Cell load balancing adjustment method and device, electronic equipment and storage medium

Abstract

The application provides a cell load balancing adjustment method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has an initial load parameter; determining a target load sharing cell of the to-be-adjusted cell according to the observation sampling data; obtaining a candidate parameter adjustment strategy of the to-be-adjusted cell and key communication index data; determining a target load parameter of the to-be-adjusted cell according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data; and generating a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter. The technical problem that the adjustment parameter and the adjustment amount cannot be accurately quantified when the cell load balancing adjustment is manually performed in the prior art, the load balancing scheme has low accuracy, the optimization period is too long, and the network environment cannot be rapidly improved is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and particularly relates to a cell load balancing adjustment method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, with the development of communication network, the load of hotspot area cells gradually increases, and the uneven distribution of users leads to high load in some cells. The load balancing of high load cells in hotspot areas has become the focus of network optimization work.

[0003] In the related art, when the load balancing of high load cells is processed, a load balancing optimization strategy based on artificial experience is usually used. First, the artificial experience is used to select the nearby cells according to the distance, adjust the switching parameters, and then observe the index change. When it is invalid, the amount of adjustment of the original adjustment parameter is increased for trial parameter adjustment. After a long time of multi-round adjustment, an effective adjustment scheme is determined.

[0004] In this way, from the selection of the balancing target neighbor area to the selection of the trial adjustment parameter and the adjustment value of each round of parameters, all are based on artificial experience, which requires high personal skills and experience level, and cannot accurately quantify the adjustment parameters and adjustment amount, resulting in low accuracy of the load balancing scheme. Moreover, since the scheme cannot be accurately quantified, the final scheme often needs to be determined through multiple experiments, resulting in a long optimization period, poor real-time performance of the load balancing adjustment scheme, and inability to meet the demand for rapid improvement of the network environment, which seriously affects the communication effect of the cell. SUMMARY

[0005] The present application aims to at least solve one of the technical problems in the related art to some extent.

[0006] To this end, the first purpose of the present application is to propose a cell load balancing adjustment method to realize accurate quantitative adjustment of cell parameters in an automated and intelligent manner, obtain a load balancing adjustment scheme, effectively solve the technical problems of missing and incomplete artificial adjustment parameters, and effectively improve the load parameter adjustment efficiency. The load balancing adjustment scheme has a short output time, meets the timeliness and accuracy requirements of the present network optimization, and has the advantages of the prior art.

[0007] The second purpose of the present application is to propose a cell load balancing adjustment device.

[0008] The third purpose of the present application is to propose an electronic equipment.

[0009] The fourth purpose of the present application is to propose a computer readable storage medium.

[0010] The fifth purpose of the present application is to propose a computer program product.

[0011] To achieve the above object, the first aspect of the present application provides a cell load balancing adjustment method, comprising: obtaining a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell; determining the target load sharing cell of the to-be-adjusted cell according to the observation sampling data; obtaining a candidate parameter adjustment strategy and key communication index data of the to-be-adjusted cell; determining a target load parameter of the to-be-adjusted cell according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data; and generating a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter.

[0012] To achieve the above object, the second aspect of the present application provides a cell load balancing adjustment device, comprising: a first obtaining module, configured to obtain a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell; a first determining module, configured to determine the target load sharing cell of the to-be-adjusted cell according to the observation sampling data; a second obtaining module, configured to obtain a candidate parameter adjustment strategy and key communication index data of the to-be-adjusted cell; a second determining module, configured to determine a target load parameter of the to-be-adjusted cell according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data; and a generating module, configured to generate a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter.

[0013] To achieve the above object, the third aspect of the present application provides an electronic device, comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the cell load balancing adjustment method provided by the first aspect of the present application is implemented.

[0014] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and when the program is executed by a processor, the cell load balancing adjustment method provided by the first aspect of the present application is implemented.

[0015] To achieve the above object, the fifth aspect of the present application provides a computer program product, when instructions in the computer program product are executed by a processor, the cell load balancing adjustment method provided by the first aspect of the present application is executed.

[0016] The cell load balancing adjustment method, device, electronic equipment and storage medium provided by the present application, by acquiring a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell, according to the observation sampling data, the target load sharing cell of the to-be-adjusted cell is determined, candidate parameter adjustment strategies and key communication index data of the to-be-adjusted cell are acquired, the target load parameter of the to-be-adjusted cell is determined according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data, the load balancing adjustment scheme of the to-be-adjusted cell is generated according to the target load parameter, the technical problem that the adjustment parameter and the adjustment amount cannot be accurately quantified in the related art when the cell load balancing adjustment is manually performed, resulting in low accuracy of the load balancing scheme, long optimization period and inability to meet the demand of rapidly improving the network environment is solved.

[0017] Additional aspects and advantages of the present application will be made apparent by the following description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description, taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 A flowchart of a cell load balancing adjustment method provided by an embodiment of the present application;

[0020] Figure 2 An architecture diagram of a parameter optimization system provided by an embodiment of the present application;

[0021] Figure 3 An algorithm flowchart of an ant colony algorithm provided by an embodiment of the present application;

[0022] Figure 4 A flowchart of another cell load balancing adjustment method provided by an embodiment of the present application;

[0023] Figure 5 A data processing flowchart of cell load balancing adjustment in an embodiment of the present application;

[0024] Figure 6 A flowchart of another cell load balancing adjustment method provided by an embodiment of the present application;

[0025] Figure 7 A single-cell correlation degree calculation result diagram in an embodiment of the present application;

[0026] Figure 8 A cell distribution diagram in an embodiment of the present application;

[0027] Figure 9 A structural schematic diagram of a cell load balancing adjustment device provided by an embodiment of the present application; and

[0028] Figure 10 A structural schematic diagram of a cell load balancing adjustment device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0029] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which the same or similar notations used throughout the drawings and the specific description denote the same or similar elements or elements having the same or similar functions. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0030] A cell load balancing adjustment method and device of an embodiment of the present application are described below with reference to the accompanying drawings.

