Terminal migration method, device, and storage medium

Abstract

This application provides a terminal migration method, device, and storage medium. Belonging to the field of communications, the method includes: identifying terminals to be migrated in energy-saving cells within a preset area, along with a first predicted traffic volume for the energy-saving cell within a preset future time period and a second predicted traffic volume for co-covering cells within the same preset future time period; determining the receiving terminal capacity of each co-covering cell based on the second predicted traffic volume value of each co-covering cell; determining the optimal co-covering cell corresponding to each terminal to be migrated; and determining the co-covering cell to be migrated for each terminal based on the receiving terminal capacity of each co-covering cell and the optimal co-covering cell corresponding to each terminal to be migrated. This invention can guarantee the success rate of terminal migration and service performance in energy-saving cells.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a terminal migration method, device, and storage medium. Background Technology

[0002] Cell shutdown or cell terminal migration technology refers to the technology of identifying cells that can be shut down as energy-saving cells from the cells managed by the network equipment in order to avoid energy waste of network equipment, and migrating the terminals in the energy-saving cells to other adjacent cells with the same coverage.

[0003] In existing cell shutdown technologies, after an energy-saving cell is shut down, terminals under the energy-saving cell will automatically connect to other cells with the same coverage area within the energy-saving cell's coverage area. For example, a terminal may connect to a cell with the same coverage area randomly or based on the measured signal strength of a neighboring cell. This cannot guarantee the success rate of the terminal's migration from the energy-saving cell to a cell with the same coverage area, nor can it guarantee the service performance of the terminal after it has migrated to the cell with the same coverage area.

[0004] Therefore, the present invention provides a terminal migration method, device and storage medium, which can determine the corresponding co-coverage cell for each terminal to be migrated based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, thereby improving the success rate of terminal migration while ensuring the service performance after the terminal migration. Summary of the Invention

[0005] This application provides a terminal migration method, device, and storage medium to solve the problems of not being able to guarantee the success rate of terminal migration from an energy-saving cell to a cell with the same coverage and the service performance after migration.

[0006] Firstly, this application provides a terminal migration method, including:

[0007] Within a preset area, an energy-saving community, terminals to be migrated in the energy-saving community, and a first predicted traffic volume value for the energy-saving community within a preset future time period are identified.

[0008] Among the cells adjacent to the energy-saving cell, cells with the same coverage as the energy-saving cell are selected. For each cell with the same coverage, a second predicted value of the traffic volume of the cell with the same coverage is determined in a preset future time based on the first predicted value of traffic volume and the compensation weight value of the cell with the same coverage. The compensation weight value is used to indicate the ability of the cell with the same coverage to accept the traffic volume of the energy-saving cell.

[0009] The receiving terminal capacity of each of the co-coverage cells is determined based on the second traffic volume prediction value of each co-coverage cell;

[0010] For each terminal to be migrated, determine the optimal co-coverage cell corresponding to the terminal to be migrated; based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, determine the co-coverage cell to be migrated for each terminal to be migrated.

[0011] In one possible design, determining the energy-saving cell within a preset area and the terminals to be migrated within the energy-saving cell includes:

[0012] Within the preset area, cells with preset configuration data of a specified value are identified as energy-saving cells, and terminals in the energy-saving cells are identified as terminals to be migrated; wherein, the preset configuration data includes one or more preset energy-saving attributes, preset frequency bands, and preset network standards.

[0013] In one possible design, determining the energy-saving cell within a preset area and the terminals to be migrated within the energy-saving cell includes:

[0014] Obtain historical performance data for each cell within the preset area over a preset historical period. The historical performance data includes one or more of the following: average PRB resource utilization, average RRC connection count, average call completion rate, average handover success rate, average service transmission latency, average service transmission rate, and average network device energy consumption.

[0015] Based on the historical performance data, a shutdown weight is determined; wherein the larger the average network device energy consumption and the average service transmission latency, the larger the shutdown weight; the smaller the average connection rate, the average handover success rate, the average service transmission rate, the average PRB resource utilization rate, and the average RRC connection number, the smaller the shutdown weight.

[0016] Cells whose shutdown weight value is greater than a preset shutdown threshold are identified as energy-saving cells;

[0017] The terminals in the energy-saving community are selected as the terminals to be migrated.

[0018] In one possible design, determining the first predicted traffic volume of the energy-saving community within a preset future time period includes:

[0019] First method: Input the preset future time into the trained first time prediction model to obtain the traffic volume of the energy-saving cell within the preset future time period output by the first time prediction model, and use the traffic volume of the energy-saving cell within the preset future time period as the first traffic volume prediction value; wherein, the first time prediction model is a time series prediction model; or

[0020] The second method involves inputting the preset future time into a second time prediction model to obtain a first service load prediction value for the energy-saving community at the preset future time, output by the second time prediction model; wherein the second time prediction model is a time series prediction model; inputting the first service load prediction value into a trained third prediction model to obtain the service volume of the energy-saving community at the preset future time, output by the third prediction model, and using the service volume of the energy-saving community at the preset future time as the first service volume prediction value; wherein the third prediction model is a random forest or XGBoost model.

[0021] In one possible design, the method further includes:

[0022] The first prediction error of the first time prediction model is determined by the first sample validation data.

[0023] The second prediction error of the second time prediction model is determined by the second sample validation data;

[0024] If the first prediction error is less than the second prediction error, the first predicted traffic volume value is determined using the first method; if the first prediction error is not less than the second prediction error, the first predicted traffic volume value is determined using the second method.

[0025] In one possible design, determining a second traffic volume forecast value for each of the co-coverage cells within a preset future time period, based on the first traffic volume forecast value and the compensation weight value of the co-coverage cell, includes:

[0026] For each of the aforementioned co-coverage cells, the compensation weight is determined based on one or more of the following combinations: signal strength weight, handover relationship weight, and service load weight.

[0027] Based on the first traffic volume forecast value and the compensation weight value, determine the second traffic volume forecast value of the same coverage cell within a preset future time period;

[0028] The signal strength weight is determined based on the ratio of the number of measurement reports in which the signal strength of the same coverage cell measured by the terminal to be migrated is greater than a preset strength to the total number of measurement reports;

[0029] The handover relationship weight is determined based on the ratio of the number of handovers between the energy-saving cell and the cell with the same coverage to the total number of handovers between the energy-saving cell and the neighboring cells;

[0030] The service load weight is determined based on the ratio of the service load of the same coverage cell to that of the energy-saving cell.

[0031] In one possible design, determining the receiving terminal capacity of each of the co-coverage cells based on a second traffic volume prediction value for each of the co-coverage cells includes:

[0032] For each of the co-coverage cells, the proportion of the second traffic volume prediction value of the co-coverage cell is determined based on the second traffic volume prediction value of the co-coverage cell and the sum of the second traffic volume prediction values ​​of all the co-coverage cells.

[0033] The receiving terminal capacity of the same coverage cell is obtained based on the proportion of the second traffic volume forecast and the number of terminals to be migrated.

[0034] In one possible design, determining the optimal co-coverage cell corresponding to each terminal to be migrated includes:

[0035] For each terminal to be migrated, a migration weight for each of the co-coverage cells is determined based on the number of successful handovers from the terminal to be migrated to each co-coverage cell within a preset historical time period; or

[0036] Obtain the measurement reports of the terminal to be migrated within a preset historical time period, take the cell with the strongest signal in each measurement report as the target cell, and determine the migration weight of each cell with the same coverage as the target cell based on the number of times each cell with the same coverage is used as the target cell.

[0037] Based on the migration weight of each of the co-coverage cells, the optimal co-coverage cell corresponding to each terminal to be migrated is determined.

[0038] In one possible design, determining the optimal co-coverage cell corresponding to each terminal to be migrated based on the migration weight of each co-coverage cell includes:

[0039] Each of the co-coverage cells is sorted in descending order of migration weight to obtain the sorting result of the co-coverage cells;

[0040] Based on the sorting results, the cell with the highest sorting order is determined as the optimal cell with the same coverage for the terminal to be migrated.

[0041] In one possible design, determining the co-coverage cell to be migrated for each terminal to be migrated, based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, includes:

[0042] When the co-coverage cell is determined to be the optimal co-coverage cell for the terminal to be migrated, the terminal to be migrated is determined to be the associated terminal of the co-coverage cell;

[0043] For each of the same coverage cells, compare the receiving terminal capacity and the number of associated terminals;

[0044] If the capacity of the receiving terminal is not less than the number of associated terminals, then the co-coverage cell is determined to be the co-coverage cell to be migrated for the associated terminal.

[0045] In one possible design, if the capacity of the receiving terminal is less than the number of associated terminals, the method further includes:

[0046] For all associated terminals in the same coverage cell, the terminal weight of each associated terminal is determined based on the number of successful handovers between each associated terminal and the same coverage cell within a preset historical time period; or, the measurement reports of each associated terminal within a preset historical time period are obtained, and the terminal weight of each associated terminal is determined based on the number of measurement reports of the cell with the strongest signal in the same coverage cell.

[0047] The associated terminals are sorted in descending order of their terminal weights;

[0048] For the associated terminal whose ranking is not greater than the receiving terminal capacity, the co-coverage cell is designated as the co-coverage cell to be migrated for the associated terminal;

[0049] For the associated terminal whose ranking is greater than the receiving terminal capacity, any one of the co-coverage cells whose receiving terminal capacity is not less than the number of associated terminals is selected as the co-coverage cell to be migrated for the associated terminal.

[0050] In one possible design, after determining the corresponding co-coverage cell for each terminal to be migrated, the method further includes:

[0051] Before the energy-saving cell enters the energy-saving shutdown state, it is instructed to send a migration instruction message to each terminal to be migrated, which is used to instruct the terminal to be migrated to access the corresponding cell with the same coverage.

