CN115802398A - Interference optimization method and device, storage medium and electronic equipment - Google Patents
Interference optimization method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115802398A CN115802398A CN202111050926.8A CN202111050926A CN115802398A CN 115802398 A CN115802398 A CN 115802398A CN 202111050926 A CN202111050926 A CN 202111050926A CN 115802398 A CN115802398 A CN 115802398A
- Authority
- CN
- China
- Prior art keywords
- interference
- station
- base station
- data
- interfered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000006870 function Effects 0.000 claims abstract description 84
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 50
- 230000002787 reinforcement Effects 0.000 claims abstract description 25
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 230000009471 action Effects 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 14
- 230000000875 corresponding effect Effects 0.000 claims description 11
- 238000003491 array Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012098 association analyses Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 7
- 210000004027 cell Anatomy 0.000 description 60
- 230000002452 interceptive effect Effects 0.000 description 19
- 238000012545 processing Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 7
- 230000006855 networking Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012517 data analytics Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 101100182248 Caenorhabditis elegans lat-2 gene Proteins 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The disclosure provides an interference optimization method, an interference optimization device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring index data; calling a clustering algorithm of a management data analysis MDA functional structure of a network management system, judging whether interference exists or not based on index data, and determining a disturbed station and a disturbed cell under the condition that the interference exists; under the condition that interference exists, an MDA function is called to determine a macro base station, and an interference station is determined according to an interfered cell and the macro base station; calling a reinforcement learning algorithm of an MDA (multiple access) function structure, and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station; and transmitting the interference optimization strategy to the interference applying station and/or the interfered station to realize interference optimization. The method can confirm the interference phenomenon, determine the interfered station and the interference applying station, generate the interference optimization strategy and issue by introducing a data analysis management service (MDAS) mechanism from the angle of network management full control, thereby realizing the dominant interference optimization full closed loop flow of the network management side.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an interference optimization method and apparatus, a storage medium, and an electronic device.
Background
In the development of 5G technology, the application of the TDD band TDD flexible duplex networking configuration scheme can meet the requirement of users in the 5G industry for large uplink capacity, but cross interference often occurs under the application of the scheme.
In the related art, the base station side can actively identify the problem, the interfered side determines the interference source, and the related staff manually configures the optimization strategy. In the existing interference optimization method, the calculation complexity of a base station side is high, information loss often exists in information transmission between a disturbed station and an interference applying station, the timeliness for solving the interference problem is reduced, and therefore the data quality of a user is influenced.
It is noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide an interference optimization method, an interference optimization device, electronic equipment and a storage medium, and provides the interference optimization method executed by a network management system.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, there is provided an interference optimization method, including:
collecting index data; calling a clustering algorithm for analyzing MDA functional structure by management data, judging whether interference exists or not based on index data, and determining a disturbed station and a disturbed cell under the condition that the interference exists; under the condition that interference exists, calling an MDA function to determine a macro base station, and determining an interference station according to an interfered cell and the macro base station; calling a reinforcement learning algorithm of an MDA functional structure, and generating an interference optimization strategy based on interfered station information of an interfered station and interference station information of an interference station; and transmitting the interference optimization strategy to the interference applying station and/or the interfered station to realize interference optimization.
In one embodiment of the present disclosure, the metric data includes: the terminal reports the measurement report MR data of the base station and the base station performance data reported by the base station; wherein the basic field of the MR data comprises: a base station identifier and a base station cell identifier; the dedicated fields of the MR data include: reference signal received power, RSRP; the basic fields of the base station performance data include: a base station identifier and a base station cell identifier; the dedicated field of the base station performance data comprises: uplink throughput and uplink Physical Resource Block (PRB) scheduling resources; and after the index data is collected, the method further comprises the following steps: and the MR data and the base station performance data are stored in an associated mode through the same basic field.
In an embodiment of the present disclosure, invoking a clustering algorithm for managing data analysis MDA functional structure, determining whether interference exists based on index data, and determining a victim station and a victim cell under the condition that interference exists, includes: calling an MDA function to obtain index data, and extracting PRB scheduling resources, RSRP and uplink throughput fields in the index data to form a three-dimensional array; calling an MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result; judging whether clustering data meeting preset conditions exist in the clustering result; if so, determining that interference exists; and after the interference is determined to exist, determining the interfered station and the interfered cell from the clustering data meeting the preset conditions.
In one embodiment of the present disclosure, invoking an MDA function, and performing a clustering analysis on a three-dimensional array by using a k-means algorithm to obtain a clustering result, includes: dividing the p three-dimensional arrays into k initial sets by taking the number of the three-dimensional arrays as an observation value p; wherein k is not more than p; and clustering by taking the minimized sum of squares in the cluster as a target to obtain k result sets as clustering results.
In an embodiment of the present disclosure, determining whether clustering data meeting a preset condition exists in the clustering result includes: calculating the PRB scheduling resource average value, the RSRP average value and the uplink throughput average value of each result set in the k result sets; determining PRB scheduling resource mean difference, RSRP mean difference and uplink throughput mean difference of each two result sets according to the PRB scheduling resource mean, the RSRP mean and the uplink throughput mean of each two result sets; comparing the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference of each two result sets with a PRB scheduling resource threshold, an RSRP threshold and an uplink throughput threshold in preset conditions respectively, and judging whether the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference which meet the inequality relation in the preset conditions exist or not; and if the cluster data exists, determining a result set related to the PRB scheduling resource mean difference value, the RSRP mean difference value and the uplink throughput mean difference value which meet the inequality relation in the preset condition as the cluster data meeting the preset condition.
In one embodiment of the present disclosure, the uplink throughput threshold is greater than 3 times the PRB scheduling resource threshold, and the uplink throughput threshold is greater than 3 times the RSRP threshold.
In an embodiment of the present disclosure, determining a victim station and a victim cell from clustered data satisfying a preset condition includes: for clustering data which is formed by every two result sets and meets preset conditions, taking the result set with the smaller average value of the uplink throughput as a target set; and respectively taking the base station and the cell in the target set as a disturbed station and a disturbed cell.
In an embodiment of the present disclosure, invoking an MDA function to determine a macro base station includes: calling an MDA function to extract longitude and latitude data of the base station from the base station parameters; and determining the base station with the distance to the interfered station smaller than the distance threshold value as a macro base station based on the latitude and longitude data of the base station.
In one embodiment of the present disclosure, determining an interfering station according to an interfered cell and a macro base station includes: calling an MDA function to extract remote interference management reference signal RIM-RS information of the macro base station; the RIM-RS information of the macro base station comprises: a macro base station cell identifier, a macro base station beam identifier and interference information sent by an interfered cell; performing association analysis on the RIM-RS information and the disturbed cell, and determining a disturbing station from the macro base station; wherein, the disturbing station information of the disturbing station comprises: interference station identification, interference cell identification and interference beam identification.