[0031] Figure 1 A flowchart of a cell load balancing adjustment method provided by an embodiment of the present application.

[0032] In the related art, when performing load balancing processing on a high-load cell, a load balancing optimization strategy based on artificial experience is usually used. First, an artificial person selects nearby cells according to distance, adjusts by switching parameters, and then observes the index change. When invalid, the adjustment parameter adjustment amount is increased for trial parameter adjustment. After a long time of multiple rounds of adjustment, an effective adjustment scheme is determined.

[0033] In this way, from the selection of the balancing target neighbor area to the selection of the trial adjustment parameter and the adjustment value of each round of parameters, all are based on artificial experience, which requires high personal skills and experience level, and the adjustment parameters and adjustment amount cannot be accurately quantified, resulting in low accuracy of the load balancing scheme. Moreover, since the scheme cannot be accurately quantified, the final scheme often needs to be determined through multiple experiments, resulting in a long optimization period, poor real-time performance of the load balancing adjustment scheme, and inability to meet the demand for rapid improvement of the network environment, which seriously affects the communication effect of the cell.

[0034] To solve this problem, embodiments of the present application provide a cell load balancing adjustment method to realize accurate quantitative adjustment of cell parameters in an automated and intelligent manner, obtain a load balancing adjustment scheme, effectively solve the technical problems of missing and incomplete consideration of artificial adjustment parameters, effectively improve the load parameter adjustment efficiency, and shorten the output time of the load balancing adjustment scheme, meeting the timeliness and accuracy requirements of network optimization, such as Figure 1 As shown in the figure, the cell load balancing adjustment method includes the following steps:

[0035] S101: acquire a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell.

[0036] The to-be-adjusted cell refers to a high-load cell of a hotspot area cell in a high-load situation.

[0037] The observation sampling data refers to data required for load balancing parameter optimization of the to-be-adjusted cell, for example, cell operating parameters, microwave radiometer observation (MRO) data, communication key performance indicator (KPI) data, and existing network configuration data, or other arbitrary data that can be used for load balancing parameter optimization of the to-be-adjusted cell, which is not limited.

[0038] The initial load parameter refers to a load parameter of the to-be-adjusted cell before adjustment.

[0039] The target load sharing cell refers to a cell that finally shares the load of the to-be-adjusted cell, and the number of the target load sharing cell can be multiple.

[0040] In the embodiment of the application, when acquiring the to-be-adjusted cell and the observation sampling data of the to-be-adjusted cell, a cell that needs to be load balanced can be selected as the to-be-adjusted cell, for example, a high-load cell of a hotspot area cell in a high-load situation. When acquiring the observation sampling data of the to-be-adjusted cell, data collection and processing can be performed from a network optimization platform, a big data platform, and a network management platform. Cell operating parameters, microwave radiometer observation data, communication key performance indicator data, and existing network configuration data, and other data required for load balancing parameter optimization of the to-be-adjusted cell can be used. Then, the ETL server can be used to clean and structure the collected data and load it into the database. The ETL server refers to a server used to execute the ETL (Extract, Transform, Load) process, so as to acquire the observation sampling data of the to-be-adjusted cell.

[0041] For example, as shown in FIG. 1, Figure 2 Figure 2 ​is the architecture diagram of the parameter optimization system provided by the embodiments of the present application. First, the cell operating parameter data and the cell communication KPI data can be collected from the network optimization platform, the MRO data can be collected from the big data platform, and the current network configuration parameter data can be collected from the network management platform. The collected data is used as observation sampling data. Then, the data in the database is cleaned and structured by using the ETL server, and is loaded into the database. Then, the required fields are parsed from the collected data, and the data is cleaned, and the missing values are processed. After that, the processed data is loaded into the algorithm by the load balancing optimization server, and the parameter optimization scheme is output. For details, refer to the specific description of the following steps.

[0042] S102: determining a target load sharing cell of the to-be-adjusted cell according to the observation sampling data.

[0043] The target load sharing cell refers to a cell that is finally used to share the load of the to-be-adjusted cell. The number of the target load sharing cell can be multiple.

[0044] After obtaining the to-be-adjusted cell and the observation sampling data of the to-be-adjusted cell, the embodiments of the present application can determine the target load sharing cell of the to-be-adjusted cell according to the observation sampling data.

[0045] In the embodiments of the present application, when the target load sharing cell of the to-be-adjusted cell is determined according to the observation sampling data, a plurality of candidate cells that can be used to share the load of the to-be-adjusted cell can be obtained first. The correlation coefficient between the plurality of candidate cells and the to-be-adjusted cell is calculated, and the neighbor area with a correlation coefficient greater than a set value is retained as a load sharing target neighbor area. In the correlation coefficient calculation, the to-be-adjusted cell is taken as the main service cell, and the MRO sampling point data of the to-be-adjusted cell is used for analysis and calculation. The frequency of each candidate cell of the high-load cell appearing in the MRO sampling point of the to-be-adjusted cell in the form of a neighbor area is counted. The correlation degree of each neighbor area with the high-load cell is quantified by analogy with the neighbor area frequency, so as to obtain the correlation coefficient of the neighbor area. The neighbor area with a correlation coefficient greater than a set value is retained as a load sharing target neighbor area.

[0046] For example, assuming that the to-be-adjusted cell has 8 MRO sampling points, and the candidate cell A appears 7 times, the correlation coefficient of the neighbor area can be represented as 7 / 8, and the correlation degree of the candidate cell A and the to-be-adjusted cell is 0.88. The correlation coefficient calculation result of all candidate cells is obtained by cyclic calculation.

