WO2024066801A1

WO2024066801A1 - Communication network load adjustment method, electronic device, and storage medium

Info

Publication number: WO2024066801A1
Application number: PCT/CN2023/114037
Authority: WO
Inventors: 裴帆
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-09-28
Filing date: 2023-08-21
Publication date: 2024-04-04
Also published as: CN117835249A

Abstract

The present application provides a communication network load adjustment method, an electronic device, and a storage medium. The method comprises: acquiring a neighbor cell relationship and cell resource information of a plurality of communication cells, and determining cell centroids of the communication cells (S110); performing region division on the communication cells according to the neighbor cell relationship and the cell resource information, and determining a hotspot balance region, wherein the hotspot balance region comprises a plurality of target communication cells (S120); acquiring distance information of terminals in the target communication cells, wherein the distance information is used for representing distances between the terminals and the cell centroids (S130); and according to the distance information, the neighbor cell relationship, and the cell resource information, determining edge adjustment information of the target communication cells on the basis of a preset machine learning algorithm, so as to adjust the coverage area of the target communication cells (S140).

Description

Communication network load adjustment method, electronic device and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is based on the Chinese patent application with application number 202211189531.0 and application date September 28, 2022, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference.

Technical Field

The present application relates to but is not limited to the field of communication technology, and in particular to a communication network load adjustment method, electronic device and storage medium.

Background technique

With the development of mobile communications, there is sometimes a gap between the design capacity of some sites in the wireless communication network and the actual business volume, which affects the user experience. If the redundant design capacity is increased, the operator's cost will increase. Therefore, dynamically coordinating the cell coverage can save costs and alleviate sudden high business volume, improving the user experience.

At present, for the communication cells whose loads are to be coordinated, only the neighboring cells closest to the communication cells are selected for load adjustment, and other neighboring cells with more user interactions with the communication cells are ignored. The load adjustment effect of the communication cells is poor. In addition, for the areas formed by multiple communication cells, load adjustment can only be performed for each communication cell one by one, resulting in poor overall load adjustment effect of the area and poor user experience.

Summary of the invention

The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

Embodiments of the present application provide a communication network load adjustment method, an electronic device, and a storage medium.

In a first aspect, an embodiment of the present application provides a communication network load adjustment method, comprising: obtaining neighboring cell relationships and cell resource information of multiple communication cells, and determining the cell centroid of each of the communication cells, wherein the cell resource information is determined by a terminal located in the communication cell; dividing each of the communication cells into regions according to the neighboring cell relationships and the cell resource information, and determining a hotspot balancing region, wherein the hotspot balancing region includes multiple target communication cells; obtaining distance information of the terminal located in each of the target communication cells, wherein the distance information is used to characterize the distance between the terminal and the centroid of each of the cells; determining edge adjustment information of each of the target communication cells based on a preset machine learning algorithm according to the distance information, the neighboring cell relationships and the cell resource information, so as to adjust the coverage range of the target communication cells.

In a second aspect, the present application further provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor runs the computer program, the communication network load adjustment method as described in the first aspect above is executed.

In a third aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the communication network load adjustment method as described in the first aspect above.

Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the description, claims and drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

FIG1 is a flow chart of a communication network load adjustment method provided by an embodiment of the present application;

FIG2 is a flow chart of a method for determining a hotspot balancing area provided by another embodiment of the present application;

FIG3 is a flow chart of a method for determining a core cell provided by another embodiment of the present application;

FIG4 is a flow chart of a method for determining a load sharing cell provided in another embodiment of the present application;

FIG5 is a flow chart of a method for determining edge adjustment information provided by another embodiment of the present application;

FIG6 is a flow chart of another method for determining edge adjustment information provided by another embodiment of the present application;

7 is a flowchart of a specific method for determining edge adjustment information provided by another embodiment of the present application;

FIG8 is a flowchart of a method for determining neighbor relationship and distance information provided by another embodiment of the present application;

FIG9 is a flow chart of a method for determining capacity proportion and capacity gap provided by another embodiment of the present application;

FIG10 is a schematic diagram of a hot spot balancing area provided by an embodiment of the present application;

FIG11 is a schematic diagram of a communication cell coverage area provided by an embodiment of the present application;

FIG. 12 is a structural diagram of an electronic device provided in another embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims or the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