In one embodiment of the present disclosure, a reinforcement learning algorithm of an MDA functional structure is invoked, and an interference optimization strategy is generated based on interference station information of an interference station and interference station information of an interference station, including: constructing an objective function and corresponding constraint conditions; the objective function is the maximization of weighted values of the throughputs of all users under the interfered station and the throughputs of all users under the interfered station; and constructing a deep reinforcement learning algorithm to solve an interference optimization strategy according to the objective function and the constraint condition.
In one embodiment of the present disclosure, a deep reinforcement learning algorithm is constructed to solve an interference optimization strategy according to an objective function and constraint conditions, including: configuring an action set and a state set;
constructing a policy network and an action evaluation network; the strategy network and the action evaluation network adopt the same three-layer network structure; determining a strategy based on policy strategy according to the action set and the state set by using a strategy network; and solving the strategy convergence by using the action evaluation network to obtain an interference optimization strategy.
In one embodiment of the present disclosure, the set of actions includes: the interference station adjusts the interference wave beam SSB direction, the interference station reduces the transmission power by 3dB, the interference station reduces the transmission power by 6dB, and the time slot resource which generates interference by the interference station and the time slot resource which generates interference by the interfered station are closed; the state set includes: and PRB scheduling resources, RSRP and uplink throughput which are scheduled in the performance data and the MR data reported by the interfered station.
In an embodiment of the present disclosure, after issuing the interference optimization policy to the interfering station and/or the victim station, the method further includes: and acquiring optimized index data of the interfered station and the interfered cell, calling an MDA function, and judging whether interference exists or not based on the optimized index data so as to realize optimized feedback.
According to another aspect of the present disclosure, there is provided an interference optimization apparatus, including:
the data acquisition module is used for acquiring index data; the judging disturbed module is used for calling a clustering algorithm for analyzing the MDA functional structure by the management data and judging whether the disturbance exists or not based on the index data; the interference determining module is used for determining an interference station and an interference cell under the condition that interference exists; the interference station determining module is used for calling an MDA function to determine a macro base station under the condition that interference exists, and determining an interference station according to the interfered cell and the macro base station; the generation strategy module is used for calling a reinforcement learning algorithm of an MDA functional structure and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station; and the issuing module is used for issuing the interference optimization strategy to the interference applying station and/or the interfered station so as to realize interference optimization.
In one embodiment of the present disclosure, the index data includes: the terminal reports the measurement report MR data of the base station and the base station performance data reported by the base station; wherein the basic field of the MR data comprises: a base station identifier and a base station cell identifier; the dedicated fields of the MR data include: reference signal received power, RSRP; the basic fields of the base station performance data include: a base station identifier and a base station cell identifier; the dedicated field of the base station performance data includes: uplink throughput and uplink Physical Resource Block (PRB) scheduling resources; and after the index data is collected, the method further comprises the following steps: and performing associated storage on the MR data and the base station performance data through the same basic field.
In an embodiment of the present disclosure, the determining that the disturbed node invokes a clustering algorithm that manages data analysis MDA functional structure, determines whether there is interference based on the index data, and determines the disturbed station and the disturbed cell under the condition that there is interference, including: calling an MDA function to obtain index data, and extracting PRB scheduling resources, RSRP and uplink throughput fields in the index data to form a three-dimensional array; calling an MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result; judging whether clustering data meeting preset conditions exist in the clustering result; if so, determining that interference exists; and after the interference is determined to exist, determining the interfered station and the interfered cell from the clustering data meeting the preset conditions.
In an embodiment of the present disclosure, the determining that the disturbed module calls an MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result includes: dividing the p three-dimensional arrays into k initial sets by taking the number of the three-dimensional arrays as an observation value p; wherein k is not more than p; and clustering by taking the minimized sum of squares in the clusters as a target to obtain k result sets as clustering results.
In an embodiment of the present disclosure, the determining whether cluster data meeting a preset condition exists in the clustering result by the disturbed module includes: calculating the PRB scheduling resource average value, the RSRP average value and the uplink throughput average value of each result set in the k result sets; determining PRB scheduling resource mean difference, RSRP mean difference and uplink throughput mean difference of each two result sets according to the PRB scheduling resource mean, the RSRP mean and the uplink throughput mean of each two result sets; comparing the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference of each two result sets with a PRB scheduling resource threshold, an RSRP threshold and an uplink throughput threshold in preset conditions respectively, and judging whether the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference which meet inequality relations in the preset conditions exist or not; and if the cluster data exists, determining a result set related to the PRB scheduling resource mean difference value, the RSRP mean difference value and the uplink throughput mean difference value which meet the inequality relation in the preset condition as the cluster data meeting the preset condition.
In one embodiment of the present disclosure, the uplink throughput threshold is greater than 3 times the PRB scheduling resource threshold, and the uplink throughput threshold is greater than 3 times the RSRP threshold.
In an embodiment of the present disclosure, the determining a victim station module determines a victim station and a victim cell from clustered data that satisfy a preset condition, including: for clustering data which is formed by every two result sets and meets preset conditions, taking the result set with the smaller average value of the uplink throughput as a target set; and respectively taking the base station and the cell in the target set as a victim station and a victim cell.
In an embodiment of the present disclosure, determining that the perturbation applying station module invokes the MDA function to determine the macro base station includes: calling an MDA function to extract longitude and latitude data of the base station from the base station parameters; and determining the base station with the distance from the interfered station smaller than the distance threshold value as a macro base station based on the latitude and longitude data of the base station.
In an embodiment of the present disclosure, the determining an interfering station module determines an interfering station according to an interfered cell and a macro base station, including: calling an MDA function to extract remote interference management reference signal (RIM-RS) information of the macro base station; the RIM-RS information of the macro base station comprises: a macro base station cell identifier, a macro base station beam identifier and interference information sent by an interfered cell; performing association analysis on the RIM-RS information and the disturbed cell, and determining a disturbing station from the macro base station; wherein, the disturbing station information of the disturbing station comprises: interference station identification, interference cell identification and interference beam identification.
In an embodiment of the present disclosure, the generation policy module invokes a reinforcement learning algorithm of an MDA functional structure, and generates an interference optimization policy based on interference station information of the interference station and interference station information of the interference station, including: constructing an objective function and corresponding constraint conditions; the objective function is the maximization of weighted values of the throughputs of all users under the interfered station and the throughputs of all users under the interfering station; and constructing a deep reinforcement learning algorithm to solve an interference optimization strategy according to the objective function and the constraint condition.