[0047] S103: obtaining a candidate parameter adjustment strategy and key communication index data of the to-be-adjusted cell.

[0048] The candidate parameter adjustment strategy refers to a candidate parameter adjustment mode that can be taken by the cell to be adjusted. The candidate parameter adjustment strategy can include three optimization strategies of parameter switching, parameter reselection, and parameter balancing, or can also include any parameter adjustment strategy that can be used to adjust the load parameter of the cell to be adjusted, and no limitation is made to this.

[0049] The key communication index data refers to communication index data that can be used to assist in load adjustment of the cell to be adjusted. The key communication index data can include average traffic, uplink traffic, downlink traffic, cell utilization, and average number of connections of the cell to be adjusted.

[0050] In the embodiments of the present application, the three optimization strategies of parameter switching, parameter reselection, and parameter balancing can be determined as the candidate parameter adjustment strategy, and the average traffic, uplink traffic, downlink traffic, cell utilization, and average number of connections of the cell to be adjusted can be collected from the network optimization platform as the key communication index data of the cell to be adjusted.

[0051] S104: determining a target load parameter of the cell to be adjusted according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data.

[0052] The target load parameter refers to a load parameter that can be used to make the cell to be adjusted in a load balanced state.

[0053] In the embodiments of the present application, when the target load parameter of the cell to be adjusted is determined according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data, a plurality of candidate parameter sets can be first determined according to the candidate parameter adjustment strategy, and the initial values of the m groups of candidate parameter sets are the values currently set by the present network configuration parameter (the initial load parameter). Then, the fitness function of the cell to be adjusted is determined according to the related parameter data of the target load sharing cell and the key communication index data. The related calculation expression of the fitness function can be introduced to calculate the specific value of the fitness function, and the idea of the ant colony algorithm is used for multiple iteration calculations. For example, as shown in the following formula (1): Figure 3 Figure 3 ​is an algorithm flow diagram of the ant colony algorithm provided by the embodiment of the present application. Each algorithm iteratively calculates the transition probability of the initial value to each region and updates the fitness function, and finally outputs the parameter combination value meeting the condition, which can be used as the target load parameter. The ant colony algorithm theoretically makes the fitness function of the to-be-adjusted cell less than the set target value on the basis that each neighboring cell (target load sharing cell) will not become a high-load cell. According to the ant colony algorithm operation, when the downlink PRB utilization rate of the high-load cell reaches the demand, the parameters can be output. The output optimal parameter combination set can include the cell level and the neighboring cell, and the optimal parameter combination set is generated, and the target load parameter of the to-be-adjusted cell is obtained.

[0054] S105: generating a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter.

[0055] The load balancing adjustment scheme refers to a detailed load sharing scheme of each target load sharing cell generated according to the target load parameter.

[0056] In the embodiment of the present application, the optimal parameter combination set (target load parameter) output can be used to generate a parameter platform specification scheme, which is sent to the parameter platform for scheme execution. Based on the optimal combination adjustment scheme of the output parameters, the mapping of related fields is automatically completed through the standardized parameter platform interface, to generate a detailed load sharing scheme of each target load sharing cell as the load balancing adjustment scheme of the to-be-adjusted cell, and the load balancing adjustment scheme is sent to the parameter platform to generate a parameter modification work order. The parameter platform will automatically generate an execution instruction, which is transparently transmitted to the manufacturer network management, to realize automatic modification operation and automatically feed back the modification result.

[0057] In the embodiment, the to-be-adjusted cell and the observation sampling data of the to-be-adjusted cell are obtained, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine the target load sharing cell of the to-be-adjusted cell. According to the observation sampling data, the target load sharing cell of the to-be-adjusted cell is determined, the candidate parameter adjustment strategy and the key communication index data of the to-be-adjusted cell are obtained, the target load parameter of the to-be-adjusted cell is determined according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data, the load balancing adjustment scheme of the to-be-adjusted cell is generated according to the target load parameter, the accurate quantitative adjustment of the cell parameter is realized in an automatic and intelligent manner, the load balancing adjustment scheme is obtained, the technical problems of missing and incomplete consideration in manual parameter adjustment are effectively solved, the load parameter adjustment efficiency is effectively improved, the load balancing adjustment scheme has a short output time, and the requirements of timeliness and accuracy of the existing network optimization are met.

[0058] The embodiment provides another cell load balancing adjustment method, Figure 4 The embodiment provides another cell load balancing adjustment method.

[0059] As shown in the method for adjusting cell load balancing, the method can comprise the following steps: Figure 4

[0060] S401: obtaining a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has an initial load parameter corresponding thereto, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell.

[0061] S402: determining the target load sharing cell of the to-be-adjusted cell according to the observation sampling data.

[0062] S403: obtaining a candidate parameter adjustment strategy of the to-be-adjusted cell and key communication index data.

[0063] For specific descriptions of S401 to S403, refer to the above embodiments, which will not be described here.

[0064] S404: determining a plurality of candidate load parameter combinations of the to-be-adjusted cell according to the candidate parameter adjustment strategy.

[0065] Optionally, in some embodiments, when the plurality of candidate load parameter combinations of the to-be-adjusted cell are determined according to the candidate parameter adjustment strategy, the to-be-adjusted parameter corresponding to the candidate parameter adjustment strategy and the parameter adjustment range corresponding to the to-be-adjusted parameter can be determined, and the to-be-adjusted parameter and the parameter adjustment range corresponding to the to-be-adjusted parameter are subjected to solution space calculation processing to obtain the plurality of candidate load parameter combinations.

