein the first response information or the second response information is used to indicate at least one of:

the terminal equipment information collected by the second access network equipment;

resource information of the second access network device;

the second access network equipment predicts the result of the terminal equipment;

the switching time recommended by the second access network equipment;

the target access network equipment recommended by the second access network equipment;

the second access network equipment recommends an artificial intelligence AI model;

the second access network equipment recommends model intermediate parameters of the AI model;

the prediction accuracy of the AI model recommended by the second access network equipment;

the second access network equipment predicts the resource use condition of the first access network equipment;

or the resource usage of the second access network device predicted by the second access network device.

9. A method of handover in a communication network, wherein a first access network device and a second access network device in the communication network remain connected to a terminal device, the method comprising:

the second access network device receives a switching request from the first access network device, wherein the switching request is used for indicating to switch the terminal device from the first access network device or the second access network device to the first target access network device;

And the second access network equipment sends first response information to the first access network equipment, wherein the first response information is used for indicating the second access network equipment to agree or reject the switching request.

10. The method of claim 9, wherein the method further comprises:

the second access network device determines the first response information according to a prediction result of the terminal device, wherein the prediction result comprises at least one of the following: the predicted geographical location information of the terminal device, the predicted traffic information of the terminal device, the predicted measurement result of the terminal device, or the predicted cell to which the terminal device accesses or camps.

11. The method of claim 10, wherein the determining the first response information based on the prediction of the terminal device comprises:

the second access network device determines that the terminal device is switched from the first access network device or the second access network device to a second target access network device according to the prediction result;

the second access network device determines that the first response information is used for indicating rejecting the handover request when the first target access network device is different from the second target access network device and the prediction accuracy of the second access network device is higher than the prediction accuracy of the first access network device; otherwise, determining that the first response information is used for indicating agreement of the switching request.

12. A method according to any of claims 9 to 11, wherein the first access network device is a secondary access network device and the second access network device is a primary access network device, the handover request being for indicating a handover of the terminal device from the secondary access network device to the first target access network device; or,

the first access network device is an auxiliary access network device, the second access network device is a main access network device, and the switching request is used for indicating to switch the terminal device from the main access network device to the first target access network device.

13. The method of any of claims 9 to 12, wherein the handover request is to indicate at least one of:

14. The method of any one of claims 9 to 13, wherein the method further comprises:

The second access network device receives a resource modification request from the first access network device, where the resource modification request is used to request modification of service bearer allocation of the first access network device and the second access network device to the terminal device.

15. The method of claim 14, wherein the method further comprises:

and the second access network equipment sends second response information to the first access network equipment, wherein the second response information is used for indicating the second access network equipment to agree or reject the resource modification request.

16. The method of any one of claims 9 to 15, wherein the first response information or the second response information is used to indicate at least one of:

resource information of the second access network device;

the switching time recommended by the second access network equipment;

the second access network equipment recommends a target access network equipment for switching;

17. A communication device comprising means for implementing the method of any one of claims 1 to 8.

18. A communication device comprising a processor and a memory, the processor and memory coupled, the processor configured to implement the method of any one of claims 1-8.

19. A communication device comprising means for implementing the method of any one of claims 9 to 16.

20. A communication device comprising a processor and a memory, the processor and memory coupled, the processor configured to implement the method of any one of claims 9 to 16.

21. A communication system comprising a communication device according to claim 17 or 18, and a communication device according to claim 19 or 20.

22. A computer readable storage medium having instructions stored thereon which, when run on a computer, cause the computer to perform the method of any of claims 1 to 8 or the method of any of claims 9 to 16.

23. A computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 8 or the method of any one of claims 9 to 16.