In one embodiment of the present disclosure, the strategy generation module constructs a deep reinforcement learning algorithm to solve the interference optimization strategy according to an objective function and constraint conditions, and includes: configuring an action set and a state set;
constructing a policy network and an action evaluation network; the strategy network and the action evaluation network adopt the same three-layer network structure; determining a strategy based on policy strategy according to the action set and the state set by using a strategy network; and solving the strategy convergence by using the action evaluation network to obtain an interference optimization strategy.
In one embodiment of the present disclosure, the set of actions includes: the interference station adjusts the SSB direction of interference beams, reduces the transmission power by 3dB, reduces the transmission power by 6dB, closes the time slot resources generating interference by the interference station and closes the time slot resources generating interference by the interfered station; the state set includes: and the performance data reported by the interfered station and the PRB scheduling resource, RSRP and uplink throughput which are scheduled in the MR data.
In an embodiment of the present disclosure, the issuing module is further configured to: after the interference optimization strategy is issued to the interfering station and/or the interfered station, the method further comprises the following steps: and acquiring optimized index data of the interfered station and the interfered cell, calling an MDA function, and judging whether interference exists or not based on the optimized index data so as to realize optimized feedback.
According to yet another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the above-mentioned interference optimization method.
According to still another aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the interference optimization method described above via execution of the executable instructions.
The interference optimization method provided by the embodiment of the disclosure can confirm the interference phenomenon, determine the interfered station, determine the interference applying station, generate the interference optimization strategy and send the interference optimization strategy to the interfered station and/or the interference applying station by introducing the data analysis management service MDAS mechanism from the perspective of network management full control, thereby realizing the full closed loop flow of interference optimization leading by the network management side.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
Fig. 1 shows a schematic diagram of an exemplary system architecture to which the interference optimization method of an embodiment of the present disclosure may be applied;
fig. 2 shows a flow chart of an interference optimization method of one embodiment of the present disclosure;
fig. 3 illustrates a flow chart of a method of determining whether interference is present according to one embodiment of the present disclosure;
FIG. 4 illustrates a flow chart of a method of determining a victim station according to one embodiment of the present disclosure;
fig. 5 shows a flow chart of a method of determining offender stations in the presence of interference according to one embodiment of the present disclosure;
fig. 6 illustrates a flow diagram of a method of generating an interference optimization strategy according to an embodiment of the present disclosure;
fig. 7 shows a schematic diagram of an apparatus for implementing interference optimization according to an embodiment of the present disclosure;
fig. 8 shows a block diagram of an interference optimization apparatus of one embodiment of the present disclosure; and
fig. 9 shows a block diagram of an interference optimization computer device in an embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.
In 5G applications, for the problem of cross interference existing in a TDD band flexible duplex networking configuration scheme adopted to meet the requirement of a user in 5G industry for large uplink capacity, interference optimization scheme research has been performed in the industry from an interfering side and a disturbed side, respectively, and the selection of interference optimization strategies under different loads or coverage is analyzed.
At present, the 3gpp tr28.809 protocol determines roles and roles of MDAS (Management Data Analytics services) in a network Management system in a Management cycle, and the Data Analytics Management services can identify the problem of network performance degradation based on a machine learning model, accurately identify the root cause of the problem, optimize the strategy solution problem, and determine an interactive feedback mechanism between a user and a provider, and Data input information and output attributes of a relevant scene. However, the following problems exist in the current standards and implementations: 1) The full control management and the specific analysis method at the network management side are lacked. At present, a solution to the cross interference problem of a TDD band flexible duplex networking configuration scheme is that a base station side actively identifies an interference problem, a victim station sends a signal to an aggressor station to determine an interference source, and then a network management configuration interference optimization strategy is manually obtained, so that on one hand, the computational complexity of the base station side is increased, and the method is lack of flexibility. On the other hand, information loss exists in information transmission between the interfered station and the interference applying station, so that timeliness of solving the interference problem is reduced, and data quality of a user is intermittently influenced; 2) Further, the network management side lacks a specific data processing mechanism for the scenario: the interference problem needs to be identified by using an MDA (Management Data analysis) function to achieve a full control mechanism of the Network manager, so as to obtain an interference optimization strategy, however, a specific analysis process for the scene is lacked in the current standard, a centralized Data acquisition unit at a RAN (Radio Access Network) side cannot be guided to perform corresponding index Data acquisition and Data analysis directions, the requirement of an output attribute cannot be determined, and the implementation of an interference optimization intelligent solution under the scene is affected.
Based on this, exemplary embodiments of the present disclosure provide an interference optimization method for solving at least one or all of the above technical problems.
Fig. 1 shows a schematic diagram of an exemplary system architecture to which the interference optimization method of the embodiments of the present disclosure may be applied; as shown in fig. 1:
the system architecture may include a server 101, a network 102, and a client 103. Network 102 serves as a medium for providing communication links between clients 103 and server 101. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The server 101 may provide services for network management control, and may be a server providing various services, for example, a background management server providing functional services such as providing index data reported by a receiving terminal (client 103), determining whether an interference phenomenon exists according to the index data, determining a victim station and a victim station when the interference phenomenon exists, generating an interference optimization policy, and issuing the interference optimization policy. Namely: the background management server arranged in the network management system can confirm whether an interference phenomenon exists according to the index data reported by the client 103, determine the interfered station and the interference applying station, generate an interference optimization strategy and issue the interference optimization strategy, so that a master interference optimization full closed-loop flow of the network management side is realized, and the data quality of the client 103 is improved.
The client 103 may be a mobile terminal such as a mobile phone, a game console, a tablet computer, an electronic book reader, smart glasses, a smart home device, an AR (Augmented Reality) device, a VR (Virtual Reality) device, or the client 103 may also be a personal computer such as a laptop computer, a desktop computer, and the like.
In some optional embodiments, after receiving the index data reported by the client 103, the server 101 may call a clustering algorithm for managing data analysis MDA functional structure to determine whether interference exists according to the index data, and determine the interfered station and the interfered cell in the presence of interference; an MDA function can be called to determine a macro base station so as to determine an interference station according to the interfered cell and the macro base station; and then, calling a reinforcement learning algorithm of an MDA function structure, and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference applying station information of the interference applying station so as to issue the interference optimization strategy to the interference applying station and/or the interfered station, thereby realizing interference optimization. The server 101 may also collect optimized index data reported by the client 103 in the victim station and the victim cell after issuing the interference optimization strategy, so as to implement optimization feedback.