[0066] In the embodiments of the present application, when the plurality of candidate load parameter combinations of the to-be-adjusted cell are determined according to the candidate parameter adjustment strategy, the to-be-adjusted parameter corresponding to the candidate parameter adjustment strategy and the parameter adjustment range corresponding to the to-be-adjusted parameter are determined. First, a plurality of parameters that can be adjusted in each candidate parameter adjustment strategy can be determined as the to-be-adjusted parameter, and the parameter adjustment range corresponding to each to-be-adjusted parameter is determined. Then, the to-be-adjusted parameter and the parameter adjustment range corresponding to the to-be-adjusted parameter are subjected to solution space calculation processing to obtain the plurality of candidate load parameter combinations. In a parameter optimization problem, the solution space is usually composed of the value range of each to-be-adjusted parameter, and the calculation of the solution space usually involves determining the value range of each to-be-adjusted parameter and determining the set of feasible solutions in combination with the related constraints of the to-be-adjusted parameter. The set of the plurality of feasible solutions obtained can be used as the plurality of candidate load parameter combinations of the to-be-adjusted cell.

[0067] ​For example, the three optimization ideas of handover extraction, reselection, and balancing involve adjusting parameters to form a parameter set M = {Cellular Interference Optimization (CIO), number of offloading users, A3 offset, …}, obtaining the parameters to be adjusted, wherein A3 offset is an important parameter for handover between base stations in a wireless communication network, and A3 offset is a threshold for a mobile device to decide whether to hand over to another base station. Then the adjustable range of each parameter is determined, and the solutions of all parameters to be adjusted are combined to form a solution space. For example, the range of parameter A is (1, 10), the range of parameter B is (1, 10), and the range of parameter C is (1, 10). The solution space formed by the three parameters is {(1, 1, 1), (1, 1, 2), (1, 1, 3), … (10, 10, 10)}.

[0068] S405: Determine the candidate fitness function value corresponding to each candidate load parameter combination according to the target load sharing cell, the initial load parameter, and the key communication indicator data.

[0069] Optionally, in some embodiments, the key communication indicator data includes a first load rate corresponding to the cell to be adjusted. When determining the candidate fitness function value corresponding to each candidate load parameter combination according to the target load sharing cell, the initial load parameter, and the key communication indicator data, a second load rate corresponding to the target load sharing cell can be obtained, an initial fitness function value corresponding to the candidate load parameter combination can be determined according to the fitness function calculation expression, a transfer probability value of the initial load parameter to the reference load parameter of the target load sharing cell can be determined according to the first load rate and the second load rate, and the initial fitness function value can be updated to obtain the candidate fitness function value.

[0070] The key communication indicator data includes a first load rate corresponding to the cell to be adjusted. The first load rate refers to the downlink physical resource block (Physical Resource Block Utilization Rate, PRB) utilization rate (%) corresponding to the cell to be adjusted.

[0071] The second load rate refers to the downlink physical resource block (Physical Resource Block Utilization Rate, PRB) utilization rate (%) corresponding to the target load sharing cell.

[0072] In the embodiments of the present application, the initial value of the m sets of parameters is set in the solution space (candidate load parameter combinations), and the initial value is the value of the current configuration parameter set in the existing network (initial load parameter). When the candidate fitness function value corresponding to each candidate load parameter combination is determined according to the target load sharing cell, the initial load parameter and the key communication index data, the expression of the fitness function F(x) is determined as follows:

[0073]

[0074]

[0075]

[0076] wherein S load_ratio is the main cell load rate (first load rate), N load_ratio is the load rate shared to the neighboring cell (second load rate), m is the number of different candidate load parameter combinations, k is the candidate load parameter combination number, i is the position of the parameter combination, j is the position that can be reached by the parameter combination, p is the pheromone evaporation coefficient, Q is a constant, L ij represents the change increment of the function, the ant colony algorithm is introduced, the transfer probability value of the initial load parameter to the reference load parameter of the target load sharing cell is determined according to the first load rate and the second load rate, the transfer probability of the initial value to each region is calculated and the fitness function is updated each time, and finally the parameter combination value that meets the condition and the load shared to each neighboring cell are output. The output parameter is the parameter output scheme, and the parameter optimization scheme includes the cell level and the neighboring cell level.

[0077] S406: determining the target load parameter from the plurality of candidate load parameter combinations according to the candidate fitness function value.

[0078] Optionally, in some embodiments, when the target load parameter is determined from the plurality of candidate load parameter combinations according to the candidate fitness function value, a preset function value threshold can be obtained, and if the candidate fitness function value is less than the preset function value threshold, the candidate load parameter combination corresponding to the candidate fitness function value is taken as the target load parameter.

[0079] For example, as shown in Figure 5 , the target load parameter is determined from the plurality of candidate load parameter combinations according to the candidate fitness function value. Figure 5is a data processing flowchart of cell load balancing adjustment in the embodiment of the present application. The overall processing flow is: data collection, data analysis, data cleaning, correlation analysis, switching band analysis, iterative operation, parameter set generation, and final scheme pushing. Specifically, the fields required for cell load balancing adjustment can be parsed from the MRO data, the empty and missing values in the data are processed, and then the correlation coefficient of the adjacent area is analyzed, the far-distance adjacent area filtering processing is performed on the working parameter information, and the switching band area identification processing is performed in combination with the correlation coefficient analysis result of the adjacent area and the far-distance adjacent area filtering processing result. Then, the load distribution function iterative operation is performed in combination with the switching band area identification processing result and the KPI index data, the optimal parameter combination set is generated in combination with the load distribution function iterative operation result and the existing network parameter configuration data, and then the parameter platform specification scheme is generated and sent to the parameter platform for specific scheme execution.

[0080] S407: generating a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter.

[0081] The specific description of S407 can be referred to the above embodiment, which is not described here.