[0052] Secondly, this application provides a terminal migration device, comprising:

[0053] The first determining module is used to determine energy-saving communities, terminals to be migrated in the energy-saving communities, and a first business volume prediction value of the energy-saving communities within a preset future time period within a preset area.

[0054] The second determining module is used to filter out the co-coverage cells corresponding to the energy-saving cell from the cells adjacent to the energy-saving cell, and for each co-coverage cell, determine the second traffic volume prediction value of the co-coverage cell in a preset future time according to the first traffic volume prediction value and the compensation weight value of the co-coverage cell, wherein the compensation weight value is used to indicate the ability of the co-coverage cell to accept the traffic volume of the energy-saving cell.

[0055] The third determining module is used to determine the receiving terminal capacity of each of the co-coverage cells based on the second traffic volume prediction value of each co-coverage cell;

[0056] The fourth determining module is used to determine the optimal co-coverage cell corresponding to each terminal to be migrated; and to determine the co-coverage cell to be migrated corresponding to each terminal to be migrated based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated.

[0057] In one possible design, the first determining module is further configured to:

[0058] Within the preset area, cells with preset configuration data of a specified value are identified as energy-saving cells, and terminals in the energy-saving cells are identified as terminals to be migrated; wherein, the preset configuration data includes one or more preset energy-saving attributes, preset frequency bands, and preset network standards.

[0059] In one possible design, the first determining module further includes an acquiring module;

[0060] The acquisition module is used to acquire historical performance data of each cell in the preset area over a preset historical time. The historical performance data includes one or more of the following: average PRB resource utilization, average RRC connection count, average call completion rate, average handover success rate, average service transmission latency, average service transmission rate, and average network device energy consumption.

[0061] The first determining module is further configured to: determine a shutdown weight based on the historical performance data; wherein the larger the average energy consumption of the network device and the average service transmission latency, the larger the shutdown weight; and the smaller the average connection rate, the average handover success rate, the average service transmission rate, the average PRB resource utilization rate, and the average RRC connection number, the smaller the shutdown weight.

[0062] Cells whose shutdown weight value is greater than a preset shutdown threshold are identified as energy-saving cells;

[0063] The terminals in the energy-saving community are selected as the terminals to be migrated.

[0064] In one possible design, the first determining module is further configured to: determine the first predicted service volume value of the energy-saving community within a preset future time according to method one or method two;

[0065] First method: Input the preset future time into the trained first time prediction model to obtain the traffic volume of the energy-saving cell within the preset future time period output by the first time prediction model, and use the traffic volume of the energy-saving cell within the preset future time period as the first traffic volume prediction value; wherein, the first time prediction model is a time series prediction model; or

[0066] The second method involves inputting the preset future time into a trained second time prediction model to obtain a first service load prediction value for the energy-saving cell in the preset future time, output by the second time prediction model; wherein the second time prediction model is a time series prediction model; inputting the first service load prediction value into a trained third prediction model to obtain the service volume of the energy-saving cell in the preset future time, output by the third prediction model, and using the service volume of the energy-saving cell in the preset future time as the first service volume prediction value; wherein the third prediction model is a random forest or XGBoost model.

[0067] In one possible design, the first determining module is further configured to:

[0068] The first prediction error of the first time prediction model is determined by the first sample validation data.

[0069] The second prediction error of the second time prediction model is determined by the second sample validation data;

[0070] If the first prediction error is less than the second prediction error, the first predicted traffic volume value is determined using the first method; if the first prediction error is not less than the second prediction error, the first predicted traffic volume value is determined using the second method.

[0071] In one possible design, the second determining module is further configured to:

[0072] For each of the aforementioned co-coverage cells, the compensation weight is determined based on one or more of the following combinations: signal strength weight, handover relationship weight, and service load weight.

[0073] Based on the first traffic volume forecast value and the compensation weight value, determine the second traffic volume forecast value of the same coverage cell within a preset future time period;

[0074] The signal strength weight is determined based on the ratio of the number of measurement reports in which the signal strength of the same coverage cell measured by the terminal to be migrated is greater than a preset strength to the total number of measurement reports;

[0075] The handover relationship weight is determined based on the ratio of the number of handovers between the energy-saving cell and the cell with the same coverage to the total number of handovers between the energy-saving cell and the neighboring cells;

[0076] The service load weight is determined based on the ratio of the service load of the same coverage cell to that of the energy-saving cell.

[0077] In one possible design, the third determining module is further configured to:

[0078] For each of the co-coverage cells, the proportion of the second traffic volume prediction value of the co-coverage cell is determined based on the second traffic volume prediction value of the co-coverage cell and the sum of the second traffic volume prediction values ​​of all the co-coverage cells.

[0079] The receiving terminal capacity of the same coverage cell is obtained based on the proportion of the second traffic volume forecast and the number of terminals to be migrated.

[0080] In one possible design, the fourth determining module is further configured to:

[0081] For each terminal to be migrated, a migration weight for each of the co-coverage cells is determined based on the number of successful handovers from the terminal to be migrated to each co-coverage cell within a preset historical time period; or

[0082] Obtain the measurement reports of the terminal to be migrated within a preset historical time period, take the cell with the strongest signal in each measurement report as the target cell, and determine the migration weight of each cell with the same coverage as the target cell based on the number of times each cell with the same coverage is used as the target cell.

[0083] Based on the migration weight of each of the co-coverage cells, the optimal co-coverage cell corresponding to each terminal to be migrated is determined.

[0084] In one possible design, the fourth determining module is further configured to:

[0085] Each of the co-coverage cells is sorted in descending order of migration weight to obtain the sorting result of the co-coverage cells;

[0086] Based on the sorting results, the cell with the highest sorting order is determined as the optimal cell with the same coverage for the terminal to be migrated.

[0087] In one possible design, the fourth determining module is further configured to:

[0088] When the co-coverage cell is determined to be the optimal co-coverage cell for the terminal to be migrated, the terminal to be migrated is determined to be the associated terminal of the co-coverage cell;

[0089] For each of the same coverage cells, compare the receiving terminal capacity and the number of associated terminals;

[0090] If the capacity of the receiving terminal is not less than the number of associated terminals, then the co-coverage cell is determined to be the co-coverage cell to be migrated for the associated terminal.

[0091] In one possible design, the fourth determining module is further configured to:

[0092] For all associated terminals in the same coverage cell, the terminal weight of each associated terminal is determined based on the number of successful handovers between each associated terminal and the same coverage cell within a preset historical time period; or, the measurement reports of each associated terminal within a preset historical time period are obtained, and the terminal weight of each associated terminal is determined based on the number of measurement reports of the cell with the strongest signal in the same coverage cell.

[0093] The associated terminals are sorted in descending order of their terminal weights;

[0094] For the associated terminal whose ranking is not greater than the receiving terminal capacity, the co-coverage cell is designated as the co-coverage cell to be migrated for the associated terminal;

[0095] For the associated terminal whose ranking is greater than the receiving terminal capacity, any one of the co-coverage cells whose receiving terminal capacity is not less than the number of associated terminals is selected as the co-coverage cell to be migrated for the associated terminal.

[0096] In one possible design, a sending module is also included, which is used for:

[0097] After determining the corresponding co-coverage cell for each terminal to be migrated, before the energy-saving cell enters the energy-saving shutdown state, the energy-saving cell is instructed to send a migration instruction message to each terminal to be migrated, instructing the terminal to be migrated to access the corresponding co-coverage cell.

[0098] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0099] The memory stores computer-executed instructions;

[0100] The processor executes computer execution instructions stored in the memory to implement a terminal migration device method.

[0101] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement a terminal migration device method.

[0102] This application provides a terminal migration device method, device, and storage medium. Within a preset area, it identifies terminals to be migrated in energy-saving cells, along with a first predicted traffic volume for the energy-saving cell within a preset future time period and a second predicted traffic volume for co-coverage cells within the same future time period. Based on the second predicted traffic volume for each co-coverage cell, it determines the receiving terminal capacity of each co-coverage cell. For each terminal to be migrated, it determines the optimal co-coverage cell corresponding to the terminal to be migrated. Based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, it determines the co-coverage cell to be migrated for each terminal to be migrated. This achieves the following technical effects:

[0103] The method of the present invention can determine the corresponding co-coverage cell for each terminal to be migrated based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, thereby improving the success rate of terminal migration while ensuring the service performance after the terminal migration.

[0104] Based on the first traffic volume forecast of the energy-saving cell in a future time (a preset future time) and the compensation weight of the co-coverage cell, the second traffic volume forecast of each co-coverage cell in the preset future time is determined. The compensation weight is used to indicate the co-coverage cell's ability to accept traffic from the energy-saving cell. According to the compensation weight, the second traffic volume forecast of the co-coverage cell can be determined based on the higher the signal coverage similarity between the co-coverage cell and the energy-saving cell, the more frequent the handover between them, or the traffic load of the co-coverage cell. That is, the traffic volume forecast that each co-coverage cell can handle in the preset future time. Then, based on the proportion of the second traffic volume forecast of each co-coverage cell in the sum of the second traffic volume forecasts of all co-coverage cells, the number of terminals to be migrated that each co-coverage cell can accept is determined, i.e., the receiving terminal capacity. Thus, the terminals to be migrated are allocated to multiple co-coverage cells according to the receiving terminal capacity of each co-coverage cell. In this way, the number of terminals to be migrated that each co-coverage cell can handle is matched with the traffic load and signal coverage of that co-coverage cell, avoiding problems such as cell congestion and failure to access the cell due to insufficient signal strength after the terminal is migrated to the co-coverage cell, thereby improving the success rate of terminal migration.