It should be understood that the number of clients, networks, and servers in fig. 1 is only illustrative, and the server 101 may be a single entity server, a server cluster composed of multiple servers, and a cloud server, and may have any number of clients, networks, and servers according to actual needs.
Hereinafter, each step of the interference optimization method in the exemplary embodiment of the present disclosure will be described in more detail with reference to the drawings and the embodiments.
Fig. 2 shows a flow chart of an interference optimization method of one embodiment of the present disclosure. The method provided by the embodiment of the present disclosure may be executed by a server or a client as shown in fig. 1, but the present disclosure is not limited thereto.
In the following description, the server cluster 101 is used as an execution subject for illustration.
As shown in fig. 2, the interference optimization method provided by the embodiment of the present disclosure may be executed by a network management system, and includes the following steps:
step S201, index data is collected.
In some embodiments, the network management system may collect and monitor MR (Measurement Report) data reported by the terminal to the base station and performance data reported by the base station within a certain time period, where the index data may include: the terminal reports the measurement report MR data of the base station and the base station performance data reported by the base station; wherein the basic field of the MR data comprises: a base station identifier and a base station cell identifier; the dedicated fields of the MR data include: RSRP (Reference Signal Received Power); the basic fields of the base station performance data include: a base station identifier and a base station cell identifier; the dedicated field of the base station performance data includes: uplink throughput, and uplink Physical Resource Block (PRB) scheduling resources; and after the index data is acquired, the MR data and the base station performance data can be stored in a correlated mode through the same basic field.
And step S203, calling a clustering algorithm for analyzing the MDA function structure by the management data, judging whether interference exists or not based on the index data, and determining the interfered station and the interfered cell under the condition that the interference exists. And S205, under the condition that interference exists, calling an MDA function to determine a macro base station, and determining an interference station according to the interfered cell and the macro base station. And step S207, calling a reinforcement learning algorithm of an MDA functional structure, and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station. And step S209, transmitting the interference optimization strategy to the interference applying station and/or the interfered station to realize interference optimization.
The application provides an interference optimization method executed by a network management system and based on network management data analysis and processing, which has the main ideas that: in a TDD (time division duplex) flexible duplex networking scene deployed for 5G large uplink users, a network management system acquires MR (magnetic resonance) data reported by a terminal and index data such as base station performance reported by a base station in real time, calls a clustering algorithm of an MDA (multiple access measurement platform) functional structure to analyze PRB (physical resource block), RSRP (reference signal power) and uplink throughput data to actively identify the existence of an interference phenomenon, and finds out a disturbed station; when interference exists, RIM-RS signal information of macro base stations around the interfered station can be analyzed to locate the found interfering station; and then, a reinforcement learning algorithm constructed by MDA is called to analyze and generate an interference optimization strategy so as to issue configuration information of the interference optimization strategy to a corresponding interference applying station or a corresponding interfered station (to) to complete interference optimization processing. The network management system utilizes the MDA function to realize the fully-controlled closed-loop flow of interference problem identification, disturbed station and interference source determination and interference optimization strategy generation.
In some embodiments, invoking a clustering algorithm for managing data analysis MDA functional structure, determining whether interference exists based on index data, and determining a victim station and a victim cell in the presence of interference, includes: calling an MDA function to obtain index data, and extracting PRB scheduling resources, RSRP and uplink throughput fields in the index data to form a three-dimensional array; calling an MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result; judging whether clustering data meeting preset conditions exist in the clustering result; if so, determining that interference exists; and after the interference is determined to exist, determining the interfered station and the interfered cell from the clustering data meeting the preset conditions.
Fig. 3 is a flowchart illustrating a method for determining whether there is interference according to an embodiment of the present disclosure, and as shown in fig. 3, the method includes:
step 301, invoking an MDA function to obtain index data, and extracting PRB scheduling resources, RSRP and uplink throughput fields in the index data to form a three-dimensional array;
step 303, calling an MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result;
step 305, judging whether clustering data meeting preset conditions exist in the clustering result; if yes, it is determined in step 307 that interference exists; if not, then at step 309 it is determined that there is no interference.
Further, in some embodiments, the network management system may invoke an MDA function, and perform cluster analysis on the three-dimensional array using a k-means algorithm to obtain a clustering result, including: dividing the p three-dimensional arrays into k initial sets by taking the number of the three-dimensional arrays as an observation value p; wherein k is not more than p; and clustering by taking the minimized sum of squares in the clusters as a target to obtain k result sets as clustering results.
The MDA function of the network administrator can be used to analyze the data to identify whether interference is present. In particular, a three-dimensional array may be subjected to clustering analysis based on a k-means algorithm, wherein the array may be defined as (X) 1 ，X 2 ，...，X p ) According toThe number of the arrays defines an observation value p, and each group of data may include the PRB, RSRP, and uplink throughput field; then clustering p groups of the observed targets into k (wherein k is<Set of k result sets S = { S = p) result sets 1 ，S 2 ，...，S k And clustering by taking the minimized square sum in the cluster as a target.
Wherein the target can be defined as:
μ i is the cluster center point of each group.
After clustering is finished, a clustering grouping identifier (such as: 1, 2, 3 \8230; \8230k) can be added behind each group of data to serve as a final clustering result for output.
In some embodiments, the determining whether clustering data meeting a preset condition exists in the clustering result includes: calculating PRB scheduling resource average value, RSRP average value and uplink throughput average value of each result set in the k result sets; determining PRB scheduling resource mean difference, RSRP mean difference and uplink throughput mean difference of each two result sets according to the PRB scheduling resource mean, the RSRP mean and the uplink throughput mean of each two result sets; comparing the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference of each two result sets with a PRB scheduling resource threshold, an RSRP threshold and an uplink throughput threshold in preset conditions respectively, and judging whether the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference which meet inequality relations in the preset conditions exist or not; and if the cluster data exists, determining a result set related to the PRB scheduling resource mean difference value, the RSRP mean difference value and the uplink throughput mean difference value which meet the inequality relation in the preset condition as the cluster data meeting the preset condition. Further, in some embodiments, the uplink throughput threshold is greater than 3 times the PRB scheduling resource threshold, and the uplink throughput threshold is greater than 3 times the RSRP threshold.
The average values of PRB, RSRP and throughput of each result set in the clustering results can be calculated, pairwise comparison is carried out, and whether data meeting the following conditions exist or not is screened:
||Avg prb_i -Avg prb_j ||＜A&||Avg rsrp_i -Avg rsrp_j ||＜B&||Avg thp_i -Avg thp_j ||＞C
any two result sets S can be determined first i And S j ，Avg prb_i And Avg prb_j Respectively representing PRB scheduling resource average values of the two result sets; avg rsrp_i And Avg rsrp_j Respectively representing RSRP average values of the two result sets; avg thp_i And Avg thp_j Respectively representing the average values of the uplink throughputs of the two result sets; wherein A represents a PRB scheduling resource threshold, B represents an RSRP threshold, C represents an uplink throughput threshold, values of A and B can be determined by referring to practical application, and the relationship among A, B and C should be maintained as follows: c is more than 3 times of A, and C is more than 3 times of B.