[0082] In the embodiment, the to-be-adjusted cell and observation sampling data of the to-be-adjusted cell are obtained, the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell. According to the observation sampling data, the target load sharing cell of the to-be-adjusted cell is determined, the candidate parameter adjustment strategy and the key communication index data of the to-be-adjusted cell are obtained, the target load parameter of the to-be-adjusted cell is determined according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data, the load balancing adjustment scheme of the to-be-adjusted cell is generated according to the target load parameter, the accurate quantitative adjustment of the cell parameter is realized in an automatic and intelligent manner, the load balancing adjustment scheme is obtained, the technical problem of missing and incomplete consideration of manual parameter adjustment is effectively solved, the load parameter adjustment efficiency is effectively improved, the load balancing adjustment scheme output time is short, and the requirements of the existing network optimization timeliness and accuracy are met.

[0083] The embodiment provides another cell load balancing adjustment method, Figure 6 The flowchart of another cell load balancing adjustment method provided in the embodiment of the present application is shown.

[0084] As Figure 6 shown, the cell load balancing adjustment method can include the following steps:

[0085] S601: obtaining a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell.

[0086] S602: Obtain a plurality of candidate load sharing cells.

[0087] The candidate load sharing cell refers to a cell that is likely to participate in load sharing of the cell to be adjusted.

[0088] S603: Determine a correlation coefficient between each candidate load sharing cell and the cell to be adjusted according to the observation sampling data.

[0089] Optionally, in some embodiments, when the correlation coefficient between each candidate load sharing cell and the cell to be adjusted is determined according to the observation sampling data, the total number of data sampling points corresponding to the observation sampling data can be determined, the number of times that the candidate load sharing cell appears in the observation sampling data is determined as a reference number, and the frequency value of the candidate load sharing cell appearing in the observation sampling data is determined according to the total number of data sampling points and the reference number, and the frequency value is taken as the correlation coefficient.

[0090] In the embodiments of the present application, the calculation formula of the cell correlation coefficient can be introduced as follows Wherein, P t represents the correlation degree of the tth candidate load sharing cell and the cell to be adjusted, is the number of MRO sampling points reported by the cell to be adjusted, and it is assumed that the cell to be adjusted reports s MRO sampling points, because SC appears only once in the form of the cell to be adjusted in each sampling point, so The value of s is s, is the total number of the tth candidate load sharing cell appearing in the form of the candidate load sharing cell in all MRO sampling points reported by the cell to be adjusted, because the number of appearances of different candidate load sharing cells is different, here, the number of appearances of the tth candidate load sharing cell is represented by n t, for example, 8 MRO sampling points are set, and the candidate load sharing cell A appears 7 times, then the correlation real value is 7 / 8, and the correlation degree of the candidate load sharing cell A and the cell to be adjusted is 0.88, and the correlation degree results of all candidate load sharing cells are calculated in a loop, for example, as shown in Figure 7 Figure 7 is a single cell correlation degree calculation result diagram in the embodiments of the present application.

[0091] S604: If the correlation coefficient is greater than a preset correlation coefficient threshold, the candidate load sharing cell corresponding to the correlation coefficient is taken as a reference load sharing cell.

[0092] S605: Filtering processing is performed on the reference load sharing cell to obtain a target load sharing cell.

[0093] ​Optionally, in some embodiments, when the reference load sharing cells are filtered to obtain the target load sharing cells, the reference load sharing cells can be filtered at a long distance to obtain the main lobe direction cells and the back lobe direction cells in the reference load sharing cells, the first level difference between the main lobe direction cells and the to-be-adjusted cell is determined, the second level difference between the back lobe direction cells and the to-be-adjusted cell is determined, and the target load sharing cell is determined from the main lobe direction cells and the back lobe direction cells according to the first level difference and the second level difference.

[0094] Optionally, in some embodiments, when the target load sharing cell is determined from the main lobe direction cells and the back lobe direction cells according to the first level difference and the second level difference, a preset level difference threshold value can be obtained, if the first level difference is less than the preset level difference threshold value, the main lobe direction cell is taken as the target load sharing cell, and if the second level difference is less than the preset level difference threshold value, the back lobe direction cell is taken as the target load sharing cell.

[0095] In the embodiments of the present application, when the reference load sharing cells are filtered to obtain the target load sharing cells, the reference load sharing cells can be filtered at a long distance, only the following two situations of adjacent cells are retained, and the remaining adjacent cells are filtered out and not taken as load sharing cells, the main lobe direction cells and the back lobe direction cells, the main lobe direction cells are the first layer site adjacent cells and the adjacent cells covered by the second layer site adjacent cells, and the back lobe direction cells are the adjacent cells with a first layer site coverage direction angle of ±45°. Based on the main lobe direction cells and the back lobe direction cells remaining after filtering, the switching band area is identified. In mobile communication, in order to ensure the continuous communication between the mobile station and the base station, part of the area between cells is covered by two or more cell signals. The data collection server performs positioning calculation of the mobile station according to the user data, performs statistics according to the positioning calculation result, calculates the soft switching band of the cell, and then separates the users in the switching band. First, the level difference between the high load cell and the adjacent cell in the switching band is calculated, the parameters to be adjusted are set through the level difference, and then part of the users in the switching band are distributed to the adjacent cells according to the adjusted parameters, so that the wireless resource utilization of the entire network is more efficient, the load of each cell is balanced, the perception of the user occupying the network is improved, the MRO data is calculated, and the sampling points with a RSRP difference of 6dB from the high load cell in the adjacent cells remaining after filtering are selected. These sampling points should be located in the overlapping area of the adjacent cells and the main cell coverage edge in theory. For example, as shown in the following figure, Figure 8 Figure 8 is a cell distribution diagram in the embodiments of the present application, and the overlapping area in the following figure is the cell distribution diagram in the embodiments of the present application. The users in the overlapping area are the users in the switching band and can be used for balanced adjustment.