[0105] In addition, the optimal co-coverage cell corresponding to each terminal to be migrated is determined based on the number of successful handovers in the history or measurement reports. Then, the co-coverage cell to be migrated for each terminal to be migrated is determined from the optimal co-coverage cells. In this way, the terminal to be migrated can be preferentially migrated to the co-coverage cell with the strongest signal strength or the most successful handovers in the history, thereby improving the success rate of the migration of the terminal from the energy-saving cell to the co-coverage cell and the service performance after migration. Attached Figure Description

[0106] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0107] Figure 1 This is a schematic diagram of a scenario involved in an embodiment of this application;

[0108] Figure 2 A flowchart illustrating a terminal migration method provided in this application embodiment. Figure 1 ;

[0109] Figure 3 A flowchart illustrating a terminal migration method provided in this application embodiment. Figure 2 ;

[0110] Figure 4 A flowchart illustrating a terminal migration method provided in this application embodiment. Figure 2 Flowchart of S307 Figure 3 ;

[0111] Figure 5 This is a schematic diagram of the structure of a terminal migration device provided in an embodiment of this application;

[0112] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0113] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0114] It should be noted that, in the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0115] The following describes in detail, with reference to the accompanying drawings, a terminal migration method provided by an embodiment of this application.

[0116] Figure 1 This is a schematic diagram illustrating the application scenario involved in this embodiment, such as... Figure 1 As shown, within a preset area, network devices may include one or more cellular cells, each cell covering its own terminals. The energy-saving management device interacts with each network device to obtain its cell's configuration data, historical performance data, measurement reports, handover data, traffic volume, traffic load, and other data.

[0117] The method in this embodiment is used in an energy-saving management device. Based on data obtained through information interaction with network equipment, it determines the terminals to be migrated in the energy-saving cell, as well as the first traffic volume prediction value of the energy-saving cell within a preset future time and the second traffic volume prediction value of the co-coverage cell within a preset future time. Based on the second traffic volume prediction value, it determines the receiving terminal capacity of each co-coverage cell. For each terminal to be migrated, it determines the optimal co-coverage cell corresponding to the terminal to be migrated. Based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, it determines the co-coverage cell to be migrated for each terminal to be migrated.

[0118] The method of this invention determines the target migration terminal for each co-coverage cell based on the receiving terminal capacity and associated terminals of each co-coverage cell. This method allows for matching each terminal to be migrated with a co-coverage cell based on the service capabilities and performance of the terminal to be migrated and the co-coverage cell, ensuring both migration success rate and service performance.

[0119] Figure 2 A schematic flowchart of a terminal migration method provided in this application embodiment. Figure 1 .like Figure 2 As shown, the method includes:

[0120] S201. Within a preset area, determine the energy-saving community, the terminals to be migrated in the energy-saving community, and the first business volume forecast value of the energy-saving community within a preset future time.

[0121] Specifically, within a preset area, energy-saving communities can be determined based on historical performance data or preset configuration data; the terminals in an energy-saving community are the terminals to be migrated within that community.

[0122] As one possible implementation, if energy-saving cells are determined based on preset configuration data, within a preset area, cells whose preset configuration data has a specified value are designated as energy-saving cells. The preset configuration data includes one or more of preset energy-saving attributes, preset frequency bands, and preset network standards. The preset energy-saving attributes include those that can be turned off and those that cannot be turned off; the preset frequency band is a specific preset frequency band; and the preset network standard includes 3G, 4G, 5G, and other network standards.

[0123] For example, when the preset energy-saving attribute is set to "can be turned off," if a cell's coverage area is a VIP protection area or a private network area, then the preset energy-saving attribute of that cell is "cannot be turned off." This cell cannot be turned off as an energy-saving cell to ensure the network performance of terminals within the cell. Similarly, when the preset frequency band is set to a high-frequency band, the identified energy-saving cell is a high-frequency band cell, enabling the shutdown of high-frequency band cells and the activation of low-frequency band cells. This allows for energy saving while utilizing the wide coverage of low-frequency band cells to meet signal coverage requirements. Furthermore, when the preset network standard is set to 5G, the identified energy-saving cell is a 5G cell, enabling the shutdown of high-energy-consuming 5G cells and the activation of low-energy-consuming 4G cells, thus reducing the total energy consumption of the energy-saving cell's coverage area.

[0124] As another possible implementation, if energy-saving cells are determined based on the acquired historical performance data, the method includes: acquiring the historical performance data of the cell within a preset historical time period through the network equipment where each cell is located, obtaining the shutdown weight based on the historical performance data, and designating cells with shutdown weights greater than the shutdown threshold as energy-saving cells.

[0125] Historical performance data includes one or more of the following: average PRB resource utilization, average RRC connection count, average connection success rate, average handover success rate, average service transmission latency, average service transmission rate, and average network device energy consumption.

[0126] Among them, the higher the average energy consumption of network equipment and the average service transmission latency, the higher the shutdown weight; the lower the average connection rate, average handover success rate, average service transmission rate, average PRB resource utilization, and average RRC connection number, the lower the shutdown weight. The setting of the shutdown weight can identify high-energy-consuming, poor-performing, and low-load cells as energy-saving cells and prioritize their shutdown.

[0127] This embodiment determines energy-saving cells based on cell configuration data. It can prioritize shutting down cells of specified frequency bands and network standards, or prohibit the shutdown of certain specified cells, in order to meet differentiated energy-saving needs. It can also determine energy-saving cells based on historical performance data. It can prioritize shutting down cells with high energy consumption, poor service performance, and low load, thereby reducing the total energy consumption of the preset area and improving service performance.

[0128] As one possible implementation, the first traffic volume forecast can be directly predicted using a first-time prediction model based on a preset historical time and the traffic volume within a preset historical time. Alternatively, it can be indirectly predicted using a second-time prediction model and a third-time prediction model based on a preset historical time and the traffic load within a preset historical time, in order to predict the traffic volume of the energy-saving community within a preset future time.

[0129] S202. Among the communities adjacent to the energy-saving community, select the corresponding co-coverage communities. For each co-coverage community, determine the second business volume forecast value of the co-coverage community in a preset future time based on the first business volume forecast value and the compensation weight value of the co-coverage community. The compensation weight value is used to indicate the co-coverage community's ability to accept the business volume of the energy-saving community.

[0130] Specifically, a co-coverage cell is defined as: among the cells adjacent to an energy-saving cell, the cell with a higher degree of overlap with the coverage area of ​​the energy-saving cell, or the cell that enables terminals in the energy-saving cell to receive stronger signals; therefore, a co-coverage cell is determined based on any one of the following: operating parameters, measurement reports, or handover data.

[0131] Among them, the working parameters of each community include the latitude, longitude, azimuth and other information of the network equipment in the community, which can be preset in the energy-saving management device; the distance between two network equipment can be calculated based on the latitude and longitude of the network equipment;

[0132] The measurement report is generated by the terminal measurement and sent to the network device. Each measurement report includes information such as the signal strength of the energy-saving cell and neighboring cells.

[0133] The handover data includes records of terminals in the energy-saving community switching between different communities; each handover data entry includes information such as the source community and target community, and whether the handover was successful.

[0134] Based on the engineering parameters, measurement reports, and handover data, we can identify cells with a higher degree of overlap with the coverage area of ​​the energy-saving community, or cells that enable terminals in the energy-saving community to receive stronger signals, as co-coverage cells.

[0135] The entity executing the above steps can be an energy-saving management device or a network device where the energy-saving community is located. If the entity executing the steps is an energy-saving management device, the energy-saving management device obtains the handover data of the energy-saving community within a preset future time through message interaction with the network device where the energy-saving community is located. If the entity executing the steps is a network device where the energy-saving community is located, the network device where the energy-saving community is located sends the information of the same coverage community to the energy-saving management device by sending a message after determining the same coverage community.

[0136] Specifically, the compensation weight is a combination of one or more of the signal strength weight, handover relationship weight, and service load weight within a preset future time period. The product of the compensation weight of the same coverage cell and the first service volume prediction value of the same coverage cell is determined as the second service volume prediction value of the same coverage cell.

[0137] The second traffic volume prediction value is the predicted traffic volume that the co-coverage cell can handle. The second traffic volume prediction value of each co-coverage cell is determined according to the compensation weight value. The traffic volume of the energy-saving cell can be allocated to multiple co-coverage cells according to the size of the compensation weight value. If the signal coverage similarity between a co-coverage cell and the energy-saving cell is higher, the handover between the two is more frequent, or the traffic load of the co-coverage cell is smaller, then the traffic volume allocated to that co-coverage cell is larger. In this way, more traffic volume of the energy-saving cell can be allocated to co-coverage cells with similar signal strength distribution, frequent handover between energy-saving cells, and smaller traffic load. This can improve the terminal migration success rate, so that the terminal in the coverage area of ​​the energy-saving cell has a stronger signal and better service performance after migrating to the co-coverage cell. At the same time, it can avoid problems such as cell congestion caused by allocating too much traffic volume to a high-load cell.

[0138] S203. Determine the receiving terminal capacity of each co-coverage cell based on the second traffic volume prediction value of each co-coverage cell.

[0139] Specifically, for each co-coverage cell, the predicted traffic volume ratio of that co-coverage cell is determined based on the proportion of the predicted traffic volume of the second traffic volume of the co-coverage cell to the predicted traffic volume of all co-coverage cells. Based on the predicted traffic volume ratio, the terminals to be migrated are allocated to each co-coverage cell. The receiving terminal capacity of each co-coverage cell is the number of terminals that the co-coverage cell can accept, and each co-coverage cell corresponds to one receiving terminal capacity.

[0140] This embodiment determines the receiving terminal capacity corresponding to each co-coverage cell based on the second traffic volume prediction value of each co-coverage cell. It realizes the proportional allocation of terminals to be migrated among different co-coverage cells based on factors such as the signal strength of each co-coverage cell, the handover relationship with energy-saving cells, and the traffic load. This can match the number of terminals to be migrated corresponding to each co-coverage cell with the traffic load and signal coverage of that co-coverage cell, avoiding problems such as cell congestion and failure to access the cell due to insufficient signal strength after the terminal is migrated to the co-coverage cell, thereby improving the success rate of terminal migration.