In some embodiments, determining the victim station and the victim cell from the clustered data satisfying the preset condition includes: for clustering data which is formed by every two result sets and meets preset conditions, taking the result set with the smaller average value of the uplink throughput as a target set; and respectively taking the base station and the cell in the target set as a victim station and a victim cell.
When two result sets meet the inequality relation, it can be considered that the terminals related to the two result sets have the problem of cross link interference, a set with a lower average value of uplink throughput in the two sets can be extracted, and corresponding base stations and cells in the sets are respectively used as interfered stations and interfered cells to be output.
Fig. 4 shows a flowchart of a method for determining a victim station according to an embodiment of the present disclosure, as shown in fig. 4, including:
step 401, calculating PRB scheduling resource average value, RSRP average value and uplink throughput average value of each result set in k result sets;
step 403, determining a PRB scheduling resource mean difference value, a RSRP mean difference value and an uplink throughput mean difference value of each two result sets according to the PRB scheduling resource mean value, the RSRP mean value and the uplink throughput mean value of each two result sets;
step 405, comparing the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference of each two result sets with a PRB scheduling resource threshold, an RSRP threshold and an uplink throughput threshold in preset conditions respectively;
step 407, when a PRB scheduling resource mean difference value, an RSRP mean difference value and an uplink throughput mean difference value which meet the inequality relationship in the preset condition exist, determining a result set related to the PRB scheduling resource mean difference value, the RSRP mean difference value and the uplink throughput mean difference value which meet the inequality relationship in the preset condition as clustering data which meet the preset condition;
step 409, regarding the clustering data which is formed by every two result sets and meets the preset conditions, taking the result set with the smaller average value of the uplink throughput as a target set;
and step 411, taking the base station and the cell in the target set as a victim station and a victim cell respectively.
In some embodiments, invoking MDA functionality to determine the macro base station comprises: calling an MDA function to extract longitude and latitude data of the base station from the base station parameters; and determining the base station with the distance from the interfered station smaller than the distance threshold value as a macro base station based on the latitude and longitude data of the base station.
The network management system can extract longitude and latitude data in the base station working parameters, so that the longitude and latitude data of the interfered station and the longitude and latitude data of the first macro base station in the peripheral range of the interfered station are obtained, and the first macro base station with the distance S between the interfered station and the first macro base station in the threshold range D is found out to serve as the macro base station in the embodiment.
The calculation method for calculating the distance S between the two base stations according to the longitude and latitude (Lat 1, lng 1) (Lat 2 ) of the two base stations is as follows:
in some embodiments, determining the offender station from the victim cell and the macro base station comprises: calling an MDA function to extract remote interference management reference signal (RIM-RS) information of the macro base station; the RIM-RS information of the macro base station comprises: a macro base station cell identifier, a macro base station beam identifier and interference information sent by an interfered cell; performing association analysis on the RIM-RS information and the disturbed cell, and determining a disturbing station from the macro base station; wherein, the disturbing station information of the disturbing station comprises: interference station identification, interference cell identification and interference beam identification.
Fig. 5 shows a flowchart of a method for determining a jamming station in the presence of interference according to an embodiment of the present disclosure, and as shown in fig. 5, the method includes:
step 501, calling an MDA function to extract longitude and latitude data of a base station from the base station parameters; in some practical applications, the latitude and longitude data of the base station can be extracted from other data tables in which the latitude and longitude information is recorded;
step 503, determining longitude and latitude data of the interfered station and longitude and latitude data of a first macro base station around the interfered station according to the longitude and latitude data of the base station;
step 505, calculating a distance S between the victim station and the first macro base station, and finding out the first macro base station corresponding to the distance S smaller than a distance threshold D as the macro base station;
509, performing association analysis on the interfered cell based on the RIM-RS information, and determining an interfering station from the macro base station; wherein, the disturbing station information of the disturbing station comprises: interference station identification, interference cell identification and interference beam identification.
In some embodiments, a reinforcement learning algorithm of the MDA functional structure is invoked, and an interference optimization strategy is generated based on victim station information of a victim station and victim station information of an offender station, including: constructing an objective function and corresponding constraint conditions; the objective function is the maximization of weighted values of the throughputs of all users under the interfered station and the throughputs of all users under the interfering station; and constructing a deep reinforcement learning algorithm to solve an interference optimization strategy according to the objective function and the constraint condition.
The MDA function of the network management in the network management system of the MDAS is introduced, and the real-time online generation of the interference optimization strategy can be realized through the established algorithm model.
For the objective function, the meaning of the objective function can be set to make the weighted value of the throughput of all users under the interfered station and the throughput of all users under the interfered station in unit time be the maximum; the objective function may be set as follows:
wherein, thp (t) represents the weighted value of the throughput of all users under the interfered station and the throughput of all users under the interfering station in unit time; n represents the total number of all users under the disturbed station, and M represents the total number of all users under the disturbing station.
For the constraint condition, the constraint effect of the constraint condition can be set as follows: the QoS (Quality of Service) of the user of the interfered station is guaranteed as much as possible, and the influence on the performance of the user of the interfering station is reduced; the constraints may be set as follows:
based on the clustering result after clustering in the previous steps, any two result sets S can be determined firstly i And S j Avg in constraints prb_i And Avg prb_j Respectively representing PRB scheduling resource average values of the two result sets; avg rsrp_i And Avg rsrp_j Respectively representing RSRP average values of the two result sets; avg thp_i And Avg thp_j Respectively representing the average values of the uplink throughputs of the two result sets; a represents a PRB scheduling resource threshold, B represents an RSRP threshold, C represents an uplink throughput threshold, the values of A and B can be determined by referring to practical application, and the relation among A, B and C should keep that C is more than 3 times of A and C is more than 3 times of B. Setting a first condition in the constraint condition so that each result set prb, throughput and RSRP in the clustering results after the clustering is performed in the previous step are all within corresponding thresholds;
the second condition in the constraint condition is set to make the throughput of all users under the interfered station not lower than mu 0 ，
The second condition in the constraint condition is set to make the probability that the total throughput of all users under the interference station is lower than q less than tau, wherein the determination of q value can be determined according to the user load m under the interference station, and the relationship is determined to be negative correlation:
in some embodiments, a deep reinforcement learning algorithm is constructed to solve the interference optimization strategy according to an objective function and constraint conditions, and the method comprises the following steps: configuring an action set and a state set;
constructing a policy network and an action evaluation network; the strategy network and the action evaluation network adopt the same three-layer network structure; determining a strategy based on a policy strategy according to the action set and the state set by utilizing a strategy network; and solving the strategy convergence by using the action evaluation network to obtain an interference optimization strategy.