[0096] ​S606: Obtain a candidate parameter adjustment strategy and key communication index data of the cell to be adjusted.

[0097] S607: Determine a target load parameter of the cell to be adjusted according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data.

[0098] S608: Generate a load balancing adjustment scheme of the cell to be adjusted according to the target load parameter.

[0099] For specific descriptions of S606 to S608, refer to the above embodiments, which will not be repeated here.

[0100] In the embodiments of the present application, the idea of outputting parameter adjustment schemes based on ant colony algorithm and the actual use of ant colony algorithm in load balancing work of high load cells are adopted. Compared with the traditional idea of long-time trial adjustment of a single scheme in conventional optimization, the ant colony algorithm considers the comprehensive consideration of switching, reselection, and balancing multi-dimensional parameter sets, quantitatively outputs the optimal combination parameter adjustment scheme, globally and comprehensively uses and quantifies parameters, traverses the adjustable range of related parameters based on the adjustment step for quantization, freely combines various parameter sets, forms a scheme matrix, and finally forms a solution space. Based on the ant algorithm, the optimal adjustment scheme with the lowest mutual influence but the best optimization effect for the high load cell is found. In the processing, various constraints are considered, and finally an implementable parameter optimization adjustment scheme is formed. The parameters of switching, reselection, and balancing are comprehensively considered, the parameters are fully covered, the scheme is comprehensive, the problems such as limitations of artificial thinking are solved, all parameter values in the adjustable range of all parameters are traversed, and a parameter combination matrix and a solution space are formed. The problems such as omission of artificial adjustment parameters and incomplete consideration are completely solved. Machine automatic processing is adopted, the processing capacity is strong, and the optimization efficiency is greatly improved.

[0101] In the embodiments, the cell to be adjusted and observation sampling data of the cell to be adjusted are obtained, the cell to be adjusted has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the cell to be adjusted. According to the observation sampling data, the target load sharing cell of the cell to be adjusted is determined, the candidate parameter adjustment strategy and the key communication index data of the cell to be adjusted are obtained, the target load parameter of the cell to be adjusted is determined according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data, and the load balancing adjustment scheme of the cell to be adjusted is generated according to the target load parameter. The accurate quantitative adjustment of the cell parameters is realized in an automatic and intelligent manner, the load balancing adjustment scheme is obtained, the technical problems such as omission of artificial adjustment parameters and incomplete consideration are effectively solved, the load parameter adjustment efficiency is effectively improved, the load balancing adjustment scheme is output in a short time, and the requirements for timeliness and accuracy of network optimization are met.

[0102] To achieve the above-mentioned embodiments, the application further provides a cell load balancing adjustment device.

[0103] Figure 6 A structural schematic diagram of a cell load balancing adjustment device provided by an embodiment of the application.

[0104] As Figure 6 shown, the cell load balancing adjustment device comprises:

[0105] A first obtaining module 901 is configured to obtain a to-be-adjusted cell and observation sampling data of the to-be-adjusted cell, wherein the to-be-adjusted cell has an initial load parameter corresponding thereto, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell.

[0106] A first determining module 902 is configured to determine the target load sharing cell of the to-be-adjusted cell according to the observation sampling data.

[0107] A second obtaining module 903 is configured to obtain a candidate parameter adjustment strategy of the to-be-adjusted cell and key communication index data.

[0108] A second determining module 904 is configured to determine a target load parameter of the to-be-adjusted cell according to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication index data.

[0109] A generating module 905 is configured to generate a load balancing adjustment scheme of the to-be-adjusted cell according to the target load parameter.

[0110] Further, in a possible implementation manner of the embodiment of the application, as Figure 10 shown, Figure 10 is a structural schematic diagram of another cell load balancing adjustment device provided by an embodiment of the application, wherein the second determining module 904 comprises:

[0111] A first determining sub-module 9041 is configured to determine a plurality of candidate load parameter combinations of the to-be-adjusted cell according to the candidate parameter adjustment strategy.

[0112] A second determining sub-module 9042 is configured to determine a candidate fitness function value corresponding to each candidate load parameter combination according to the target load sharing cell, the initial load parameter, and the key communication index data.

[0113] A third determining sub-module 9043 is configured to determine the target load parameter from the plurality of candidate load parameter combinations according to the candidate fitness function value.

[0114] Further, in a possible implementation manner of the embodiment of the application, wherein the first determining sub-module 9041 is specifically configured to:

[0115] determine the to-be-adjusted parameter corresponding to the candidate parameter adjustment strategy and a parameter adjustment range corresponding to the to-be-adjusted parameter;

[0116] perform solution space calculation processing on the to-be-adjusted parameter and the parameter adjustment range corresponding to the to-be-adjusted parameter, to obtain a plurality of candidate load parameter combinations.

[0117] Further, in a possible implementation of the embodiment of the present application, the key communication index data includes: a first load rate corresponding to the to-be-adjusted cell;

[0118] The second determination submodule 9042 is specifically configured to:

[0119] obtain a second load rate corresponding to the target load sharing cell;

[0120] determine an initial fitness function value corresponding to the candidate load parameter combination according to the fitness function calculation expression;

[0121] determine a transfer probability value of the reference load parameter of the initial load parameter to the target load sharing cell according to the first load rate and the second load rate;

[0122] update the initial fitness function value according to the transfer probability value, to obtain a candidate fitness function value.

[0123] Further, in a possible implementation of the embodiment of the present application, the third determination submodule 9043 is specifically configured to:

[0124] obtain a preset function value threshold;

[0125] if the candidate fitness function value is less than the preset function value threshold, the candidate load parameter combination corresponding to the candidate fitness function value is taken as the target load parameter.