[0141] S204. For each terminal to be migrated, determine the optimal co-coverage cell corresponding to the terminal to be migrated; based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, determine the co-coverage cell to be migrated for each terminal to be migrated.

[0142] This embodiment determines the corresponding co-coverage cell for the terminal to be migrated based on the number of successful handovers in the past or measurement reports. Then, it prioritizes the selection of the co-coverage cell to be accessed from the co-coverage cells to be migrated. In this way, the terminal to be migrated can be preferentially switched to the co-coverage cell with the strongest signal or the most successful handovers in the past, thereby improving the success rate of the migration of the terminal from the energy-saving cell to the co-coverage cell and the service performance after migration.

[0143] S205. After determining the corresponding co-coverage cell for each terminal to be migrated, before the energy-saving cell enters the shutdown state, instruct the energy-saving cell to send a migration instruction message to the terminal to be migrated, which is used to instruct the terminal to be migrated to access the corresponding co-coverage cell.

[0144] Specifically, network devices can control the migration method of the terminal through migration instruction messages, ensuring the migration success rate and service performance of the terminal to be migrated while the community is shut down for energy saving.

[0145] The method provided in this embodiment determines, within a preset area, the terminals to be migrated in energy-saving cells, a first predicted traffic volume for the energy-saving cell within a preset future time, and a second predicted traffic volume for co-coverage cells within a preset future time. Based on the second predicted traffic volume for each co-coverage cell, the receiving terminal capacity of each co-coverage cell is determined. For each terminal to be migrated, the optimal co-coverage cell corresponding to the terminal to be migrated is determined. Based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, the corresponding co-coverage cell to be migrated for each terminal to be migrated is determined. This achieves the following technical effects:

[0146] Based on the first traffic volume forecast of the energy-saving cell in a future time (a preset future time) and the compensation weight of the co-coverage cell, the second traffic volume forecast of each co-coverage cell in the preset future time is determined. The compensation weight is used to indicate the co-coverage cell's ability to accept traffic from the energy-saving cell. According to the compensation weight, the second traffic volume forecast of the co-coverage cell can be determined based on the higher the signal coverage similarity between the co-coverage cell and the energy-saving cell, the more frequent the handover between them, or the traffic load of the co-coverage cell. That is, the traffic volume forecast that each co-coverage cell can handle in the preset future time. Then, based on the proportion of the second traffic volume forecast of each co-coverage cell in the sum of the second traffic volume forecasts of all co-coverage cells, the number of terminals to be migrated that each co-coverage cell can accept is determined, i.e., the receiving terminal capacity. Thus, the terminals to be migrated are allocated to multiple co-coverage cells according to the receiving terminal capacity of each co-coverage cell. In this way, the number of terminals to be migrated that each co-coverage cell can handle is matched with the traffic load and signal coverage of that co-coverage cell, avoiding problems such as cell congestion and failure to access the cell due to insufficient signal strength after the terminal is migrated to the co-coverage cell, thereby improving the success rate of terminal migration.

[0147] In addition, the optimal co-coverage cell corresponding to each terminal to be migrated is determined based on the number of successful handovers in the history or measurement reports. Then, the co-coverage cell to be migrated for each terminal to be migrated is determined from the optimal co-coverage cells. In this way, the terminal to be migrated can be preferentially migrated to the co-coverage cell with the strongest signal strength or the most successful handovers in the history, thereby improving the success rate of the migration of the terminal from the energy-saving cell to the co-coverage cell and the service performance after migration.

[0148] In summary, the method of the present invention can determine the corresponding co-coverage cell for each terminal to be migrated based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, thereby improving the success rate of terminal migration while ensuring the service performance after the terminal migration.

[0149] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. The same or similar concepts or processes may not be described again in some embodiments.

[0150] Figure 3 A schematic flowchart of a terminal migration method provided in this application embodiment. Figure 2 .like Figure 3 As shown, the method includes:

[0151] S301. Obtain historical performance data of each cell through the network equipment where each cell is located; obtain the shutdown weight based on the historical performance data; designate cells with shutdown weight greater than the shutdown threshold as energy-saving cells; designate terminals in energy-saving cells as terminals to be migrated.

[0152] Specifically, historical performance data includes one or more of the following over a preset historical period: average PRB resource utilization, average RRC connection count, average connection success rate, average handover success rate, average service transmission latency, average service transmission rate, and average network device energy consumption. The higher the average network device energy consumption and average service transmission latency, the higher the shutdown weight; conversely, the lower the average connection success rate, average handover success rate, average service transmission rate, average PRB resource utilization, and average RRC connection count, the lower the shutdown weight.

[0153] For example, the shutdown weight can be set as the ratio of a first mean parameter and a second mean parameter, wherein the first mean parameter is one or a combination of one or more of the network device power consumption average and the service transmission latency average; and the second mean is one or a combination of one or more of the connection success rate average, the handover success rate average, the service transmission rate average, the PRB resource utilization average, and the RRC connection number average.

[0154] For example, the combined value of the average energy consumption and the average service transmission delay can be defined as (average energy consumption / preset energy consumption value) * (average service transmission delay / preset time value), or a * (average energy consumption / preset energy consumption value) + b * (average service transmission delay / preset delay value), where a and b are weighting coefficients with values ​​ranging from 0 to 1, and a + b = 1;

[0155] This method can identify high-energy-consuming, poor-performing, and low-load cells as energy-saving cells and prioritize their shutdown, thereby reducing the total energy consumption of the preset area and improving service performance.

[0156] S302. Determine the first business volume forecast value of the energy-saving community within a preset future time within the preset area;

[0157] Specifically, the first business volume forecast can be obtained using either of the following two methods:

[0158] The first method is to input the preset future time into the trained first-time prediction model to obtain the traffic volume of the energy-saving community in the preset future time, and use the traffic volume of the energy-saving community in the preset future time as the first traffic volume prediction value.

[0159] For example, method one includes the following steps:

[0160] a. Obtain multiple traffic volume statistics for each cell within a preset historical time period; the traffic volume of a cell is statistically analyzed by the network device where the cell is located according to a preset period. The preset historical time includes multiple preset periods. For example, the preset historical time is 7*24 hours and the preset period is 15 minutes; the traffic volume can be defined as any one of the uplink and downlink data traffic of the cell or the sum of both.

[0161] b. Take multiple business volume statistics within a preset historical time period as sample data, i.e., the first sample, and input them into the preset first time prediction model to obtain the trained first prediction model; the first time prediction model is used to reflect the one-to-one correspondence between each preset period and the business volume; optionally, the first prediction model can adopt one of the existing time series prediction models, such as ARIMA, PROPHET, LSTM, neural network, etc.

[0162] c. Based on the first-time prediction model after training, obtain the first business volume prediction value corresponding to each preset period within the preset future time;

[0163] The second method involves inputting a preset future time into a trained second-time prediction model to obtain the first business load prediction value of the energy-saving community in the preset future time, as output by the second-time prediction model; wherein, the second-time prediction model is a time series prediction model; the first business load prediction value is input into a trained third prediction model to obtain the business volume of the energy-saving community in the preset future time, as output by the third prediction model, and the business volume of the energy-saving community in the preset future time is used as the first business volume prediction value.

[0164] For example, it includes the following steps:

[0165] a. Obtain multiple service load statistics for each cell within a preset historical time period; the acquisition method is the same as in step one and will not be repeated here; use the multiple service load statistics within the preset historical time period as sample data, i.e., the second sample, and input them into the preset second time prediction model to obtain the trained second time prediction model; the second time prediction model is used to reflect the one-to-one correspondence between each preset period and the service load; optionally, the second time prediction model can adopt existing time series prediction models, such as ARIMA, PROPHET, LSTM, neural network, etc.; where service load can be defined as PRB resource utilization or RRC connection count;

[0166] b. Based on the trained second-time prediction model, obtain the first business load prediction value corresponding to each preset period within the preset future time; the preset future time includes multiple preset periods. For example, the preset future time is 24 hours and the preset period is 15 minutes.

[0167] c. Obtain multiple traffic volume and traffic load statistics for each cell within a preset historical time period as sample data, i.e., the third sample, and input them into the preset third prediction model for training to obtain the trained third prediction model; the third prediction model is a function model used to reflect the one-to-one correspondence between traffic load and traffic volume; optionally, the third prediction model can adopt existing algorithm models such as random forest and Xgboost.

[0168] d. Input the first business load forecast value into the trained third prediction model to obtain the business volume within a preset future time period output by the third prediction model, which is used as the first business volume forecast value.

[0169] In this method, in order to determine the predicted value of cell traffic volume, the predicted value of cell traffic load is first determined, and then the predicted value of traffic volume corresponding to the predicted value of traffic load is obtained according to the correspondence between traffic volume and traffic load. Since the traffic load of the cell changes with time in a relatively regular manner, the predicted value of traffic load obtained based on the time series prediction algorithm is closer to the true value, thus making the prediction of traffic volume based on the function model more accurate.

[0170] Specifically, the first business forecast can also be obtained using a third method:

[0171] After the first-time prediction model is trained, the first prediction error of the first-time prediction model is obtained using the first sample validation data. After the second-time prediction model is trained, the second prediction error of the second-time prediction model is obtained using the second sample validation data. If the first prediction error is less than the second prediction error, the first traffic volume prediction value is obtained using the first method; if the first prediction error is not less than the second prediction error, the first traffic volume prediction value is obtained using the second method. The first sample validation data includes traffic volume statistics for the energy-saving community within a second historical period; the second sample validation data includes traffic load statistics for the energy-saving community within a second historical period; the second historical period is a preset time period.

[0172] Specifically, forecast error is used to reflect the deviation between the forecast and actual values ​​of business load in order to evaluate the accuracy of time series forecasts. It can be determined based on any one of the following indicators: mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute relative error (MAPE).