In response to the problem that the load adjustment effect of communication cells is poor and the load adjustment effect of the entire region is poor, the present application provides a communication network load adjustment method, electronic device and storage medium, the communication network load adjustment method includes: obtaining neighboring cell relations and cell resource information of multiple communication cells, and determining the cell centroid of each communication cell, wherein the cell resource information is determined by a terminal located in the communication cell; dividing each communication cell into regions according to the neighboring cell relations and cell resource information, and determining a hotspot balancing region, wherein the hotspot balancing region includes multiple target communication cells; obtaining distance information of terminals located in each target communication cell, wherein the distance information is used to characterize the distance between the terminal and the centroid of each cell; determining each target communication cell according to the distance information, neighboring cell relations and cell resource information based on a preset machine learning algorithm. The edge adjustment information is used to adjust the coverage of the target communication cell. According to the solution provided in the embodiment of the present application, through regional division, multiple target communication cells are divided into hot spot balancing areas according to the neighboring cell relationships and cell resource information of the communication cells. The hot spot balancing area refers to the area where load adjustment is required, and then through a machine learning algorithm, the distance between the terminal and the centroid of each cell, as well as the neighboring cell relationship and cell resource information of the target communication cell are used to determine the edge adjustment information of each target communication cell in the hot spot balancing area, and then adjust the coverage of the target communication cell, thereby realizing dynamic adjustment of the edge of the target communication cell and load adjustment of adjacent target communication cells, effectively improving the load adjustment effect of the communication cell. In addition, the load of each target communication cell in the hot spot balancing area can be dynamically balanced, and the entire hot spot balancing area can be used as a load adjustment unit, which makes it easier to achieve global optimality and improve the overall load adjustment effect of the region, thereby improving user experience.

The embodiments of the present application are described below in conjunction with the accompanying drawings.

A communication network load adjustment method provided in an embodiment of the present application can be applied in a terminal or a server, and can also be software running in a terminal or a server.

As shown in Figure 1, Figure 1 is a flow chart of a communication network load adjustment method provided by an embodiment of the present application. The communication network load adjustment method includes but is not limited to the following steps:

Step S110, obtaining neighboring cell relations and cell resource information of multiple communication cells, and determining the cell centroid of each communication cell, wherein the cell resource information is determined by a terminal located in the communication cell;

Step S120, dividing each communication cell into regions according to the neighboring cell relationship and the cell resource information, and determining a hot spot balancing region, wherein the hot spot balancing region includes a plurality of target communication cells;

Step S130, obtaining distance information of the terminal located in each target communication cell, wherein the distance information is used to represent the distance between the terminal and the centroid of each cell;

Step S140, according to the distance information, neighboring cell relationship and cell resource information, based on a preset machine learning algorithm, edge adjustment information of each target communication cell is determined to adjust the coverage of the target communication cell.

It is understandable that a wireless communication subnet may include multiple communication cells, each of which may be connected to a number of terminals. A terminal accessing a communication cell is equivalent to a terminal being located in the communication cell. The cell resource information of the communication cell is associated with the terminal located in the communication cell. The cell resource information may refer to the capacity share and the capacity gap. In some embodiments, the more terminals located in the communication cell, the fewer available resources in the communication cell, the higher the capacity share in the communication cell, the higher the load of the communication cell, and when the number of terminals exceeds the terminal capacity of the cell, a capacity gap will also appear. Conversely, the fewer terminals located in the communication cell, the more available resources in the communication cell, the lower the capacity share in the communication cell, and the lower the load of the communication cell; neighboring cell relations are used to determine the neighboring cells of a communication cell. For example, if communication cell A is a neighboring cell of communication cell B, the neighboring cell relationship between communication cell A and communication cell B is adjacent. If communication cell A is not a neighboring cell of communication cell B, the neighboring cell relationship between communication cell A and communication cell B is non-adjacent. Using neighboring cell relations and cell resource information, a hotspot balancing area is divided, and the hotspot balancing area includes target communication cells with higher loads and lower loads. The communication cell can be set as the cell centroid, and the distance between the terminal and the centroid of each cell can be obtained; then, through the machine learning algorithm, the edge adjustment information of each target communication cell can be determined through the distance between the terminal and the centroid of each cell, as well as the cell resource information of each target communication cell, and then the coverage of the target communication cell can be adjusted according to the edge adjustment information, and the edge of the target communication cell with a higher load can be shrunk, and correspondingly, the edge of the target communication cell with a lower load can be expanded. At this time, the terminal located at the edge of the target communication cell with a higher load will switch to the target communication cell with a lower load, the number of terminals located in the target communication cell with a higher load will decrease, and the number of terminals located in the target communication cell with a lower load will increase, thus achieving load balancing of each target communication cell in the hotspot balancing area, without increasing redundant design capacity, and reducing operator costs; based on this, through the area Domain division, according to the neighboring cell relationship and cell resource information of the communication cell, multiple target communication cells are divided into hot spot balancing areas. The hot spot balancing area refers to the area where load adjustment is required. Then, through the machine learning algorithm, the distance between the terminal and the centroid of each cell, as well as the neighboring cell relationship and cell resource information of the target communication cell are used to determine the edge adjustment information of each target communication cell in the hot spot balancing area, and then adjust the coverage range of the target communication cell, so as to realize dynamic adjustment of the edge of the target communication cell and load adjustment of the adjacent target communication cells, effectively improving the load adjustment effect of the communication cell. In addition, it can dynamically balance the load of each target communication cell in the hot spot balancing area, and use the entire hot spot balancing area as the load adjustment unit, which makes it easier to achieve global optimization and improve the overall load adjustment effect of the region, thereby improving user experience.