[0126] Further, in a possible implementation of the embodiment of the present application, the first determination module 902 is specifically configured to:

[0127] obtain a plurality of candidate load sharing cells;

[0128] determine a correlation coefficient between each candidate load sharing cell and the to-be-adjusted cell according to the observation sampling data;

[0129] if the correlation coefficient is greater than a preset correlation coefficient threshold, the candidate load sharing cell corresponding to the correlation coefficient is taken as the reference load sharing cell;

[0130] perform filtering processing on the reference load sharing cell, to obtain the target load sharing cell.

[0131] Further, in a possible implementation of the embodiment of the application, the first determining module 902 is further configured to:

[0132] determine the total number of data sampling points corresponding to the observation sampling data;

[0133] determine the number of times that the candidate load sharing cell appears in the observation sampling data as the reference number;

[0134] determine the frequency value of the candidate load sharing cell appearing in the observation sampling data according to the total number of data sampling points and the reference number, and the frequency value is taken as the correlation coefficient.

[0135] Further, in a possible implementation of the embodiment of the application, the first determining module 902 is further configured to include:

[0136] perform a long-distance filtering process on the reference load sharing cell to obtain a main lobe direction cell and a back lobe direction cell in the reference load sharing cell;

[0137] determine a first level value difference between the main lobe direction cell and the to-be-adjusted cell and a second level value difference between the back lobe direction cell and the to-be-adjusted cell;

[0138] determine the target load sharing cell from the main lobe direction cell and the back lobe direction cell according to the first level value difference and the second level value difference.

[0139] Further, in a possible implementation of the embodiment of the application, the first determining module 902 is further configured to include:

[0140] obtain a preset level value difference threshold;

[0141] if the first level value difference is less than the preset level value difference threshold, the main lobe direction cell is taken as the target load sharing cell;

[0142] if the second level value difference is less than the preset level value difference threshold, the back lobe direction cell is taken as the target load sharing cell.

[0143] It should be noted that the foregoing explanation and description of the embodiment of the cell load balancing adjustment method also apply to the cell load balancing adjustment device of this embodiment, which will not be described here again.

[0144] In the embodiments of the present application, the observation sampling data of the to-be-adjusted cell and the to-be-adjusted cell are acquired, wherein the to-be-adjusted cell has a corresponding initial load parameter, and the observation sampling data is used to determine a target load sharing cell of the to-be-adjusted cell. According to the observation sampling data, the target load sharing cell of the to-be-adjusted cell is determined. The candidate parameter adjustment strategy of the to-be-adjusted cell and the key communication index data are acquired. According to the initial load parameter, the target load sharing cell, the candidate parameter adjustment strategy and the key communication index data, the target load parameter of the to-be-adjusted cell is determined. According to the target load parameter, the load balancing adjustment scheme of the to-be-adjusted cell is generated. The accurate quantitative adjustment of the cell parameter is realized in an automatic and intelligent manner. The load balancing adjustment scheme is obtained. The technical problem of incomplete and incomplete manual parameter adjustment is effectively solved. The load parameter adjustment efficiency is effectively improved. The load balancing adjustment scheme has a short output time, and meets the timeliness and accuracy requirements of the existing network optimization.

[0145] In order to realize the above-mentioned embodiments, the present application further provides an electronic device, comprising: a processor and a memory connected with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to realize the cell load balancing adjustment method provided by the foregoing embodiments.

[0146] In order to realize the above-mentioned embodiments, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to realize the cell load balancing adjustment method provided by the foregoing embodiments.

[0147] In order to realize the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, which is executed by a processor to realize the cell load balancing adjustment method provided by the foregoing embodiments.

[0148] The collection, storage, use, processing, transmission, provision and disclosure of user personal information in the present application comply with relevant laws and regulations, and do not violate public order and good customs.

[0149] It should be noted that the personal information from the user should be collected for legal and reasonable purposes, and should not be shared or sold outside these legal uses. In addition, such collection / sharing should be carried out after the user's informed consent is obtained, including but not limited to informing the user to read the user agreement / user notice before the user uses the function, and signing the agreement / authorization including authorization of relevant user information. In addition, any necessary steps should be taken to protect and ensure access to such personal information data, and to ensure that other people with access to personal information data comply with their privacy policy and processes.

[0150] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0151] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0152] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0153] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0154] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or a combination thereof. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus or device. The computer readable medium can specifically be, but is not limited to, the following: an electronic connection (electronic apparatus) having one or more wires, a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disk read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium upon which the program can be printed, because the program can be electronically obtained, for example, by optically scanning the paper or other medium, then

[0155] It should be understood that portions of the application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware and in another embodiment, any of the following technologies, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions upon data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0156] Those of skill in the art could readily implement the above described example methods with all or a portion of the disclosed steps carried out by a program for use with a computer system or similar electronic apparatus, or carried out by such a system or apparatus itself. The aforementioned methods can be written as one or more computer programs (for use with different operating systems or platforms) to implement the disclosed example methods.