[0173] The prediction error can be determined based on sample data within a preset historical time period. Specifically, the sample data is divided into training data within a first historical time period and validation data within a second historical time period. The first and second historical times are a period within the preset historical time period and do not overlap in time. The prediction model is trained based on the training data, and the predicted value corresponding to the second historical time period is obtained. The deviation between the predicted value and the true value is determined based on the validation data within the second historical time period.

[0174] For example, if the prediction error is determined based on the mean absolute percentage error (MAPE), then the prediction error is: in, Indicates the predicted value, y i This represents the true value, and n represents the number of data points in the validation data.

[0175] S303. Among the communities adjacent to the energy-saving community, select the communities with the same coverage as the energy-saving community.

[0176] Specifically, the corresponding co-coverage cell for the energy-saving cell can be determined based on any one of the cell's operating parameters, measurement reports, or handover data. The specific content of the operating parameters, measurement reports, and handover data has already been explained in S202 and will not be repeated here. The method is as follows:

[0177] Method 1: Determine the same coverage cell based on engineering parameters:

[0178] If the distance between the network devices of a certain neighboring cell of an energy-saving cell is less than a preset distance threshold and the difference in azimuth angle is less than a preset angle threshold, then the neighboring cell is determined as the same coverage cell corresponding to the energy-saving cell.

[0179] Method 2: Determine the same coverage cell based on the measurement report:

[0180] Obtain multiple measurement reports from multiple terminals connected to the energy-saving cell within a preset historical time period. Each measurement report carries the signal strength of the energy-saving cell and other neighboring cells.

[0181] If the difference between the signal strength of a neighboring cell and the signal strength of the energy-saving cell is less than a preset threshold, then the measurement report is identified as the target measurement report for that neighboring cell.

[0182] If the ratio of the number of target measurement reports to the total number of measurement reports for a certain neighboring cell is greater than a preset value, then the neighboring cell is identified as a co-coverage cell of the energy-saving community.

[0183] The entity executing the above steps can be an energy-saving management device or a network device in the energy-saving community. If the entity is an energy-saving management device, it obtains multiple measurement reports from multiple terminals connected to the energy-saving community within a preset historical period through message interaction with the network device in the energy-saving community. If the entity is a network device in the energy-saving community, it sends the information of the same coverage community to the energy-saving management device by sending a message after determining the same coverage community.

[0184] Method 3: Determine the same coverage cell based on handover data:

[0185] Obtain handover data of energy-saving communities within a preset historical time period. If the source or target community in a certain handover data includes a neighboring community, then the handover data is determined as the target handover data of that neighboring community. If the ratio of the number of target handover data corresponding to a neighboring community to the total number of handover data of the energy-saving community is greater than a preset value, then the neighboring community is determined as a community with the same coverage of the energy-saving community.

[0186] The entity executing the above steps can be an energy-saving management device or a network device where the energy-saving community is located. If the entity executing the steps is an energy-saving management device, the energy-saving management device obtains the handover data of the energy-saving community within a preset historical period through message interaction with the network device where the energy-saving community is located. If the entity executing the steps is a network device where the energy-saving community is located, the network device where the energy-saving community is located sends the information of the same coverage community to the energy-saving management device by sending a message after determining the same coverage community.

[0187] This method can identify the co-coverage cells of the energy-saving cell, which can be used as the cells for terminals to access within the coverage area of ​​the energy-saving cell after the energy-saving cell is turned off. Based on this, the method can further determine the co-coverage cell for each terminal under the energy-saving cell to be accessed from all co-coverage cells by predicting the traffic volume of the co-coverage cells, thus ensuring the success rate of terminal migration and the service performance after migration.

[0188] S304. For each cell with the same coverage, determine the compensation weight based on one or more of the following: signal strength weight, handover relationship weight, and service load weight; determine the second service volume forecast value for the cell with the same coverage within a preset future time period based on the first service volume forecast value and the compensation weight value.

[0189] As an example, the preset future time period includes N preset periods, and the first business volume prediction value of the energy-saving community corresponding to each preset period is represented as {D1, D2, ..., D...} N}, where D iThis represents the predicted first traffic volume value corresponding to the i-th preset period within a certain preset period in the future; the number of co-covered cells corresponding to the energy-saving cell is M, and the compensation weights of each co-covered cell are {p1, p2, ..., p...} M},p j Let {D1*p} be the compensation weight of the j-th co-coverage cell; then the predicted second traffic volume of the j-th co-coverage cell within a predetermined future time period can be expressed as {D1*p}. j ,D2*p j ,......,D N *p j};

[0190] Among them, the signal strength weight is determined by the ratio of the number of measurement reports in the energy-saving cell where the signal strength of the same coverage cell is greater than the preset strength to the total number of measurement reports; the handover relationship weight is determined by the ratio of the historical handover count between the energy-saving cell and the same coverage cell to the total number of handover counts between the energy-saving cell and the neighboring cells; and the service load weight is determined by the ratio of the service load of the same coverage cell to the energy-saving cell.

[0191] Specifically, each measurement report of the energy-saving cell within a preset historical period carries the signal strength of the energy-saving cell and the cell with the same coverage. The ratio of the number of measurement reports with the signal strength value of the cell with the same coverage greater than a preset first threshold to the total number of measurement reports of the energy-saving cell within the preset historical period is determined as the signal strength weight of the cell with the same coverage.

[0192] Specifically, for energy-saving communities, each handover data entry within a preset historical time period includes the source community and the target community for each handover. The number of handover data entries in the source community or target community that include the same coverage community is determined as the first quantity, and the ratio of the first quantity to the total number of handover data entries in the energy-saving community is determined as the handover relationship weight of the same coverage community.

[0193] Specifically, the service load weight can be determined based on the service load of the same coverage cell and the energy-saving cell within a preset historical period, and is defined as the ratio of the average service load of the energy-saving cell and the same coverage cell within a preset historical period.

[0194] In this step, the second traffic volume prediction value is the traffic volume brought by terminals that migrate from the energy-saving cell to the same coverage cell after the energy-saving cell is turned off; by determining the second traffic volume prediction value, the traffic volume undertaken by the same coverage cell can be accurately predicted when the energy-saving cell is turned off.

[0195] When determining the second traffic volume forecast value for migration from energy-saving cells to co-coverage cells, a method of allocation based on compensation weights is adopted. This method distributes the traffic volume of energy-saving cells to multiple co-coverage cells according to the size of the compensation weight. The method of allocation based on compensation weights takes into account the differences between different cells in terms of signal strength, handover relationship with energy-saving cells, and traffic load. If the signal coverage similarity between a co-coverage cell and an energy-saving cell is higher, the handover between them is more frequent, or the traffic load of the co-coverage cell is lower, then the traffic volume allocated to that co-coverage cell is larger. In this way, more traffic volume from energy-saving cells can be allocated to co-coverage cells with similar signal strength distribution, frequent handover between energy-saving cells, and lower traffic load. This can improve the success rate of terminal migration, resulting in stronger signal strength and better service performance for terminals within the coverage area of ​​energy-saving cells after migration to co-coverage cells. At the same time, it can avoid problems such as cell congestion caused by allocating too much traffic volume to a high-load cell.

[0196] S305. For each co-coverage cell, determine the proportion of the second traffic volume prediction value of the co-coverage cell based on the second traffic volume prediction value of the co-coverage cell and the sum of the second traffic volume prediction values ​​of all co-coverage cells; obtain the receiving terminal capacity of the co-coverage cell based on the proportion of the second traffic volume prediction value and the number of terminals to be migrated.

[0197] Specifically, the receiving terminal capacity corresponding to each co-coverage cell, i.e. the number of terminals to be migrated, is calculated by the following formula: Number of terminals to be migrated = Sum of the second traffic volume forecast of the co-coverage cell and the second traffic volume forecast of all co-coverage cells * Total number of target terminals.

[0198] S306. For each terminal to be migrated, determine the optimal co-coverage cell corresponding to the terminal to be migrated.

[0199] Specifically, for each terminal to be migrated, the migration weight is obtained based on the number of successful handovers from the terminal to each co-coverage cell within a preset historical time period; or the measurement reports of the terminal to be migrated within a preset historical time period are obtained, the co-coverage cell with the strongest signal in each measurement report is taken as the target cell, and the number of times each co-coverage cell is taken as the target cell is obtained, and the migration weight is obtained based on the number of times.

[0200] Specifically, each co-coverage cell is sorted in descending order of migration weight to obtain the sorting result of the co-coverage cells; based on the sorting result, the co-coverage cell ranked first is the optimal co-coverage cell for the terminal to be migrated.

[0201] S307. Based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated, determine the co-coverage cell to be migrated for each terminal to be migrated.

[0202] Specifically, Figure 4 A flowchart illustrating a terminal migration method provided in this application embodiment. Figure 2 Flowchart of S307 Figure 3 ,like Figure 4 S307 includes:

[0203] S3071. When a co-coverage cell is determined to be the optimal co-coverage cell for the terminal to be migrated, the terminal to be migrated is determined to be the associated terminal of that co-coverage cell; for each co-coverage cell, the receiving terminal capacity and the number of associated terminals are compared.

[0204] Specifically, for each co-coverage cell, there are receiving terminal capacity and associated terminals. The receiving terminal capacity is the number of cells that the co-coverage cell can receive, and the associated terminals are the terminals to be migrated that regard the co-coverage cell as the optimal co-coverage cell.

[0205] The receiving terminal capacity is compared with the number of associated terminals. If the receiving terminal capacity is greater than the number of associated terminals, then after receiving all associated terminals, the co-coverage cell still has remaining capacity to receive other terminals to be migrated. If the receiving terminal capacity is less than the number of associated terminals, then there are many associated terminals in the co-coverage cell that cannot be matched with the co-coverage cell. Therefore, comparing the receiving terminal capacity and the number of associated terminals is to solve the mismatch problem between the receiving terminal capacity and the number of associated terminals, so as to ensure that each terminal to be migrated can determine its co-coverage cell to be migrated to.