In some implementations, the three-layer network structure may include: the method comprises the steps of setting an input layer of a neuron + rule function, setting a middle layer of the neuron + relu function and setting an output layer of the neuron + sigmoid + softmax function.
In some embodiments, the set of actions includes: the interference station adjusts the interference wave beam SSB direction, the interference station reduces the transmission power by 3dB, the interference station reduces the transmission power by 6dB, and the time slot resource which generates interference by the interference station and the time slot resource which generates interference by the interfered station are closed; the data in the action set can be considered as a 5-attribute branch action.
The state set includes: and the performance data reported by the interfered station and the PRB scheduling resource, RSRP and uplink throughput which are scheduled in the MR data.
The strategy generation method can be used for carrying out strategy generation based on the output result of the preorder step, and can comprise the steps of constructing the Markov tuple user state and the action from the current moment to the next moment, constructing a system reward function according to the state and the action, and constructing a deep reinforcement learning model to determine and generate the optimal interference optimization strategy.
Fig. 6 shows a flowchart of a method for generating an interference optimization strategy according to an embodiment of the present disclosure, as shown in fig. 6, including:
step S601, constructing an objective function and a corresponding constraint condition;
step S603, configuring an action set and a state set, and constructing a policy network and an action evaluation network;
step S605, determining a strategy based on policy strategy according to the action set and the state set by using a strategy network;
and step S607, using the action evaluation network to solve the strategy convergence to obtain the interference optimization strategy.
In some practical applications, configuration information of the interference optimization strategy can be obtained through a reinforcement learning algorithm of an MDA functional structure, and the configuration information can indicate an adjustment strategy related to 5 transfer actions in an action set; after the interference optimization strategy is issued to the interfering station and/or the interfered station, the interfering station and/or the interfered station can make specific adjustment based on the configuration information in the strategy, that is: specific output attributes can be obtained through a reinforcement learning algorithm constructed by an MDA function, and are used for enabling the interference station and/or the interfered station to execute so as to solve the interference problem.
In some embodiments, after issuing the interference optimization policy to the interfering station and/or the interfered station, the method further includes: and acquiring optimized index data of the interfered station and the interfered cell, calling an MDA function, and judging whether interference exists or not based on the optimized index data so as to realize optimized feedback.
By using the interference optimization method in the application, the network management equipment can be utilized to issue the interference configuration information generated by the MDA function to the interference station and/or the interference station to take effect. And the network manager collects the optimized data of the disturbed side in real time, determines whether the interference information of the disturbed side is solved, and iterates in real time to carry out MDA processing analysis. The method has the function of feedback verification, and the MDA updates the model parameters and strategies in real time on line, and iterates the optimization strategies, so that a better optimization effect is achieved.
Fig. 7 is a schematic diagram of an apparatus for implementing interference optimization according to an embodiment of the present disclosure, as shown in fig. 7, including:
RAN domain network management equipment, a disturbed station and a disturbing station;
on the RAN network management equipment side, functions such as data acquisition and classification, interference problem identification and analysis, interference station determination and analysis, interference optimization strategy generation and analysis and the like can be realized by using the introduced MDA function, and after the interference optimization strategy is generated, the strategy is issued to the interference station and/or the interference applying station to take effect, so that the interference problem is solved in real time. In some practical applications, after the interference station and/or the interference applying station execute the interference optimization strategy, the network management equipment side can also acquire optimized data of the interfered side, analyze and feed back the optimization effect in time, and update the learning model in time to adjust the optimization scheme, thereby achieving a better optimization effect.
In some practical applications, the method and the device have a data acquisition and configuration information issuing interaction mechanism, the establishment of a model in an MDA function can be updated in real time, the output is optimized, and an interaction flow between devices is fused with the existing network management architecture, so that the deployment and implementation are facilitated.
According to the interference optimization method provided by the application, on one hand, aiming at the interference optimization problem of a TDD frequency band flexible duplex networking configuration scene, the network management side can acquire input data for interference optimization under the scene by introducing an MDAS mechanism, actively construct a model, and obtain an output attribute for optimization through the model; the RAN centralized data acquisition unit on the network management side can realize index data acquisition, the introduced MDA function can realize model construction and data analysis, and further the full-control closed-loop flow of active identification of interference problems, interference source determination and interference optimization strategy generation can be realized from the network management full-control angle, so that the real-time performance of interference problem identification and the high efficiency of interference strategy generation under the scene can be guaranteed, and reliable guarantee is provided for the performance of vertical industry users with large uplink requirements.
On the other hand, from the implementation angle, the network management system provided by the application increases the MDA function of the scene, can realize the acquisition, input, analysis mechanism and output attribute of data from the network management side, and an operator can pertinently realize data acquisition and purposefully develop a model algorithm, thereby providing a foundation support for the operator to face the vertical industry to deploy networking optimization and upgrade of the industry with higher uplink requirements.
The interference optimization method provided by the application can also reduce the calculation complexity of the base station, perform data processing analysis from the network management perspective and automatically issue the interference optimization strategy configuration information to take effect, reduce the burden of manual configuration of operation and maintenance personnel, and improve the operation and maintenance efficiency.
It is to be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the method according to an exemplary embodiment of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
Fig. 8 shows a block diagram of an interference optimization apparatus 800 of one embodiment of the present disclosure; as shown in fig. 8, includes:
a data acquisition module 801, configured to acquire index data;
a disturbed judging module 802, configured to invoke a clustering algorithm for managing data analysis MDA functional structure, and judge whether there is interference based on the index data;
a disturbed station determining module 803, configured to determine a disturbed station and a disturbed cell in the presence of interference;
a disturbance station determining module 804, configured to invoke an MDA function to determine a macro base station in the presence of interference, and determine a disturbance station according to a disturbed cell and the macro base station;
the generation strategy module 805 is used for calling a reinforcement learning algorithm of an MDA (multiple access) function structure and generating an interference optimization strategy based on the interfered station information of the interfered station and the interfering station information of the interfering station;
the issuing module 806 is configured to issue the interference optimization policy to an interfering station and/or a victim station, so as to implement interference optimization.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
Fig. 9 shows a block diagram of an interference optimization computer device in an embodiment of the present disclosure. It should be noted that the illustrated electronic device is only an example, and should not bring any limitation to the functions and the application scope of the embodiment of the present invention.