It should be noted that there is no need to determine the coverage range of the communication cell. It is only necessary to determine the edge adjustment information of the communication cell through a machine learning algorithm. The amount of data processing is less and the adjustment efficiency can be improved. The edge adjustment information refers to the edge change of the communication cell. For example, the edge change is 10db or -10db; if the edge change is a positive value, it means that the edge of the communication cell needs to be expanded. If the edge change is a negative value, it means that the edge of the communication cell needs to be shrunk.

It should be noted that the coverage of the communication cell is adjusted through the cell edge management module. After receiving the edge adjustment information, the cell edge management module adjusts the coverage of the corresponding target communication cell. The adjustment methods of the target communication cell by the cell edge management module include but are not limited to: adjusting the switching threshold, adjusting the antenna direction angle, adjusting the line power, adjusting the PRACH detection threshold, adjusting the access level threshold, adjusting the uplink maximum transmission power, and adjusting the reselection parameters; in addition, based on expert experience, it is possible to judge whether the current coverage is reasonable cell by cell, and manually adjust the coverage of the target communication cell through the cell edge management module.

It is worth noting that there are at least two ways to adjust the coverage of the target communication cell. The first adjustment method is to modify the switching parameters or other parameters so that the terminals accessing other communication cells switch to this cell in advance or delay, thereby indirectly achieving the result of changing the coverage of the communication cell, but the actual coverage of the communication cell remains unchanged; the second adjustment method is to adjust the communication cell coverage parameters to change the actual coverage of the communication cell.

It is worth noting that the capacity share and capacity gap can be determined by the number of RRC connected users; the distance between the terminal and the centroid of each cell can be determined by data such as path loss distribution and terminal positioning data; and the time delay between the terminal and the communication cell can be used to replace the distance between the terminal and the cell centroid.

It is worth noting that if a mass emergency incident or fire incident occurs, the dispatching and processing of fire trucks or ambulances will also face capacity and distance issues for the decision-making center. The machine learning algorithm in the communication network load adjustment method provided in the embodiment of the present application can be used to complete the dispatching and processing of fire trucks or ambulances.

In addition, referring to FIG. 2 , in one embodiment, the cell resource information includes capacity proportion; step S120 in the embodiment shown in FIG. 1 includes but is not limited to the following steps:

Step S210, determining the load attribute of the communication cell according to the capacity proportion;

Step S220, dividing each communication cell into regions according to the neighboring cell relationship and load attributes, and determining the hot spot balancing region.

It can be understood that the capacity share of a communication cell is determined by the number of terminals located in the communication cell. The capacity share refers to the utilization rate of the resource capacity of the communication cell. The larger the capacity share, the higher the load of the communication cell. Conversely, the smaller the capacity share, the lower the load of the communication cell. Therefore, the load attributes of the communication cell can be determined by the capacity share, and then the hot spot balancing area can be divided in each communication cell in combination with the neighboring cell relationship and load attributes.

In addition, referring to FIG. 3 , in one embodiment, the hotspot balancing area in step S220 in the embodiment shown in FIG. 2 includes a core cell; the method for determining the core cell includes but is not limited to the following steps:

Step S310, when the capacity ratio is greater than a preset first threshold, determining that the load attribute of the communication cell is a high-load cell;

Step S320: Based on the neighboring cell relationship, any high-load cell is used as a core cell, and all high-load cells adjacent to the core cell are used as core cells.

It can be understood that by setting the first threshold, the capacity share of the communication cell is judged, and then the high-load cell is distinguished. When a hot spot balancing area needs to be determined, starting from any high-load cell, the high-load cell is taken as the core cell, and combined with the neighboring cell relationship, all high-load cells that have a neighboring cell relationship with the core cell are taken as core cells.

In addition, referring to FIG. 4 , in one embodiment, the hotspot balancing area in step S220 in the embodiment shown in FIG. 2 also includes a load sharing cell; the method for determining the load sharing cell includes but is not limited to the following steps:

Step S410, when the capacity proportion is less than or equal to a preset second threshold, determining that the load attribute of the communication cell is a medium-low load cell, wherein the second threshold is less than or equal to the first threshold;

Step S420: Based on the neighboring cell relationship, traverse each medium and low load cell, and use all medium and low load cells adjacent to the core cell as load sharing cells.