[0206] S3072. If the receiving terminal capacity is not less than the number of associated terminals, then the same coverage cell is determined as the same coverage cell to be migrated for the associated terminals.

[0207] Specifically, there are two scenarios: the receiving terminal capacity equals the number of associated terminals, and the receiving terminal capacity is greater than the number of associated terminals.

[0208] If the receiving terminal capacity is equal to the number of associated terminals, then the co-coverage cell can receive all associated terminals, that is, it can determine that the co-coverage cell to be migrated for all associated terminals is the co-coverage cell; the co-coverage cell cannot be identified as the co-coverage cell of other co-coverage cells to be migrated.

[0209] When the receiving terminal capacity is greater than the number of associated terminals, the co-coverage cell still has remaining capacity to receive other terminals to be migrated after receiving all associated terminals; that is, it can determine the co-coverage cell to be migrated for all associated terminals; the co-coverage cell can be identified as the co-coverage cell of the other terminals to be migrated, and the co-coverage cell will be used in S3074 to match with other terminals to be migrated.

[0210] S3073. If the receiving terminal capacity is less than the number of associated terminals, for all associated terminals in the same coverage cell, obtain the terminal weight of each associated terminal; sort the associated terminals in descending order of terminal weight; for associated terminals whose ranking is not greater than the receiving terminal capacity, use the same coverage cell as the same coverage cell to be migrated.

[0211] Specifically, the terminal weight of each associated terminal is determined based on the number of successful handovers between each associated terminal and the same coverage cell within a preset historical period; or, the measurement reports of each associated terminal within a preset historical period are obtained, and the terminal weight of each associated terminal is determined based on the number of measurement reports of the cell with the strongest signal being the same coverage cell.

[0212] In summary, it can be determined that the higher the terminal weight, the easier it is for the associated terminal to successfully hand over to a cell with the same coverage area, or the stronger the signal of the associated cell with the same coverage area.

[0213] When the receiving terminal capacity is less than the number of associated terminals, the associated terminals are sorted in descending order of terminal weight. The associated terminal with the highest weight is selected first to be matched with the cell with which it is easier to successfully hand over or whose signal is stronger than that of the cell with which it is covered. The other associated terminals will be used in S3074 to match with other cells with the same coverage.

[0214] For example, if the number of associated terminals in a certain co-coverage cell is M and the receiving terminal capacity is N, when M>N, the terminal weights of the M associated terminals are sorted from largest to smallest, and the associated terminals corresponding to the top N terminal weights are selected to be matched with the co-coverage cell. The last MN associated terminals will be used in S3074 to match with other co-coverage cells.

[0215] S3074. For associated terminals whose ranking is greater than the receiving terminal capacity, any one of the co-coverage cells whose receiving terminal capacity is not less than the number of associated terminals shall be used as the co-coverage cell to be migrated for that associated terminal.

[0216] Specifically, in S3072, the co-coverage cells with receiving terminal capacity greater than the number of associated terminals are obtained, and in S3073, the last MN associated terminals are obtained; any one of the above co-coverage cells can be used as the associated terminal to be migrated, ensuring that each terminal to be migrated can be matched with its own co-coverage cell to be migrated.

[0217] Specifically, after determining the corresponding co-coverage cell for each terminal to be migrated, before the energy-saving cell enters the energy-saving shutdown state, the energy-saving cell is instructed to send a migration instruction message to each terminal to be migrated, which is used to instruct the terminal to be migrated to access the corresponding co-coverage cell.

[0218] The method provided in this embodiment can achieve the following technical effects:

[0219] Based on the performance data of each cell within a preset historical period, energy-saving cells are identified. Cells with high energy consumption, poor service performance, and low load are prioritized for shutdown as energy-saving cells, thereby reducing the total energy consumption of the preset area and improving service performance.

[0220] When determining the first traffic volume forecast value of an energy-saving community in the future, in order to determine the traffic volume forecast value of the same coverage community, the first traffic load forecast value of the energy-saving community in the future is first determined. Then, based on the correspondence between traffic volume and traffic load, the traffic volume forecast value corresponding to the traffic load forecast value is obtained. Since the traffic load of the community changes with time in a relatively regular manner, the traffic load forecast value obtained based on the time series forecast algorithm is closer to the true value, thereby making the traffic volume forecast based on the random forest or Xgboost model more accurate, which can improve the accuracy of traffic volume forecast of the same coverage community.

[0221] The number of terminals to be migrated for each co-coverage cell is determined based on the second traffic volume forecast value of each co-coverage cell within a preset future time. Then, based on the historical handover data or measurement reports of the terminals to be migrated, the corresponding co-coverage cell to be migrated for each terminal is determined. This prioritizes the selection of the co-coverage cell to which each terminal to be migrated should access from the target co-coverage cells. This ensures that the number of terminals to be migrated for each co-coverage cell matches the traffic load and signal coverage of that cell, avoiding problems such as cell congestion and failure to access the cell due to insufficient signal strength after migration, thus improving the success rate of terminal migration. Simultaneously, it allows terminals to be migrated to prioritize handover to co-coverage cells with the strongest signal strength or the highest number of historical successful handovers, thereby improving the success rate of migration from energy-saving cells to co-coverage cells and the service performance after migration.

[0222] When determining the predicted traffic volume for migration from energy-saving cells to co-coverage cells, a compensation weight allocation method is adopted. This method distributes the traffic volume of energy-saving cells to multiple co-coverage cells according to the compensation weight. The compensation weight allocation method takes into account the differences between different cells in terms of signal strength, handover relationship with energy-saving cells, and traffic load. It can allocate more traffic volume of energy-saving cells to co-coverage cells with similar signal strength distribution, frequent handover between energy-saving cells, and lower traffic load. This can improve the success rate of terminal migration, resulting in stronger signal strength and better service performance for terminals in the coverage area of ​​energy-saving cells after migration to co-coverage cells. At the same time, it can avoid problems such as cell congestion caused by allocating too much traffic volume to a high-load cell.

[0223] In this embodiment of the invention, electronic devices or main control devices can be divided into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional module. It should be noted that the module division in this embodiment of the invention is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0224] Figure 5 This is a schematic diagram of the structure of a terminal migration device provided in an embodiment of this application. Figure 5 As shown, the device 50 includes:

[0225] The first determining module 501 is used to determine the energy-saving community, the terminal to be migrated in the energy-saving community, and the first business volume prediction value of the energy-saving community in a preset future time within a preset area.

[0226] The second determining module 502 is used to filter out the co-coverage cells corresponding to the energy-saving cell among the cells adjacent to the energy-saving cell, and for each co-coverage cell, determine the second traffic volume prediction value of the co-coverage cell in a preset future time according to the first traffic volume prediction value and the compensation weight value of the co-coverage cell, wherein the compensation weight value is used to indicate the ability of the co-coverage cell to accept the traffic volume of the energy-saving cell.

[0227] The third determining module 503 is used to determine the receiving terminal capacity of each co-coverage cell based on the second traffic volume prediction value of each co-coverage cell.

[0228] The fourth determining module 504 is used to determine the optimal co-coverage cell corresponding to each terminal to be migrated; and to determine the co-coverage cell to be migrated for each terminal to be migrated based on the receiving terminal capacity of each co-coverage cell and the optimal co-coverage cell corresponding to each terminal to be migrated.

[0229] Furthermore, the first determining module 501 is specifically used for:

[0230] Within a preset area, cells with preset configuration data of specified values ​​are designated as energy-saving cells, and terminals in energy-saving cells are designated as terminals to be migrated; wherein, the preset configuration data includes one or more preset energy-saving attributes, preset frequency bands, and preset network standards.

[0231] Furthermore, the first determining module 501 also includes an obtaining module 505; the obtaining module 505 is specifically used for:

[0232] Obtain historical performance data for each cell within a preset area over a preset historical period. The historical performance data includes one or more of the following: average PRB resource utilization, average RRC connection count, average call completion rate, average handover success rate, average service transmission latency, average service transmission rate, and average network device energy consumption.

[0233] The first determining module 501 is further used to: determine the shutdown weight based on historical performance data; wherein the larger the average network device energy consumption and the average service transmission latency, the larger the shutdown weight; the smaller the average connection rate, the average handover success rate, the average service transmission rate, the average PRB resource utilization rate, and the average RRC connection number, the smaller the shutdown weight.

[0234] Cells with a shutdown weight value greater than a preset shutdown threshold are identified as energy-saving cells;

[0235] Terminals in energy-saving communities are designated as terminals to be migrated.

[0236] Furthermore, the first determining module 501 is specifically used to: determine the first business volume forecast value of the energy-saving community within a preset future time according to method one or method two;

[0237] Method 1: Input a preset future time into the trained first-time prediction model to obtain the traffic volume of the energy-saving community within the preset future time, and use the traffic volume of the energy-saving community within the preset future time as the first traffic volume prediction value; wherein, the first-time prediction model is a time series prediction model; or

[0238] The second method involves inputting a preset future time into a trained second-time prediction model to obtain the first business load prediction value of the energy-saving community at the preset future time, where the second-time prediction model is a time series prediction model. The first business load prediction value is then input into a trained third-time prediction model to obtain the business volume of the energy-saving community at the preset future time, where the business volume of the energy-saving community at the preset future time is used as the first business volume prediction value. The third-time prediction model is either a random forest or an XGBoost model.

[0239] Furthermore, the first determining module 501 is specifically used for:

[0240] The first prediction error of the first-time prediction model was determined using the first sample validation data.

[0241] The second prediction error of the second time prediction model was determined using the second sample validation data.

[0242] If the first prediction error is less than the second prediction error, the first business volume prediction value is determined by the first method; if the first prediction error is not less than the second prediction error, the first business volume prediction value is determined by the second method.