[0157] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0158] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for adjusting load balancing in a residential community, characterized in that, Includes the following steps: Acquire the cell to be adjusted and the observation sampling data of the cell to be adjusted, wherein the cell to be adjusted has corresponding initial load parameters, and the observation sampling data is used to determine the target load-sharing cell of the cell to be adjusted; Based on the observed sampling data, the target load-sharing cell for the cell to be adjusted is determined; Obtain the candidate parameter adjustment strategy and key communication indicator data of the cell to be adjusted; The target load parameters of the cell to be adjusted are determined based on the initial load parameters, the target load-sharing cell, the candidate parameter adjustment strategy, and the key communication indicator data. A load balancing adjustment scheme for the cell to be adjusted is generated based on the target load parameters; The step of determining the target load parameters of the cell to be adjusted based on the initial load parameters, the target load-sharing cell, the candidate parameter adjustment strategy, and the key communication indicator data includes: Based on the candidate parameter adjustment strategy, a combination of multiple candidate load parameters for the cell to be adjusted is determined; Based on the target load-sharing cell, the initial load parameters, and the key communication indicator data, determine the candidate fitness function value corresponding to each candidate load parameter combination; The target load parameter is determined from the plurality of candidate load parameter combinations based on the candidate fitness function values; The key communication indicator data includes: the first load rate corresponding to the cell to be adjusted; The step of determining the candidate fitness function value corresponding to each candidate load parameter combination based on the target load-sharing cell, the initial load parameters, and the key communication indicator data includes: Obtain the second load rate corresponding to the target load-sharing cell; The initial fitness function value corresponding to the candidate load parameter combination is determined based on the fitness function calculation expression. Based on the first load rate and the second load rate, determine the transfer probability value of the initial load parameters to the reference load parameters of the target load-sharing cell; The initial fitness function value is updated based on the transition probability value to obtain the candidate fitness function value.

2. The method according to claim 1, characterized in that, The step of determining multiple candidate load parameter combinations for the cell to be adjusted according to the candidate parameter adjustment strategy includes: Determine the parameter to be adjusted corresponding to the candidate parameter adjustment strategy and the parameter adjustment range corresponding to the parameter to be adjusted; The solution space calculation is performed on the parameter to be adjusted and the parameter adjustment range corresponding to the parameter to be adjusted to obtain the multiple candidate load parameter combinations.

3. The method according to claim 1, characterized in that, The step of determining the target load parameter from the plurality of candidate load parameter combinations based on the candidate fitness function value includes: Get the preset function value threshold; If the candidate fitness function value is less than the preset function value threshold, then the candidate load parameter combination corresponding to the candidate fitness function value is used as the target load parameter.

4. The method according to claim 1, characterized in that, The step of determining the target load-sharing cell for the cell to be adjusted based on the observed sampling data includes: Obtain multiple candidate load-sharing cells; Based on the observed sampling data, determine the correlation coefficient between each candidate load-sharing cell and the cell to be adjusted; If the correlation coefficient is greater than the preset correlation coefficient threshold, then the candidate load-sharing cell corresponding to the correlation coefficient is used as the reference load-sharing cell. The reference load-sharing cell is filtered to obtain the target load-sharing cell.

5. The method according to claim 4, characterized in that, The step of determining the correlation coefficient between each candidate load-sharing cell and the cell to be adjusted based on the observed sampling data includes: Determine the total number of data sampling points corresponding to the observed sampling data; The number of times the candidate load-sharing cell appears in the observed sampling data is determined as a reference number; Based on the total number of sampling points and the reference count, the frequency value of the candidate load-sharing cell appearing in the observed sampling data is determined, and the frequency value is used as the correlation coefficient.

6. The method according to claim 4, characterized in that, The step of filtering the reference load-sharing cell to obtain the target load-sharing cell includes: The reference load-sharing cell is subjected to long-range filtering to obtain the main lobe direction cell and the back lobe direction cell in the reference load-sharing cell. Determine the first level difference between the main lobe direction cell and the cell to be adjusted, and the second level difference between the back lobe direction cell and the cell to be adjusted; The target load-sharing cell is determined from the main lobe direction cell and the back lobe direction cell based on the first level value difference and the second level value difference.

7. The method according to claim 6, characterized in that, The step of determining the target load-sharing cell from the main lobe direction cells and the back lobe direction cells based on the first level value difference and the second level value difference includes: Obtain the preset level difference threshold; If the first level difference is less than the preset level difference threshold, then the main lobe direction cell is taken as the target load-sharing cell; If the difference in the second level value is less than the preset level value difference threshold, then the back lobe direction cell is taken as the target load-sharing cell.

8. A community load balancing adjustment device, characterized in that, include: The first acquisition module is used to acquire the cell to be adjusted and the observation sampling data of the cell to be adjusted, wherein the cell to be adjusted has corresponding initial load parameters, and the observation sampling data is used to determine the target load-sharing cell of the cell to be adjusted. The first determining module is used to determine the target load-sharing cell of the cell to be adjusted based on the observed sampling data; The second acquisition module is used to acquire the candidate parameter adjustment strategy and key communication indicator data of the cell to be adjusted; The second determining module is used to determine the target load parameters of the cell to be adjusted based on the initial load parameters, the target load sharing cell, the candidate parameter adjustment strategy, and the key communication indicator data. The generation module is used to generate a load balancing adjustment scheme for the cell to be adjusted based on the target load parameters. The second determining module is specifically used for: Based on the candidate parameter adjustment strategy, a combination of multiple candidate load parameters for the cell to be adjusted is determined; Based on the target load-sharing cell, the initial load parameters, and the key communication indicator data, determine the candidate fitness function value corresponding to each candidate load parameter combination; The target load parameter is determined from the plurality of candidate load parameter combinations based on the candidate fitness function values; The key communication indicator data includes: the first load rate corresponding to the cell to be adjusted; The step of determining the candidate fitness function value corresponding to each candidate load parameter combination based on the target load-sharing cell, the initial load parameters, and the key communication indicator data includes: Obtain the second load rate corresponding to the target load-sharing cell; The initial fitness function value corresponding to the candidate load parameter combination is determined based on the fitness function calculation expression. Based on the first load rate and the second load rate, determine the transfer probability value of the initial load parameters to the reference load parameters of the target load-sharing cell; The initial fitness function value is updated based on the transition probability value to obtain the candidate fitness function value.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the cell load balancing adjustment method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the cell load balancing adjustment method as described in any one of claims 1-7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the cell load balancing adjustment method according to any one of claims 1-7.

Images