It can be understood that by setting the second threshold, the capacity share of the communication cell is judged, and then the medium and low load cells are distinguished. When a hot spot balancing area needs to be determined, after the core cell is determined, all the medium and low load cells adjacent to each core cell are used as load sharing cells in combination with the neighboring cell relationship. Finally, all the core cells and load sharing cells are regarded as a whole area, namely, the hot spot balancing area. In the hot spot balancing area, since the load of the core cell is too high, it will affect the user experience. It is necessary to adjust the load of the core cell, and connect some terminals located in the core cell to the adjacent load sharing cell to reduce the load of the core cell, thereby ensuring the user experience.

It is worth noting that using the hotspot balancing area as the load adjustment unit makes it easier to achieve global optimality, improve the overall load adjustment effect of the region, and thus improve user experience.

It should be noted that the second threshold value can be set manually or obtained through repeated experiments and tuning; the first threshold value and the second threshold value can be the same or different.

In addition, referring to FIG5, in one embodiment, the hotspot balancing area includes a core cell and a load sharing cell, and the cell resource information includes a capacity ratio and a capacity gap; step S140 in the embodiment shown in FIG1 includes but is not limited to the following steps:

Step S510, traversing the core cells based on the sorting information of capacity proportion and capacity gap;

Step S520: for any core cell, a terminal located in the core cell is taken as a terminal to be processed, and based on a neighboring cell relationship, a load sharing cell adjacent to the core cell is taken as a cell to be processed;

Step S530, input the distance information of the terminal to be processed, the neighboring cell relationship, the capacity proportion of the core cell, the capacity proportion of the cell to be processed and the capacity gap of the core cell into the machine learning algorithm to determine the edge adjustment information of each target communication cell.

It can be understood that in the processing of the machine learning algorithm, the core cells are traversed according to the capacity proportion and the size of the capacity gap, each core cell is processed in turn, and the capacity gap of each core cell is judged. If there are core cells with capacity gaps among the core cells to be processed, the core cells with larger capacity gaps are given priority. If the capacity gaps in the core cells to be processed are all zero, the core cells with larger capacity proportions are given priority. This can dynamically balance the load of each target communication cell in the hotspot balancing area to achieve global optimization, thereby improving user experience.

It is worth noting that the ranking information based on capacity share and capacity gap refers to the ranking information based on capacity share and capacity gap from high to low.

In addition, referring to FIG. 6 , in one embodiment, the cell resource information includes capacity proportion and capacity gap, and the machine learning algorithm includes a classification model or a clustering model; step S140 in the embodiment shown in FIG. 1 includes but is not limited to the following steps:

Step S610, obtaining an initial belonging tag of each terminal, wherein the initial belonging tag is used to represent a target communication cell corresponding to the terminal;

Step S620, inputting the distance information, neighboring cell relationship, capacity proportion and capacity gap into a classification model or a clustering model to determine a target attribution label of each terminal, wherein the target attribution label is used to characterize a target communication cell corresponding to the terminal;

Step S630, determining edge adjustment information of each target communication cell according to the distance information, the initial belonging label, the target belonging label and the neighboring cell relationship.

It can be understood that the initial attribution label of the terminal is first obtained, and the initial attribution label is used to characterize the target communication cell currently accessed by the terminal; then, based on the processing of the classification model or the clustering model, the target attribution label of each terminal is determined through the distance information, the neighboring area relationship, the capacity proportion of each communication cell and the capacity gap of each core cell, and the target attribution label is used to characterize the target communication cell that the terminal should access; through the initial attribution label and distance information of each terminal, as well as the neighboring area relationship of the target communication cell, the initial edge information of each target communication cell can be determined, and through the target attribution label and distance information of each terminal, as well as the neighboring area relationship of the target communication cell, the target edge information of each target communication cell can be determined, and the edge adjustment information of the target communication cell can be determined through the initial edge information and the target edge information, and then the edge adjustment information adjusts the coverage of each target communication cell, so that the terminal can access the target communication cell corresponding to the target attribution label. When each terminal accesses the target communication cell corresponding to the target attribution label, the load of each target communication cell in the hot spot balancing area is dynamically balanced to achieve global optimization, thereby improving user experience.

It should be noted that the target attribution label of each terminal can be determined through the classification model. In some embodiments, when classifying terminals located in any core cell, first determine that the maximum number of terminals that the core cell can accommodate is N, then pre-classify in combination with the distance information, and classify the N terminals closest to the cell centroid of the core cell into the core cell, and then classify the attribution of each terminal through the classification model, using the cell resource information of the core cell and its adjacent load sharing cells, determine the communication cell to which each terminal belongs, and classify several terminals that are far from the cell centroid of the core cell into the load sharing cell to which they belong, thereby determining the target attribution label of each terminal.

It should be noted that the target attribution label of each terminal can also be determined through the clustering model. In some embodiments, the terminals located in each communication cell are clustered according to the distance information of the terminal, and the terminals that are closer to the cell centroid of a certain communication cell are clustered into the same communication cell. The clustering results are adjusted in combination with the neighboring cell relationship, capacity share and capacity gap, and the target attribution label of each terminal is determined through the communication cell to which each terminal is targeted.

In addition, referring to FIG. 7 , in one embodiment, step S630 in the embodiment shown in FIG. 6 includes but is not limited to the following steps:

Step S710: for any terminal, when the target attribution tag is different from the initial attribution tag, determining a first target communication cell according to the initial attribution tag, and determining a second target communication cell according to the target attribution tag, wherein the first target communication cell is adjacent to the second target communication cell;

Step S720, determine edge adjustment information based on the distance information, the first target communication cell, the second target communication cell and the neighboring cell relationship, wherein the edge adjustment information is used to adjust the coverage of the first target communication cell or the second target communication cell to minimize the difference in capacity share between the first target communication cell and the second target communication cell.

It can be understood that the initial edge information of each target communication cell can be determined through the initial attribution label and distance information of each terminal, and the neighboring relationship of the target communication cell; the target edge information of each target communication cell can be determined through the target attribution label and distance information of each terminal, and the neighboring relationship of the target communication cell; when the target attribution label is different from the initial attribution label, it is equivalent to that the target edge information is different from the initial edge information, and the edge of the communication cell needs to be adjusted. When adjusting two adjacent target communication cells, the two target communication cells can be adjusted at the same time. For example, the first The coverage of the target communication cell expands and the coverage of the second target communication cell shrinks, or the coverage of the first target communication cell shrinks and the coverage of the second target communication cell expands. Alternatively, only one of the target communication cells can be adjusted to shrink or expand the coverage of the target communication cell, thereby achieving rapid switching of terminals that need to adjust the access cell to the new communication cell, thereby ensuring user experience.

In addition, referring to FIG. 8 , in one embodiment, before step S110 in the embodiment shown in FIG. 1 , there are also but not limited to the following steps:

Step S810, obtaining a measurement report of each communication cell, wherein the measurement report is generated by a terminal located in the communication cell;

Step S820: Determine neighbor relationship and distance information according to the measurement report.

It can be understood that the Measurement Report (MR) refers to the measurement information reported by the terminal in the cell overlapping area. The measurement report includes the identifier of the serving cell, the identifier of the neighboring cell detected by the terminal, the reference signal received power RSRP information of the distance from the terminal to the serving cell, and the RSRP information from the terminal to the neighboring cell. Therefore, by obtaining the measurement reports of each communication cell through the measurement report summary module, the neighboring cell relationship of each communication cell can be determined through the association relationship between the serving cell and the neighboring cell in the measurement report, and the distance information of the terminal can be determined through the RSRP information. Therefore, by analyzing the measurement report, it is possible to statically or dynamically adjust the coverage range of each communication cell, balance the load of each target communication cell, and improve the user experience.

In addition, referring to FIG. 9 , in one embodiment, the cell resource information includes capacity proportion and capacity gap; before step S110 in the embodiment shown in FIG. 1 , the following steps are also included but not limited to:

Step S910, obtaining resource utilization information, resource capacity information of the communication cell and the initial belonging tag of each terminal, wherein the initial belonging tag is used to characterize the target communication cell corresponding to the terminal;

Step S920, determining the capacity ratio according to the resource utilization information;

Step S930: determining the capacity gap according to the resource capacity information and the initial attribution tag.

It can be understood that the resource utilization information of the communication cell is used to characterize the resource utilization rate, and the resource capacity information of the communication cell is used to characterize the resource capacity. The resource capacity in the communication cell is fixed. Through the resource utilization rate, the capacity ratio can be determined. In addition, in the hot spot balancing area, since the upper limit of the capacity ratio is 100%, in order to accurately determine the load state of the communication cell, it is necessary to determine the capacity gap of the target communication cell. The capacity gap is used to characterize the value of the capacity exceeding the resource capacity. The capacity gap can be calculated through the initial attribution tag and the resource capacity information. In some embodiments, each terminal is regarded as having the same resource occupancy, and the resource capacity of each target communication cell is fixed. The number of terminals corresponding to each target communication cell is determined by the initial attribution tag, and then the resource excess of each target terminal is calculated. The resource excess is the difference between the sum of the resource occupancy of all terminals in the target communication cell and the resource capacity of the target communication cell. If the resource excess is zero, the capacity gap is zero. If the resource excess is greater than zero, the capacity gap is the ratio of the resource excess to the resource capacity.

In addition, in one embodiment, the resource utilization information includes business resource utilization information and hardware resource utilization information; the business resource utilization information includes at least one of the following: frequency domain utilization, downlink power utilization; the hardware resource utilization information includes at least one of the following: the ratio of the number of connected users to the maximum number of supported users, CPU utilization.

It can be understood that the load attributes of the communication cell can be determined through the business resource utilization information and the hardware resource utilization information. A high-load cell can be a high load on business resources or a high load on hardware resources. Hardware resources are used to characterize the performance of the communication cell. If business resources such as frequency domain resources are about to be exhausted or reach the upper limit, the business needs of the terminal will be restricted, affecting the user experience. Therefore, alleviating the high load on business resources can help increase the communication efficiency of the wireless communication subnet. The traffic of the communication cell can ensure the user experience; if the hardware resources such as CPU or memory are about to reach the upper limit or have reached the upper limit, the system will be unstable. Therefore, alleviating the high load on hardware resources can prevent the communication cell from entering an abnormal state.

In addition, refer to FIG. 10 , which is a schematic diagram of a hotspot balancing area provided by an embodiment of the present application.

It can be understood that when performing regional division, each communication cell is set as the cell centroid. If any two communication cells are adjacent, the cell centroids corresponding to the two communication cells are connected by a dotted line. First, all high-load cells of the wireless communication subnet are identified. For example, the cell centroids corresponding to the high-load cells are marked as H1, H2, H3, and H4 in turn. Then, starting from any high-load cell, the high-load cell is taken as the core cell. For example, starting from H1, the high-load cell corresponding to H1 is taken as the core cell. Then, according to the neighboring cell relationship, since H2 is adjacent to H1, H3 and H4 are adjacent to each other. 4 are adjacent to H2 respectively, therefore, the high-load cells corresponding to H2, H3 and H4 are all taken as core cells; then, according to the neighboring cell relationship, all the medium and low-load cells adjacent to each core cell are determined, and the medium and low-load cells are taken as load-sharing cells, and the centroids corresponding to each load-sharing cell are marked L1, L2, L3, L4 and L5 in sequence; finally, the communication cells corresponding to H1, H2, H3, H4, L1, L2, L3, L4 and L5 are taken as a whole area, namely, the hotspot balancing area; the cell centroids outside the hotspot balancing area are marked O1, O2, O3 and O4 in sequence.

It should be noted that the dotted rectangular box corresponding to the hotspot balancing area is for illustration only and does not represent the coverage range corresponding to the hotspot balancing area. Since the coverage range of each communication cell is usually a sector-shaped area, the coverage range of the hotspot balancing area can be formed by superimposing multiple sector-shaped areas.

In addition, refer to Figure 11, which is a schematic diagram of the communication cell coverage provided by an embodiment of the present application.

It can be understood that when performing regional division, each communication cell is set as the cell centroid. If there is a dotted line connection between the terminal and the cell centroid, it means that the terminal can report a measurement report to the communication cell; for any cell centroid, there is a sector area formed by dotted lines, and the sector area is the coverage range of the communication cell; adjusting the coverage range of the communication cell is to adjust the direction or size of the sector area; through regional division, according to the neighboring relationship and cell resource information of the communication cell, multiple target communication cells are divided into hot spot balancing areas, and the hot spot balancing area refers to the area where load adjustment is required, and then through the machine learning algorithm, the distance between the terminal and the centroid of each cell, as well as the neighboring relationship and cell resource information of the target communication cell, the edge adjustment information of each target communication cell in the hot spot balancing area is determined, and then the coverage range of the target communication cell is adjusted, so as to realize dynamic adjustment of the edge of the target communication cell, load adjustment of the adjacent target communication cell, and effectively improve the load adjustment effect of the communication cell. In addition, the load of each target communication cell in the hot spot balancing area can be dynamically balanced, and the entire hot spot balancing area is used as the load adjustment unit, which is easier to achieve the global optimum, improve the overall load adjustment effect of the region, and thus improve the user experience.

In addition, referring to FIG. 12 , an embodiment of the present application further provides an electronic device.

The electronic device includes: one or more processors and memory, and one processor and memory are taken as an example in Fig. 12. The processor and memory may be connected via a bus or other methods, and the connection via a bus is taken as an example in Fig. 12.

The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs, such as the communication network load adjustment method in the above-mentioned embodiment of the present application. The processor implements the communication network load adjustment method in the above-mentioned embodiment of the present application by running the non-transitory software programs and programs stored in the memory.

The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data required to execute the communication network load adjustment method in the above-mentioned embodiment of the present application, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, The memory may include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The non-transient software program and program required to implement the communication network load adjustment method in the above-mentioned embodiment of the present application are stored in the memory. When executed by one or more processors, the communication network load adjustment method in the above-mentioned embodiment of the present application is executed, for example, the method steps S110 to S140 in Figure 1, the method steps S210 to S220 in Figure 2, the method steps S310 to S320 in Figure 3, the method steps S410 to S420 in Figure 4, the method steps S510 to S530 in Figure 5, the method steps S610 to S630 in Figure 6, the method steps S710 to S720 in Figure 7, and the method steps S810 to S820 in Figure 8 are executed. 0. In steps S910 to S930 of the method in FIG9, neighboring cell relations and cell resource information of multiple communication cells are obtained, and the cell centroid of each communication cell is determined, wherein the cell resource information is determined by a terminal located in the communication cell; each communication cell is divided into regions according to the neighboring cell relations and cell resource information, and a hotspot balancing region is determined, wherein the hotspot balancing region includes multiple target communication cells; distance information of the terminal located in each target communication cell is obtained, wherein the distance information is used to characterize the distance between the terminal and the centroid of each cell; according to the distance information, neighboring cell relations and cell resource information, based on a preset machine learning algorithm, edge adjustment information of each target communication cell is determined to adjust the coverage of the target communication cell. Based on this, through regional division, multiple target communication cells are divided into hot spot balancing areas according to the neighboring cell relationships and cell resource information of the communication cells. The hot spot balancing area refers to the area where load adjustment is required. Then, through the machine learning algorithm, the distance between the terminal and the centroid of each cell, as well as the neighboring cell relationship and cell resource information of the target communication cell are used to determine the edge adjustment information of each target communication cell in the hot spot balancing area, and then adjust the coverage range of the target communication cell, thereby realizing dynamic adjustment of the edge of the target communication cell and load adjustment of adjacent target communication cells, effectively improving the load adjustment effect of the communication cell. In addition, the load of each target communication cell in the hot spot balancing area can be dynamically balanced, and the entire hot spot balancing area can be used as the load adjustment unit, which makes it easier to achieve global optimality and improve the overall load adjustment effect of the region, thereby improving user experience.

In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by a processor or a controller, for example, by a processor in the above-mentioned electronic device embodiment, so that the above-mentioned processor can execute the communication network load adjustment method in the above-mentioned embodiment, for example, execute the method steps S110 to S140 in Figure 1, the method steps S210 to S220 in Figure 2, the method steps S310 to S320 in Figure 3, the method steps S410 to S420 in Figure 4, the method steps S510 to S530 in Figure 5, the method steps S610 to S630 in Figure 6, and the method steps S710 to S72 in Figure 7. 0. Steps S810 to S820 of the method in FIG8 and steps S910 to S930 of the method in FIG9 are performed by obtaining neighboring cell relations and cell resource information of multiple communication cells, and determining the cell centroid of each communication cell, wherein the cell resource information is determined by a terminal located in the communication cell; dividing each communication cell into regions according to the neighboring cell relations and the cell resource information, and determining a hotspot balancing region, wherein the hotspot balancing region includes multiple target communication cells; obtaining distance information of the terminal located in each target communication cell, wherein the distance information is used to characterize the distance between the terminal and the centroid of each cell; determining edge adjustment information of each target communication cell based on the distance information, neighboring cell relations and cell resource information and a preset machine learning algorithm to adjust the coverage of the target communication cell. Based on this, through regional division, according to the neighboring cell relationship and cell resource information of the communication cell, multiple target communication cells are divided into hot spot balancing areas. The hot spot balancing area refers to the area where load adjustment is required. Then, through the machine learning algorithm, the distance between the terminal and the centroid of each cell, as well as the neighboring cell relationship and cell resource information of the target communication cell are used to determine the edge adjustment information of each target communication cell in the hot spot balancing area, and then adjust the coverage range of the target communication cell, realize dynamic adjustment of the edge of the target communication cell, and adjust the load of the adjacent target communication cell, effectively improving the load adjustment effect of the communication cell. In addition, it is possible to dynamically balance the load of each target communication cell in the hotspot balancing area, and use the entire hotspot balancing area as a load adjustment unit, which makes it easier to achieve global optimality and improve the overall load adjustment effect of the area, thereby improving user experience.

It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

The above is a specific description of some implementations of the present application, but the present application is not limited to the above implementation methods. Technical personnel familiar with the field may also make various equivalent modifications or substitutions without violating the essence of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

A communication network load adjustment method, comprising:

Acquire neighboring cell relationships and cell resource information of a plurality of communication cells, and determine a cell centroid of each of the communication cells, wherein the cell resource information is determined by a terminal located in the communication cell;

According to the neighboring cell relationship and the cell resource information, each of the communication cells is divided into regions to determine a hotspot balancing region, wherein the hotspot balancing region includes a plurality of target communication cells;

Acquire distance information of the terminal located in each of the target communication cells, wherein the distance information is used to represent the distance between the terminal and the centroid of each of the cells;

According to the distance information, the neighboring cell relationship and the cell resource information, based on a preset machine learning algorithm, edge adjustment information of each of the target communication cells is determined to adjust the coverage of the target communication cells.
The method according to claim 1, wherein the cell resource information includes a capacity ratio; and the step of dividing each of the communication cells into regions according to the neighboring cell relationship and the cell resource information to determine a hotspot balancing region comprises:

Determining a load attribute of the communication cell according to the capacity proportion;

According to the neighboring cell relationship and the load attribute, each of the communication cells is divided into regions to obtain a hotspot balancing region.
The method according to claim 2, wherein the hotspot balancing area includes a core cell; and the core cell is determined by the following steps:

When the capacity proportion is greater than a preset first threshold, determining that the load attribute of the communication cell is a high-load cell;

Based on the neighboring cell relationship, any one of the high-load cells is used as a core cell, and all the high-load cells adjacent to the core cell are used as the core cells.
The method according to claim 3, wherein the hotspot balancing area further includes a load sharing cell; the load sharing cell is determined by the following steps:

When the capacity proportion is less than or equal to a preset second threshold, determining that the load attribute of the communication cell is a medium-low load cell, wherein the second threshold is less than or equal to the first threshold;

Based on the neighboring cell relationship, each of the medium and low load cells is traversed, and all the medium and low load cells adjacent to the core cell are used as load sharing cells.
The method according to claim 1, wherein the hotspot balancing area includes a core cell and a load sharing cell, and the cell resource information includes a capacity ratio and a capacity gap; the determining the edge adjustment information of each of the target communication cells based on the distance information, the neighboring cell relationship and the cell resource information and based on a preset machine learning algorithm, comprises:

Based on the ranking information of the capacity proportion and the capacity gap, traverse the core cells;

For any of the core cells, the terminal located in the core cell is taken as a terminal to be processed, and based on the neighboring cell relationship, the load sharing cell adjacent to the core cell is taken as a cell to be processed;

The distance information of the terminal to be processed, the neighboring cell relationship, the capacity proportion of the core cell, the capacity proportion of the cell to be processed and the capacity gap of the core cell are input into the machine learning algorithm to determine the edge adjustment information of each of the target communication cells.
The method according to claim 1, wherein the cell resource information includes a capacity share and a capacity gap, and the machine learning algorithm includes a classification model or a clustering model; the determining the edge adjustment information of each of the target communication cells based on the distance information, the neighboring cell relationship and the cell resource information based on a preset machine learning algorithm comprises:

Acquire an initial belonging tag of each of the terminals, wherein the initial belonging tag is used to characterize the target communication cell corresponding to the terminal;

Input the distance information, the neighboring cell relationship, the capacity proportion and the capacity gap into the classification model or the clustering model to determine a target attribution label of each terminal, wherein the target attribution label is used to characterize the target communication cell corresponding to the terminal;

The edge adjustment information of each of the target communication cells is determined according to the distance information, the initial attribution label, the target attribution label and the neighboring cell relationship.
The method according to claim 6, wherein the determining the edge adjustment information of each of the target communication cells according to the distance information, the initial attribution tag, the target attribution tag and the neighboring cell relationship comprises:

For any of the terminals, when the target attribution tag is different from the initial attribution tag, determining a first target communication cell according to the initial attribution tag, and determining a second target communication cell according to the target attribution tag, wherein the first target communication cell is adjacent to the second target communication cell;

The edge adjustment information is determined based on the distance information, the first target communication cell, the second target communication cell and the neighboring cell relationship, wherein the edge adjustment information is used to adjust the coverage range of the first target communication cell or the second target communication cell to minimize the difference in capacity share between the first target communication cell and the second target communication cell.
The method according to claim 1, wherein before the step of obtaining the neighboring cell relationship and cell resource information of each communication cell, it also includes:

Obtaining a measurement report of each of the communication cells, wherein the measurement report is generated by the terminal located in the communication cell;

The neighboring cell relationship and the distance information are determined according to the measurement report.
The method according to claim 1, wherein the cell resource information includes capacity proportion and capacity gap; before the step of obtaining the neighboring cell relationship and cell resource information of each communication cell, it also includes:

Acquire resource utilization information, resource capacity information of the communication cell and an initial belonging tag of each of the terminals, wherein the initial belonging tag is used to characterize the target communication cell corresponding to the terminal;

Determining the capacity ratio according to the resource utilization information;

The capacity gap is determined according to the resource capacity information and the initial attribution tag.
According to the method according to claim 9, the resource utilization information includes business resource utilization information and hardware resource utilization information; the business resource utilization information includes at least one of the following: frequency domain utilization or downlink power utilization; the hardware resource utilization information includes at least one of the following: the ratio of the number of connected users to the maximum number of supported users or CPU utilization.
An electronic device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the communication network load adjustment method as claimed in any one of claims 1 to 10 when executing the computer program.
A computer-readable storage medium stores a computer-executable program, wherein the computer-executable program is used to enable a computer to execute the communication network load adjustment method as described in any one of claims 1 to 10.