[0243] Furthermore, the second determining module 502 is specifically used for:

[0244] For each cell with the same coverage, the compensation weight is determined based on one or more of the following: signal strength weight, handover relationship weight, and service load weight.

[0245] Based on the first traffic volume forecast and the compensation weight, determine the second traffic volume forecast for the same covered cell within a preset future time period;

[0246] The signal strength weight is determined by the ratio of the number of measurement reports in which the signal strength of the terminal to be migrated in the same coverage cell is greater than the preset strength to the total number of measurement reports.

[0247] The handover relationship weight is determined based on the ratio of the number of handovers between the energy-saving cell and the cell with the same coverage to the total number of handovers between the energy-saving cell and its neighboring cells;

[0248] The service load weight is determined based on the ratio of the service load of the same coverage cell to that of the energy-saving cell.

[0249] Furthermore, the third determining module 503 is specifically used for:

[0250] For each cell with the same coverage, the proportion of the second traffic volume forecast value of the cell with the same coverage is determined based on the second traffic volume forecast value of the cell with the same coverage and the sum of the second traffic volume forecast values ​​of all cells with the same coverage.

[0251] The receiving terminal capacity of the same coverage cell is obtained by using the proportion of the second traffic volume forecast and the number of terminals to be migrated.

[0252] Furthermore, the fourth determining module 504 is specifically used for:

[0253] For each terminal to be migrated, the migration weight of each co-coverage cell is determined based on the number of successful handovers to each co-coverage cell within a preset historical time period; or

[0254] Obtain measurement reports of the terminal to be migrated within a preset historical time period, take the cell with the strongest signal in each measurement report as the target cell, and determine the migration weight of each cell with the same coverage based on the number of times each cell with the same coverage is used as the target cell.

[0255] Based on the migration weight of each co-coverage cell, the optimal co-coverage cell corresponding to each terminal to be migrated is determined.

[0256] Furthermore, the fourth determining module 504 is specifically used for:

[0257] Sort each cell with the same coverage according to the migration weight from largest to smallest to obtain the sorting result of the cells with the same coverage.

[0258] Based on the ranking results, the cell with the highest ranking and corresponding coverage is determined as the optimal cell with corresponding coverage for the terminal to be migrated.

[0259] Furthermore, the fourth determining module 504 is specifically used for:

[0260] When a cell with the same coverage is determined to be the optimal cell with the same coverage for the terminal to be migrated, the terminal to be migrated is determined to be the associated terminal of that cell with the same coverage.

[0261] For each cell with the same coverage, compare the receiving terminal capacity and the number of associated terminals;

[0262] If the receiving terminal capacity is not less than the number of associated terminals, then the co-coverage cell is determined as the co-coverage cell to be migrated for the associated terminals.

[0263] Furthermore, the fourth determining module 504 is specifically used for:

[0264] For all associated terminals in the same coverage cell, the terminal weight of each associated terminal is determined based on the number of successful handovers between each associated terminal and the same coverage cell within a preset historical period; or, the measurement reports of each associated terminal within a preset historical period are obtained, and the terminal weight of each associated terminal is determined based on the number of measurement reports of the cell with the strongest signal in the same coverage cell.

[0265] The associated terminals are sorted in descending order of their terminal weights;

[0266] For associated terminals whose ranking is no greater than the receiving terminal capacity, the same coverage cell will be used as the same coverage cell to be migrated for the associated terminal.

[0267] For associated terminals whose ranking is greater than their receiving terminal capacity, any one of the co-coverage cells with a receiving terminal capacity not less than the number of associated terminals will be selected as the co-coverage cell to be migrated for that associated terminal.

[0268] Furthermore, it also includes a sending module 506, which is specifically used for:

[0269] After determining the corresponding co-coverage cell for each terminal to be migrated, before the energy-saving cell enters the energy-saving shutdown state, the energy-saving cell is instructed to send a migration instruction message to each terminal to be migrated, which is used to instruct the terminal to be migrated to access the corresponding co-coverage cell.

[0270] The terminal migration device provided in this embodiment can execute a terminal migration method of the above embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0271] In a specific implementation of the aforementioned terminal migration device, each module can be implemented as a processor. The processor can execute computer execution instructions stored in the memory, thereby enabling the processor to perform the aforementioned terminal migration method.

[0272] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 60 includes at least one processor 601 and a memory 602. The electronic device 60 also includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0273] In the specific implementation process, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to execute a terminal migration method as described above on the electronic device side.

[0274] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0275] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0276] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage.

[0277] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0278] The above description of the functions implemented by electronic devices and main control devices has introduced the solutions provided by the embodiments of the present invention. It is understood that, in order to implement the above functions, the electronic device or main control device includes hardware structures and / or software modules corresponding to the execution of each function. By combining the units and algorithm steps of the various examples described in the embodiments of the present invention, the embodiments of the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present invention.

[0279] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the terminal migration method described above.

[0280] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0281] One example is a readable storage medium coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in an electronic device or a host device.

[0282] This application also provides a computer program product, comprising: a computer program stored in a readable storage medium, wherein at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the scheme provided in any of the above embodiments.

[0283] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0284] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A terminal migration method, characterized by, The method comprises: determining an energy-saving cell, a terminal to be migrated in the energy-saving cell, and a first traffic volume prediction value of the energy-saving cell in a preset future time in a preset area; in a cell adjacent to the energy-saving cell, a same-coverage cell corresponding to the energy-saving cell is screened out, for each same-coverage cell, a second traffic volume prediction value of the same-coverage cell in a preset future time is determined according to the first traffic volume prediction value and a compensation weight value of the same-coverage cell, wherein the compensation weight value is used to indicate the capability of the same-coverage cell to accommodate the traffic volume of the energy-saving cell; according to the second traffic volume prediction value of each same-coverage cell, a receiving terminal capacity of each same-coverage cell is determined; for each terminal to be migrated, an optimal same-coverage cell corresponding to the terminal to be migrated is determined, and a to-be-migrated same-coverage cell corresponding to each terminal to be migrated is determined according to the receiving terminal capacity of each same-coverage cell and the optimal same-coverage cell corresponding to each terminal to be migrated; the step of, for each same-coverage cell, determining a second traffic volume prediction value of the same-coverage cell in a preset future time according to the first traffic volume prediction value and a compensation weight value of the same-coverage cell, comprises: for each same-coverage cell, the compensation weight value is determined according to a combination of a signal strength weight value, a handover relationship weight value and a traffic load weight value; a second traffic volume prediction value of the same-coverage cell in a preset future time is determined according to the first traffic volume prediction value and the compensation weight value; wherein the signal strength weight value is determined according to a ratio of a number of measurement reports in which the signal strength measured by the terminal to be migrated to the same-coverage cell is greater than a preset strength to a total number of measurement reports; the handover relationship weight value is determined according to a ratio of a number of handovers between the energy-saving cell and the same-coverage cell to a total number of handovers between the energy-saving cell and adjacent cells; the traffic load weight value is determined according to a ratio of a traffic load of the same-coverage cell to a traffic load of the energy-saving cell; the step of, for each terminal to be migrated, determining an optimal same-coverage cell corresponding to the terminal to be migrated, comprises: for each terminal to be migrated, a migration weight value of each same-coverage cell is determined according to a number of successful handovers of the terminal to be migrated to each same-coverage cell in a preset historical time; or measurement reports of the terminal to be migrated in a preset historical time are obtained, a cell with the strongest signal in each measurement report is taken as a target cell, and a migration weight value of each same-coverage cell is determined according to a number of times that each same-coverage cell is taken as a target cell; an optimal same-coverage cell corresponding to each terminal to be migrated is determined according to the migration weight value of each same-coverage cell; the step of, for each terminal to be migrated, determining an optimal same-coverage cell corresponding to the terminal to be migrated according to the migration weight value of each same-coverage cell, comprises: each same-coverage cell is sorted in descending order of the migration weight value to obtain a sorting result of the same-coverage cells; According to the sorting result, the same-coverage cell ranked first is determined as the optimal same-coverage cell corresponding to the terminal to be migrated.

2. The method of claim 1, wherein, In the method according to claim 1, the method further comprises: In the preset area, a cell with preset configuration data being a specified value is determined as the energy-saving cell, and a terminal in the energy-saving cell is determined as the terminal to be migrated; wherein the preset configuration data comprises one or more of preset energy-saving attributes, preset frequency bands and preset network standards.

3. The method of claim 1, wherein, The method further comprises: obtaining historical performance data of each cell in the preset area at a preset historical time, wherein the historical performance data comprises one or more of PRB resource utilization average, RRC connection number average, connection rate average, handover success rate average, service transmission delay average, service transmission rate average and network device energy consumption average; determining a shutdown weight value according to the historical performance data; wherein the greater the network device energy consumption average and service transmission delay average, the greater the shutdown weight value; the smaller the connection rate average, handover success rate average, service transmission rate average, PRB resource utilization average and RRC connection number average, the smaller the shutdown weight value; determining a cell with a shutdown weight value greater than a preset shutdown threshold as the energy-saving cell; determining a terminal in the energy-saving cell as the terminal to be migrated.

4. The method of claim 1, wherein, The method further comprises: a first mode: inputting the preset future time into a trained first time prediction model to obtain service volume of the energy-saving cell at the preset future time output by the first time prediction model, and taking the service volume of the energy-saving cell at the preset future time as the first service volume prediction value; wherein the first time prediction model is a time series prediction model; or a second mode: inputting the preset future time into a trained second time prediction model to obtain a first service load prediction value of the energy-saving cell at the preset future time output by the second time prediction model; wherein the second time prediction model is a time series prediction model; inputting the first service load prediction value into a trained third prediction model to obtain service volume of the energy-saving cell at the preset future time output by the third prediction model, and taking the service volume of the energy-saving cell at the preset future time as the first service volume prediction value; wherein the third prediction model is a random forest or Xgboost model.

5. The method of claim 4, wherein, The method further comprises: determining a first prediction error of the first time prediction model by first sample verification data; determining a second prediction error of the second time prediction model by second sample verification data; if the first prediction error is smaller than the second prediction error, determining the first service volume prediction value by the first mode; if the first prediction error is not smaller than the second prediction error, determining the first service volume prediction value by the second mode.

6. The method of claim 1, wherein, The method further comprises: For each of the same coverage cell, according to the second traffic volume prediction value of the same coverage cell and the sum of all second traffic volume prediction values of the same coverage cell, the proportion of the second traffic volume prediction value of the same coverage cell is determined. According to the proportion of the second traffic volume prediction value and the number of the terminal to be migrated, the receiving terminal capacity of the same coverage cell is obtained.

7. The method of claim 1, wherein, The method further comprises: When the same coverage cell is determined as the optimal same coverage cell of the terminal to be migrated, the terminal to be migrated is determined as the associated terminal of the same coverage cell. For each of the same coverage cell, the number of associated terminals and the receiving terminal capacity are compared. If the receiving terminal capacity is not less than the number of associated terminals, the same coverage cell is determined as the same coverage cell to be migrated of the associated terminal.

8. The method of claim 7, wherein, If the receiving terminal capacity is less than the number of associated terminals, the method further comprises: For all associated terminals of the same coverage cell, according to the number of successful handovers between each of the associated terminals and the same coverage cell within a preset historical time, the terminal weight value of each of the associated terminals is determined; or, the measurement report of each of the associated terminals within a preset historical time is obtained, and according to the number of measurement reports in which the cell with the strongest signal is the same coverage cell, the terminal weight value of each of the associated terminals is determined. The associated terminals are sorted in descending order of terminal weight value. For the associated terminal with a ranking not greater than the receiving terminal capacity, the same coverage cell is taken as the same coverage cell to be migrated of the associated terminal. For the associated terminal with a ranking greater than the receiving terminal capacity, any one of the same coverage cells in which the receiving terminal capacity is not less than the number of associated terminals is taken as the same coverage cell to be migrated of the associated terminal.

9. The method according to any one of claims 1 to 8, characterized in that, After determining the same coverage cell to be migrated corresponding to each of the terminals to be migrated, the method further comprises: Before the energy-saving cell enters the energy-saving off state, the energy-saving cell sends a migration indication message to each of the terminals to be migrated, for indicating the terminal to be migrated to access the corresponding same coverage cell to be migrated.

10. A terminal migration apparatus, characterized by comprising: The method further comprises: A first determination module is configured to determine an energy-saving cell, a terminal to be migrated in the energy-saving cell, and a first traffic volume prediction value of the energy-saving cell in a preset future time in a preset area; A second determination module is configured to select a same coverage cell corresponding to the energy-saving cell from cells adjacent to the energy-saving cell, and determine a second traffic volume prediction value of the same coverage cell in a preset future time according to the first traffic volume prediction value and a compensation weight value of the same coverage cell for each of the same coverage cells, wherein the compensation weight value is used to indicate the ability of the same coverage cell to accommodate the traffic volume of the energy-saving cell. a third determining module, configured to determine a receiving terminal capacity of each of the same-coverage cells according to a second traffic volume prediction value of each of the same-coverage cells; a fourth determining module, configured to determine, for each of the to-be-migrated terminals, an optimal same-coverage cell corresponding to the to-be-migrated terminal, and determine a to-be-migrated same-coverage cell corresponding to each of the to-be-migrated terminals according to the receiving terminal capacity of each of the same-coverage cells and the optimal same-coverage cell corresponding to each of the to-be-migrated terminals; the second determining module is further configured to: determine, for each of the same-coverage cells, the compensation weight according to a combination of a signal strength weight, a handover relationship weight and a traffic load weight; determine a second traffic volume prediction value of the same-coverage cell within a preset future time according to the first traffic volume prediction value and the compensation weight; wherein the signal strength weight is determined according to a ratio of a number of measurement reports in which the to-be-migrated terminal measures a signal strength of the same-coverage cell to be greater than a preset strength to a total number of measurement reports; the handover relationship weight is determined according to a ratio of a number of times of handover between the energy-saving cell and the same-coverage cell to a total number of times of handover between the energy-saving cell and neighboring cells; the traffic load weight is determined according to a ratio of a traffic load of the same-coverage cell to a traffic load of the energy-saving cell; the fourth determining module is further configured to: determine, for each of the to-be-migrated terminals, a migration weight of each of the same-coverage cells according to a number of successful handovers of the to-be-migrated terminal to each of the same-coverage cells within a preset historical time; or obtain measurement reports of the to-be-migrated terminal within a preset historical time, take a cell with the strongest signal in each of the measurement reports as a target cell, and determine a migration weight of each of the same-coverage cells according to a number of times of taking each of the same-coverage cells as the target cell; determine the optimal same-coverage cell corresponding to each of the to-be-migrated terminals according to the migration weight of each of the same-coverage cells; the fourth determining module is further configured to: sort each of the same-coverage cells according to the migration weight from large to small to obtain a sorting result of the same-coverage cells; determine the same-coverage cell with the first sorting result as the optimal same-coverage cell corresponding to the to-be-migrated terminal according to the sorting result.

11. The apparatus of claim 10, wherein, the first determining module is further configured to: within the preset area, determine a cell with preset configuration data as a specified value as the energy-saving cell, and determine a terminal in the energy-saving cell as the to-be-migrated terminal; wherein the preset configuration data includes one or more of a preset energy-saving attribute, a preset frequency band and a preset network standard.

12. The apparatus of claim 10, wherein, the first determining module further includes an obtaining module; the obtaining module is configured to obtain historical performance data of each cell in a preset historical time within the preset area, and the historical performance data includes one or more of a PRB resource utilization rate average, an RRC connection number average, a connection rate average, a handover success rate average, a service transmission delay average, a service transmission rate average and a network device energy consumption average. The first determining module is further configured to determine a shutdown weight value according to the historical performance data, wherein the shutdown weight value is greater when the energy consumption average value and the service transmission delay average value of the network device are greater, and the shutdown weight value is smaller when the turn-on rate average value, the handover success rate average value, the service transmission rate average value, the PRB resource utilization rate average value, and the RRC connection number average value are smaller. The cell with the shutdown weight value greater than a preset shutdown threshold value is determined as the energy-saving cell. The terminal in the energy-saving cell is determined as the terminal to be migrated.

13. The apparatus of claim 10, wherein, The first determining module is further configured to determine a first service volume prediction value of the energy-saving cell in a preset future time according to the first mode or the second mode. In a first mode, the preset future time is input into a trained first time prediction model to obtain a service volume of the energy-saving cell in the preset future time output by the first time prediction model, and the service volume of the energy-saving cell in the preset future time is taken as the first service volume prediction value. The first time prediction model is a time series prediction model. In a second mode, the preset future time is input into a trained second time prediction model to obtain a first service load prediction value of the energy-saving cell in the preset future time output by the second time prediction model. The second time prediction model is a time series prediction model. The first service load prediction value is input into a trained third prediction model to obtain a service volume of the energy-saving cell in the preset future time output by the third prediction model, and the service volume of the energy-saving cell in the preset future time is taken as the first service volume prediction value. The third prediction model is a random forest or Xgboost model. The first determining module is further configured to:

14. The apparatus of claim 13, wherein, determine a first prediction error of the first time prediction model through first sample verification data; determine a second prediction error of the second time prediction model through second sample verification data; if the first prediction error is smaller than the second prediction error, determine the first service volume prediction value through the first mode, and if the first prediction error is not smaller than the second prediction error, determine the first service volume prediction value through the second mode. The third determining module is further configured to:

15. The apparatus of claim 10, wherein, for each of the same coverage cells, determine a second service volume prediction value proportion of the same coverage cell according to the second service volume prediction value of the same coverage cell and a sum of second service volume prediction values of all the same coverage cells; obtain a receiving terminal capacity of the same coverage cell according to the second service volume prediction value proportion and the number of the terminals to be migrated. The fourth determining module is further configured to:

16. The apparatus of claim 10, wherein, when the same coverage cell is determined as the optimal same coverage cell of the terminals to be migrated, determine the terminals to be migrated as associated terminals of the same coverage cell; for each of the same coverage cells, compare the receiving terminal capacity and the number of the associated terminals; if the receiving terminal capacity is not smaller than the number of the associated terminals, determine the same coverage cell as a same coverage cell to be migrated of the associated terminals. The fourth determining module is further configured to:

17. The apparatus of claim 16, wherein, ​ determining a terminal weight of each of the associated terminals according to a preset historical time number of successful handovers between each of the associated terminals and the same coverage cell; or, obtaining a measurement report of each of the associated terminals in a preset historical time, and determining a terminal weight of each of the associated terminals according to a number of measurement reports of the same coverage cell with the strongest signal; ranking the associated terminals according to the terminal weights from large to small; for the associated terminal with a ranking greater than the receiving terminal capacity, taking the same coverage cell as a to-be-migrated same coverage cell of the associated terminal; for the associated terminal with a receiving terminal capacity not less than the number of associated terminals, taking any one of the same coverage cells with a receiving terminal capacity not less than the number of associated terminals as a to-be-migrated same coverage cell of the associated terminal.

18. The apparatus of any one of claims 10-17, wherein, Further comprising a sending module configured to: after determining the to-be-migrated same coverage cell corresponding to each of the to-be-migrated terminals, before the energy-saving cell enters an energy-saving off state, instructing the energy-saving cell to send a migration instruction message to each of the to-be-migrated terminals, so as to instruct the to-be-migrated terminals to access the corresponding to-be-migrated same coverage cell.

19. An electronic device, comprising: comprising: a processor, and a memory connected to the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method of any one of claims 1 to 9.

20. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1 to 9.

Images