An electronic device 900 according to this embodiment of the invention is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one memory unit 920, and a bus 930 that couples various system components including the memory unit 920 and the processing unit 910.
Wherein the storage unit stores program code that is executable by the processing unit 910 to cause the processing unit 910 to perform steps according to various exemplary embodiments of the present invention described in the above section "exemplary methods" of the present specification. For example, the processing unit 910 may execute step S201 shown in fig. 2, and collect index data; and step S203, calling a clustering algorithm for analyzing the MDA functional structure by the management data, judging whether interference exists or not based on the index data, and determining the interfered station and the interfered cell under the condition that the interference exists. And S205, under the condition that interference exists, calling an MDA function to determine a macro base station, and determining an interference station according to the interfered cell and the macro base station. And step S207, calling a reinforcement learning algorithm of an MDA functional structure, and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station. And step S209, transmitting the interference optimization strategy to the interference applying station and/or the interfered station to realize interference optimization.
The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 9201 and/or a cache memory unit 9202, and may further include a read only memory unit (ROM) 9203.
The electronic device 900 may also communicate with one or more external device interference optimization apparatus 800 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 900, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 950. Also, the electronic device 900 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 960. As shown, the network adapter 960 communicates with the other modules of the electronic device 900 via the bus 930. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above section "exemplary methods" of the present description, when said program product is run on the terminal device.
The program product for implementing the above method according to the embodiment of the present invention may employ a portable compact disc read only memory (CD-ROM) and include program codes, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Moreover, although the steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that the steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, and may also be implemented by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (16)
1. An interference optimization method, performed by a network management system, comprising:
acquiring index data;
calling a clustering algorithm for analyzing MDA functional structure by management data, judging whether interference exists or not based on the index data, and determining a disturbed station and a disturbed cell under the condition that the interference exists;
under the condition that interference exists, calling the MDA function to determine a macro base station, and determining an interference station according to the interfered cell and the macro base station;
calling a reinforcement learning algorithm of the MDA functional structure, and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station;
and transmitting the interference optimization strategy to the disturbing station and/or the disturbed station to realize interference optimization.
2. The method of claim 1, wherein the metric data comprises: the terminal reports the measurement report MR data of the base station and the base station performance data reported by the base station; wherein, the first and the second end of the pipe are connected with each other,
the basic field of the MR data comprises: a base station identifier and a base station cell identifier; the dedicated field of the MR data comprises: reference signal received power, RSRP; the basic fields of the base station performance data include: a base station identifier and a base station cell identifier; the dedicated field of the base station performance data comprises: uplink throughput and uplink Physical Resource Block (PRB) scheduling resources; and the number of the first and second groups,
after the index data is collected, the method further comprises the following steps: and the MR data and the base station performance data are stored in a correlated mode through the same basic field.
3. The method of claim 2, wherein invoking a clustering algorithm for Managing Data Analysis (MDA) functional structure, determining whether interference exists based on the index data, and determining the victim station and the victim cell if interference exists comprises:
calling the MDA function to obtain the index data, and extracting PRB scheduling resources, RSRP and uplink throughput fields in the index data to form a three-dimensional array;
calling the MDA function, and performing clustering analysis on the three-dimensional array by using a k-means algorithm to obtain a clustering result;
judging whether clustering data meeting preset conditions exist in the clustering result or not;
if so, determining that interference exists; and after the interference is determined to exist, determining the interfered station and the interfered cell from the clustering data meeting the preset conditions.
4. The method of claim 3, wherein invoking the MDA function and performing a clustering analysis on the three-dimensional array using a k-means algorithm to obtain a clustering result comprises:
dividing the p three-dimensional arrays into k initial sets by taking the number of the three-dimensional arrays as an observation value p; wherein k is less than or equal to p;
and clustering by taking the minimized sum of squares in the cluster as a target to obtain k result sets as the clustering result.
5. The method according to claim 4, wherein judging whether the clustering result has clustering data meeting a preset condition comprises:
calculating PRB scheduling resource average value, RSRP average value and uplink throughput average value of each result set in the k result sets;
determining PRB scheduling resource mean difference, RSRP mean difference and uplink throughput mean difference of each two result sets according to the PRB scheduling resource mean, the RSRP mean and the uplink throughput mean of each two result sets;
comparing the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference of each two result sets with the PRB scheduling resource threshold, the RSRP threshold and the uplink throughput threshold in the preset condition respectively, and judging whether the PRB scheduling resource mean difference, the RSRP mean difference and the uplink throughput mean difference which meet the inequality relation in the preset condition exist or not;
and if the cluster data exists, determining a result set related to the PRB scheduling resource mean difference value, the RSRP mean difference value and the uplink throughput mean difference value which meet the inequality relation in the preset condition as the cluster data meeting the preset condition.
6. The method of claim 5, wherein the uplink throughput threshold is greater than 3 times the PRB scheduled resource threshold and the uplink throughput threshold is greater than 3 times the RSRP threshold.
7. The method of claim 5, wherein determining the victim station and the victim cell from clustered data satisfying a predetermined condition comprises:
for clustering data which are formed by every two result sets and meet preset conditions, taking the result set with the smaller average value of the uplink throughput as a target set;
and taking the base station and the cell in the target set as the interfered station and the interfered cell respectively.
8. The method of claim 1, wherein invoking the MDA function to determine the macro base station comprises:
calling the MDA function to extract longitude and latitude data of the base station from the base station parameters;
and determining the base station with the distance to the interfered station smaller than a distance threshold value as a macro base station based on the latitude and longitude data of the base station.
9. The method of claim 1, wherein determining the aggressor station from the victim cell and the macro base station comprises:
calling the MDA function to extract the remote interference management reference signal RIM-RS information of the macro base station; wherein the RIM-RS information of the macro base station comprises: a macro base station cell identifier, a macro base station beam identifier and interference information sent by an interfered cell;
performing association analysis on the RIM-RS information and the interfered cell, and determining the interference station from the macro base station; wherein, the disturbing station information of the disturbing station comprises: interference station identification, interference cell identification and interference beam identification.
10. The method according to claim 1, wherein invoking a reinforcement learning algorithm of the MDA functional construct, and generating an interference optimization strategy based on victim station information of the victim station and aggressor station information of the aggressor station comprises:
constructing an objective function and corresponding constraint conditions; the objective function is the maximization of weighted values of the throughputs of all users under the interfered station and the throughputs of all users under the interfered station;
and constructing a deep reinforcement learning algorithm to solve an interference optimization strategy according to the objective function and the constraint condition.
11. The method of claim 10, wherein constructing a deep reinforcement learning algorithm to solve an interference optimization strategy according to the objective function and the constraint condition comprises:
configuring an action set and a state set;
constructing a policy network and an action evaluation network; the strategy network and the action evaluation network adopt the same three-layer network structure;
determining a strategy based on policy strategy according to the action set and the state set by using the strategy network;
and utilizing the action evaluation network to solve the strategy convergence to obtain the interference optimization strategy.
12. The method of claim 11, wherein the set of actions comprises: the interference station adjusts the direction of an interference wave beam SSB, the interference station reduces the transmission power by 3dB, the interference station reduces the transmission power by 6dB, and the time slot resource generating interference by the interference station and the time slot resource generating interference by the interfered station are closed;
the state set includes: and the performance data reported by the interfered station and the PRB scheduling resource, RSRP and uplink throughput which are scheduled in the MR data.
13. The method according to claim 1, wherein after issuing the interference optimization policy to the offender station and/or the victim station, further comprising:
and acquiring optimized index data of the interfered station and the interfered cell, calling the MDA function, and judging whether interference exists or not based on the optimized index data so as to realize optimized feedback.
14. An interference optimization device, wherein the interference optimization device is disposed at a network management system side, and comprises:
the data acquisition module is used for acquiring index data;
the judging disturbed module is used for calling a clustering algorithm for analyzing the MDA functional structure by the management data and judging whether the disturbance exists or not based on the index data;
the interference determining module is used for determining an interference station and an interference cell under the condition that interference exists;
the interference station determining module is used for calling the MDA function to determine a macro base station under the condition that interference exists, and determining an interference station according to the interfered cell and the macro base station;
the generation strategy module is used for calling a reinforcement learning algorithm of the MDA functional structure and generating an interference optimization strategy based on the interfered station information of the interfered station and the interference station information of the interference station;
and the issuing module is used for issuing the interference optimization strategy to the interference applying station and/or the interfered station so as to realize interference optimization.
15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the interference optimization method according to any one of claims 1 to 13.
16. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the interference optimization method of any one of claims 1 to 13.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050926.8A CN115802398A (en) | 2021-09-08 | 2021-09-08 | Interference optimization method and device, storage medium and electronic equipment |
| PCT/CN2022/103772 WO2023035750A1 (en) | 2021-09-08 | 2022-07-05 | Method and apparatus for interference optimization, storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050926.8A CN115802398A (en) | 2021-09-08 | 2021-09-08 | Interference optimization method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115802398A true CN115802398A (en) | 2023-03-14 |
Family
ID=85416805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111050926.8A Pending CN115802398A (en) | 2021-09-08 | 2021-09-08 | Interference optimization method and device, storage medium and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115802398A (en) |
| WO (1) | WO2023035750A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115996409A (en) * | 2023-03-23 | 2023-04-21 | 中国移动通信有限公司研究院 | Interference detection processing method, device, equipment and readable storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349037B (en) * | 2023-12-06 | 2024-04-19 | 中国科学院深圳先进技术研究院 | Method, device, computer equipment and storage medium for eliminating interference in off-line application |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108111248B (en) * | 2017-12-29 | 2019-06-18 | 广州市贝讯通信技术有限公司 | A kind of atmospheric duct interference optimization method and system |
| CN112543411B (en) * | 2019-09-20 | 2023-07-11 | 中兴通讯股份有限公司 | Interference positioning method, device and system of wireless communication system |
| CN110913331A (en) * | 2019-11-08 | 2020-03-24 | 中睿通信规划设计有限公司 | Base station interference source positioning system and method |
| CN112818596A (en) * | 2021-01-29 | 2021-05-18 | 广东振子电子科技有限公司 | Intelligent interference identification positioning method and system thereof |
-
2021
- 2021-09-08 CN CN202111050926.8A patent/CN115802398A/en active Pending
-
2022
- 2022-07-05 WO PCT/CN2022/103772 patent/WO2023035750A1/en unknown
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115996409A (en) * | 2023-03-23 | 2023-04-21 | 中国移动通信有限公司研究院 | Interference detection processing method, device, equipment and readable storage medium |
| CN115996409B (en) * | 2023-03-23 | 2023-07-04 | 中国移动通信有限公司研究院 | Remote interference detection processing method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023035750A1 (en) | 2023-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023035750A1 (en) | Method and apparatus for interference optimization, storage medium, and electronic device | |
| CN110401964A (en) | A kind of user oriented is Poewr control method of the center network based on deep learning | |
| CN110187973A (en) | A kind of service arrangement optimization method towards edge calculations | |
| Mechalikh et al. | PureEdgeSim: A simulation framework for performance evaluation of cloud, edge and mist computing environments | |
| US20210012187A1 (en) | Adaptation of Deep Learning Models to Resource Constrained Edge Devices | |
| WO2019206100A1 (en) | Feature engineering programming method and apparatus | |
| CN113037877A (en) | Optimization method for time-space data and resource scheduling under cloud edge architecture | |
| Li et al. | Research on QoS service composition based on coevolutionary genetic algorithm | |
| CN110708708A (en) | Wireless resource optimization method and device | |
| CN112804287A (en) | Intelligent network slice template generation method and system for power Internet of things | |
| Yamanaka et al. | Proximity-aware IaaS in an edge computing environment with user dynamics | |
| CN114943284A (en) | Data processing system and method of behavior prediction model | |
| CN113438733B (en) | System and method for realizing indoor positioning based on 5G and WIFI and electronic equipment | |
| CN113688490A (en) | Network co-construction sharing processing method, device, equipment and storage medium | |
| EP3560145A1 (en) | Apparatus and method for identifying network object groups | |
| CN115174416A (en) | Network planning system, method and device and electronic equipment | |
| CN114205238A (en) | Network resource optimization and model training method, device, storage medium and equipment | |
| Osibo et al. | An edge computational offloading architecture for ultra-low latency in smart mobile devices | |
| CN114222371A (en) | Flow scheduling method for coexistence of eMBB (enhanced multimedia broadcast/multicast service) and uRLLC (unified radio link control) equipment | |
| Han et al. | Opportunistic coded distributed computing: An evolutionary game approach | |
| US20210103830A1 (en) | Machine learning based clustering and patterning system and method for network traffic data and its application | |
| Song et al. | Federated dynamic spectrum access | |
| Valerio et al. | Optimising cost vs accuracy of decentralised analytics in Fog computing environments | |
| CN117279019B (en) | Method and device for predicting spectrum efficiency, electronic equipment and storage medium | |
| CN113485718B (en) | Context-aware AIoT application program deployment method in edge cloud cooperative system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |