CN118265038A

CN118265038A - Network coverage optimization method, electronic equipment and storage medium

Info

Publication number: CN118265038A
Application number: CN202211699964.0A
Authority: CN
Inventors: 庞磊; 刘巧艳; 毛凯; 李建国; 王郭燕; 张劲超; 周先文
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2022-12-28
Filing date: 2022-12-28
Publication date: 2024-06-28
Also published as: WO2024140507A1

Abstract

The embodiment of the application provides a network coverage optimization method, electronic equipment and a storage medium, relates to the technical field of communication, and can improve the efficiency and accuracy of an optimization process by utilizing a multi-objective optimization mode. The network coverage optimization method comprises the following steps: initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized can be obtained first. And then solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set, wherein one non-dominant solution in the non-dominant solution set is used for indicating target values of the antenna parameters of the plurality of cells in the cell cluster to be optimized. And finally, selecting a target non-dominant solution from the non-dominant solution set, and setting antenna parameters of a plurality of cells in the cell cluster to be optimized based on the target non-dominant solution.

Description

Network coverage optimization method, electronic equipment and storage medium

Technical Field

The present application relates to the field of communications technologies, and in particular, to a network coverage optimization method, an electronic device, and a storage medium.

Background

With the continuous development of wireless communication technology and the diversification of mobile services, the requirements of users on the quality of wireless communication networks are gradually increased, and areas with poor network coverage quality can occur due to the current reasons of increased base station antennas, change of surrounding environments of base stations, unreasonable planning layout of early base stations and the like. Therefore, network coverage optimization is an important link in wireless communication network construction.

But for areas of poor coverage by such networks, the coverage of the cells is typically optimized by site surveys and adjusting the relevant parameters of the cells based on engineer experience. Therefore, a large amount of manpower and material resources are consumed, the efficiency and the accuracy of the optimization process are low, and the optimization result is not ideal.

Disclosure of Invention

The application provides a network coverage optimization method, electronic equipment and a storage medium, which can improve the efficiency and accuracy of an optimization process in a multi-objective optimization mode.

In order to achieve the above purpose, the application adopts the following technical scheme:

in a first aspect, an embodiment of the present application provides a network coverage optimization method, where the method includes:

and acquiring initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized.

And then solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set, wherein one non-dominant solution in the non-dominant solution set is used for indicating target values of the antenna parameters of the plurality of cells in the cell cluster to be optimized.

And finally, selecting one non-dominant solution from the non-dominant solution set, and setting antenna parameters of a plurality of cells in the cell cluster to be optimized based on the selected non-dominant solution.

In a second aspect, an embodiment of the present application further provides an electronic device, including:

the acquisition module is used for acquiring initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized.

The processing module is used for solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set, wherein one non-dominant solution in the non-dominant solution set is used for indicating target values of the antenna parameters of the plurality of cells in the cell cluster to be optimized.

The processing module is further configured to select one non-dominant solution from the non-dominant solution set, and set antenna parameters of a plurality of cells in the cell cluster to be optimized based on the selected non-dominant solution.

In a third aspect, an embodiment of the present application further provides a communication, including: a memory and a processor; the memory is coupled to the processor; the memory is used for storing a computer program; the processor, when executing the computer program, implements the network coverage optimization method provided in the first aspect.

In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium having stored thereon computer instructions that, when run on an electronic device, cause the electronic device to perform a network coverage optimization method as provided in the first aspect above.

In a fifth aspect, embodiments of the present application also provide a computer program product comprising computer program instructions which, when executed by a processor, implement a network coverage optimization method as provided in the first aspect above.

In the embodiment of the application, the technical scheme combines the optimization requirement of the actual wireless network environment, carries out multi-objective optimization on the actual network coverage problem, and can obtain the optimization result of the more adaptive environment more quickly. And compared with the traditional mode of adjusting according to expert experience, the method reduces a great deal of manpower investment and improves network deployment efficiency.

Drawings

The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate and do not limit the application.

Fig. 1 is a schematic diagram of a communication system 10 provided by the present application;

Fig. 2 is a flow chart of a network coverage optimization method according to an embodiment of the present application;

fig. 3 is a flow chart of a network coverage optimization method according to an embodiment of the present application;

FIG. 4a is a schematic diagram of a multi-objective optimization process according to an embodiment of the present application;

FIG. 4b is a schematic diagram of another multi-objective optimization process according to an embodiment of the present application;

FIG. 4c is a schematic diagram of yet another multi-objective optimization process provided by an embodiment of the present application;

FIG. 5 is a schematic flow chart of a multi-objective optimization process according to an embodiment of the present application;

FIG. 6 is a flow chart of another multi-objective optimization process according to an embodiment of the present application;

Fig. 7 is a flow chart of another network coverage optimization method according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more.

In embodiments of the application, words such as "exemplary" or "such as" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

For ease of understanding, the basic concepts of some terms or techniques involved in embodiments of the present invention are first briefly described and illustrated.

(1) Multi-objective optimization problem

The objective optimization problem generally refers to obtaining an optimal solution of an objective function through a certain optimization algorithm. If the objective function of the optimization is one, the objective optimization problem in this case is called a single objective optimization problem. If there are two or more objective functions to be optimized, the objective optimization problem in this case is called a multi-objective optimization problem.

Illustratively, the multi-objective optimization problem can be represented by the following equation (1):

F (x) = ((F ₁(x)……f_m(x))^T formula (1))

subject to x∈Ω

And f ₁(x)……f_m (x) all represent objective functions, and m is the number of objective functions to be optimized for the multi-objective optimization problem. x epsilon omega represents constraint conditions, x represents variables, and omega represents the value space of x. F (x) represents the target optimization result of the multi-target optimization problem.

(2) Non-dominant solution

For multi-objective optimization problems, there is typically a set of solutions that are not superior in terms of overall objective function. It will be appreciated that one feature of the solution to the multi-objective optimization problem is that it is not possible to refine any objective function while not weakening at least one other objective function, in other words, while improving any objective function, it is necessary to weaken at least one other objective function. Therefore, a solution having such a feature is referred to as a non-dominant solution.

Wherein "governance (dominate)" represents a method of comparative solution. If one solution A is not worse than another solution B on all objective functions and solution A is better than solution B on at least one objective function, then solution A can be considered to dominate solution B. If one solution cannot be dominated by any other solution, then this solution is called a non-dominated solution (non-dominated solution). If one solution is dominated by any of the other solutions, then this solution is referred to as the dominated solution (dominated solution). Accordingly, the solution of the multi-objective optimization problem is referred to as a non-dominant solution, and accordingly, the solution set of the multi-objective optimization problem may be referred to as a non-dominant solution set.

In some embodiments, the non-dominant solution may also be referred to as a pareto (Paerot) solution, an optimal solution, etc., without limitation.

(3) Weight summation method

The weighting summation method assumes that the multi-objective optimization problem to be optimized has m objective functions whose aggregate function passes through a non-negative weighting vectorWeighting onto each target converts the multi-target optimization problem into a plurality of single-target sub-problems.

Illustratively, the aggregate function of the weight summation method can be expressed as the following equation (2):

subject to x∈Ω

Wherein, Is a set of weight vectors that, for all i=1, 2, …, m,

(4) Chebyshev method

Illustratively, the aggregate function of the chebyshev method can be expressed as the following formula (3)

Wherein,As a reference point, z ₁ denotes a reference point corresponding to the objective function f ₁ (x), and z _m denotes a reference point corresponding to the objective function f _m (x). For each i=1, …, m, there is

Lambda ^j is the weight vector of the weight,

The foregoing is a description of technical terms related to the embodiments of the present disclosure, and is not repeated herein below.

Currently, in addition to the manner of adjusting the relevant parameters of the cells according to the experience of engineers, coverage problems such as overlapping coverage, weak coverage, over coverage, poor signal-to-interference-plus-noise ratio (signal to interference plus noise ratio, SINR) and the like can be optimized with a single objective. But this optimization is not perfect. Taking a large-scale multiple input multiple output (Massive Multiple Input Multiple Output, massive MIMO) as an example, the Massive MIMO can flexibly adjust multiple dimensions such as horizontal lobe width, vertical lobe width, beam direction angle, downtilt angle, beam quantity, and the like, and can also be finely adjusted by setting reasonable step sizes under each dimension. Therefore, network capacity and stereoscopic depth coverage under various complex scenes can be greatly improved. However, due to factors such as low completeness of the antenna parameter library, complex scene requirements, various building forms and the like, network coverage problems such as weak coverage, overlapping coverage, excessive coverage, poor quality of SINR and the like still exist. Moreover, the coverage problem is often a packing dislocation, and there is a coupling relationship. Therefore, a single optimization of network coverage does not achieve a good solution.

In view of this, the present application provides a network coverage optimization method, which can first obtain initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized by using a multi-objective evolutionary algorithm. And then solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set, wherein one non-dominant solution in the non-dominant solution set is used for indicating target values of the antenna parameters of the plurality of cells in the cell cluster to be optimized. And finally, selecting one non-dominant solution from the non-dominant solution set, and setting antenna parameters of a plurality of cells in the cell cluster to be optimized based on the selected non-dominant solution. Thus, the investment of a large amount of manpower is reduced and the network deployment efficiency is improved.

The following describes in detail the implementation of the embodiment of the present application with reference to the drawings.

The method provided by the embodiment of the application can be applied to various communication systems. For example, the communication system may be a long term evolution (long term evolution, LTE) system, a fifth generation (5th generation,5G) communication system, a Wi-Fi system, a third generation partnership project (3rd generation partnership project,3GPP) related communication system, a future evolution communication system (e.g., a sixth generation (6th generation,6G) communication system, etc.), or a system in which multiple systems are integrated, etc., without limitation. The method provided by the embodiment of the present application will be described below by taking the communication system 10 shown in fig. 1 as an example. Fig. 1 is only a schematic diagram, and does not limit the applicable scenario of the technical solution provided by the present application.

Fig. 1 is a schematic diagram of a communication system 10 according to an embodiment of the present application. In fig. 1, communication system 10 may include a network device 101, and a terminal 102 and a terminal 103 in communication with network device 101. In some embodiments, communication system 10 also includes a computing device 104 in communication with network device 101. In some embodiments, communication system 10 further includes a network device 105 in communication with network device 101 or computing apparatus 104, and terminals 106 and 107 in communication with network device 105.

In fig. 1, a network device may provide a wireless access service for a terminal. Specifically, each network device corresponds to a service coverage area, and a terminal entering the area can communicate with the network device to receive the wireless access service provided by the network device. In some embodiments, the service coverage may include one or more cells (cells). For example, the service coverage area corresponding to the network device 101 includes cell 1 and cell 2, the terminal 102 accesses the network device 101 through cell 1, and the terminal 103 accesses the network device 101 through cell 2.

The network device in the embodiment of the present application, such as the network device 101 or the network device 105, may be any device having a radio transceiver function, for example, a base station in LTE, a base station in New Radio (NR), or a base station for subsequent evolution of 3 GPP.

The terminal in the embodiment of the application comprises the following steps: the terminal 102, the terminal 103, the terminal 106, or the terminal 107 is any device having a wireless transmitting/receiving function. For example, the terminal is a handheld device (e.g., a cell phone or tablet computer, etc.), an in-vehicle device, a wearable device, a terminal or computing device in an internet of things (internet of things, ioT) system, etc. with wireless communication functionality. A terminal may also be referred to as a terminal device, or User Equipment (UE), without limitation.

The computing device 104 in fig. 1 may be any device having communication and computing capabilities. For example, the computing device 104 is a server, computer, cloud server, or the like.

The communication system 10 shown in fig. 1 is for example only and is not intended to limit the scope of the present application. Those skilled in the art will appreciate that in particular implementations, communication system 10 may include other devices, and that the number of network devices, terminals, or computing devices may be determined according to particular needs without limitation.

The embodiment of the application also provides electronic equipment, which is an execution main body of the network coverage optimization method. The electronic device is an electronic device having data processing capabilities. For example, the electronic device may be a computing apparatus in the communication system 10, or the electronic device may be a functional module in the computing apparatus 104, or the electronic device may be any computing device connected to the computing apparatus 104, or the like. Of course, the electronic device may also be the network device, which is not limited in the embodiment of the present application.

As shown in fig. 2, a network coverage optimization method provided by an embodiment of the present application may include the following steps:

S101, obtaining initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized.

The antenna parameters of the cell are important parameters affecting the coverage effect of the cell network. In practical applications, different cell antenna parameters may be set based on network coverage requirements of different scenes, such as macro coverage scenes and high-rise coverage scenes.

In some embodiments, the antenna parameters of the cell may include at least one of azimuth, downtilt, horizontal bandwidth, and vertical bandwidth. The azimuth angle of the cell is the included angle between the network main coverage direction of the cell and the horizontal normal direction of the cell. The downtilt angle of a cell is the angle between the network main coverage direction of the cell and the normal direction perpendicular to the cell. Horizontal beamwidth refers to the beamwidth of the horizontal plane of the antenna. Vertical beamwidth refers to the beamwidth of the antenna in the vertical plane.

The wider the horizontal bandwidth, the better the coverage at the sector boundary, but the more likely the beam distortion occurs when the antenna tilt angle increases, thereby forming a cross-zone coverage. The narrower the width of the vertical beam, the faster the signal decays away from the main beam direction, and the easier it is to accurately control the coverage by adjusting the antenna tilt angle.

In some embodiments, the measurement information of the terminal includes signal quality of a plurality of cells in a cell cluster to be optimized measured by the terminal. By way of example, the signal quality may be expressed in terms of parameters such as reference signal received power (REFERENCE SIGNAL RECEIVING power, RSRP), which is not limited.

In some embodiments, the measurement information of the terminal may further include direction of arrival (direction of the angle, DOA) information, which may include horizontal-direction of the angle (H-DOA) information and vertical-direction of the angle (V-DOA) information.

It should be understood that the measurement information of the plurality of terminals in the embodiment of the present application may be used to calculate coverage index parameters related to a plurality of cells in the cell cluster to be optimized, such as a repetition rate, a weak coverage rate, and the like. These coverage indicator parameters may reflect the severity of coverage problems for the cell.

S102, solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set.

In some embodiments, the set of non-dominant solutions includes one or more non-dominant solutions for indicating target values of antenna parameters for a plurality of cells in the cluster of cells to be optimized.

Illustratively, taking an example that one cell cluster to be optimized includes l cells, the above-mentioned one non-dominant solution may be expressed as the following formula (4):

w= [ Wcell ₀,Wcell₁,Wcell₂...Wcell_l-1 ] formula (4)

Wherein Wcell ₀、Wcell₁、Wcell₂……Wcell_l-1 are target values of antenna parameters of each of the l cells, respectively.

In some embodiments, the multi-objective optimization problem is determined from a plurality of the following objective functions:

an objective function with minimized overlap coverage as an optimization objective;

an objective function with minimized weak coverage as an optimization objective;

taking the minimum signal-to-noise ratio quality difference as an objective function of an optimization target;

an objective function with minimized handoff coverage as an optimization objective;

an objective function with maximized signal-to-noise ratio as an optimization target;

an objective function with maximized signal quality as an optimization target;

taking the maximized signal-to-dry ratio as an objective function of an optimization target;

an objective function with the maximized transmission rate as an optimization target;

And an objective function with the maximized split ratio as an optimization target.

Wherein the split ratio is used to characterize the ratio between the traffic of the target traffic and the traffic of all traffic. The target traffic may be, for example, 5G traffic.

It should be appreciated that the above objective functions are merely examples, and that other objective functions related to coverage problems may also be considered when performing coverage optimization for a cluster of cells to be optimized, which is not limited.

In some embodiments, the multi-objective optimization problem may be solved by a decomposition-based multi-objective optimization algorithm, a non-dominant ordered genetic algorithm (NSGA-II), a multi-objective evolutionary algorithm, or the like, without limitation.

For example, step S102 may be specifically implemented as: the method comprises the steps that the multi-objective optimization problem is solved based on the initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and the measurement information of a plurality of terminals, so as to obtain the non-dominant solution set; the decomposition dimension of the decomposition-based multi-objective optimization algorithm is determined according to the number of cells contained in the cell cluster to be optimized and the number of objective functions related to the multi-objective optimization problem.

S103, selecting a target non-dominant solution from the non-dominant solution set, and setting antenna parameters of a plurality of cells in the cell cluster to be optimized based on the target non-dominant solution.

As a possible implementation manner, the most critical objective function can be determined according to the main cause of the coverage problem of the cell cluster to be optimized; traversing each non-dominant solution in the non-dominant solution sets to calculate a function value of a most critical objective function corresponding to each non-dominant solution; and selecting the non-dominant solution corresponding to the optimal function value from the function values of the most critical objective function corresponding to each non-dominant solution as the objective non-dominant solution.

For example, the main reason for the coverage problem of the cell cluster to be optimized is that the overlap coverage is too high, then the most critical objective function is one that aims to minimize the overlap coverage as an optimization objective.

In the actual use process, a target non-dominant solution can be selected from the determined non-dominant solutions based on the current network coverage requirement scene (such as a high-rise scene), so that the network coverage optimization result is adapted to the scene, and the network coverage requirements under different user scenes can be met.

In some embodiments, when a decomposition-based multi-objective optimization algorithm is employed to solve the multi-objective optimization problem, as shown in fig. 3, step S102 may be implemented as the following steps:

S1021, decomposing the multi-objective optimization problem into a plurality of single-objective sub-problems, and configuring a corresponding population for each single-objective sub-problem in the plurality of single-objective sub-problems.

In some embodiments, multiple weight vectors are initialized, and the multi-objective optimization problem can be decomposed into multiple single-objective sub-problems according to the multiple weight vectors. Each weight vector corresponds to a single target sub-problem.

As an example, based on the optimization target number S, the correspondence is tensed into an S-dimensional space. Uniformly sampling the S-dimensional space, determining the sampling quantity H in each target direction, and defining 1/H as sampling step length; the number of S-dimensional uniform sampling weight vectors is

In some embodiments, for each weight vector, the distance between the weight vector and the other weight vectors may be calculated, and then the T weight vectors closest to the weight vector are selected as the neighboring weight vectors of the weight vector. Thus, the single target sub-problem corresponding to the T weight vectors is the adjacent sub-problem of the single target sub-problem corresponding to the weight. It should be noted that only adjacent sub-problems can be used to optimize each other.

S1022, performing iterative optimization on the population corresponding to each single-target sub-problem in the plurality of single-target sub-problems based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized, measurement information of a plurality of terminals and an aggregation function of a multi-target optimization algorithm based on decomposition, and stopping and outputting a non-dominant solution set when the iterative stopping condition is met.

For example, the iteration stop condition may be that the number of iterations reaches a preset number.

In some embodiments, during the iterative optimization process, an external population is provided to store non-dominant solutions. Thus, a non-dominant solution set can be extracted from the outer population at the time of iteration stop.

In some embodiments, as shown in fig. 4a, the space spanned by the multi-objective optimization problem may be uniformly sampled with a certain sampling step, so that the multi-objective optimization problem is conveniently disassembled into the sum of single-objective sub-problems corresponding to multiple weight vectors in parallel. In fig. 4a, F1, F2 denote the above objective functions, w1, w2 … …, and w9 denote 9 sampling points. Next, as shown in fig. 4b, the problem of solving Pareto (Pareto) front approximation solutions can be converted into a set of scalar optimization problems based on an aggregation function. Finally, as shown in fig. 4c, iterative optimization is performed by adopting a new solution in the neighborhood, and finally convergence is performed to obtain a Pareto front.

In some embodiments, as shown in fig. 5, an iterative optimization process for a population corresponding to a single target sub-problem includes:

s201, generating offspring individuals in a population corresponding to the single target sub-problem by utilizing a genetic variation mechanism based on a candidate value set of the antenna parameters.

In some embodiments, a sequence number is randomly selected, genetic variation is performed on the sequence number to generate a new sequence number, a candidate value corresponding to the new sequence number is extracted from the candidate value set, and the candidate value corresponding to the new sequence number is used as a child individual y'.

S202, determining m objective function values corresponding to child individuals based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized, measurement information of a plurality of terminals and the child individuals.

As a possible implementation manner, according to initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and child individuals, measurement information of a plurality of terminals is updated respectively, and updated measurement information of the plurality of terminals is obtained. And then according to the updated measurement information of the terminals, determining the function values of m objective functions corresponding to the child individuals.

The updated measurement information of the terminal comprises updated signal quality of a plurality of cells in the cell cluster to be optimized.

In some embodiments, for measurement information of each terminal, the signal quality of the target cell in the cell cluster to be optimized is updated by:

Determining initial antenna gain corresponding to a target cell according to an initial value of an antenna parameter of the target cell; determining a target antenna gain corresponding to a target cell according to a target value of an antenna parameter of the target cell indicated by the child individual; and determining the updated signal quality of the target cell according to the signal quality of the target cell, the initial antenna gain corresponding to the target cell and the target antenna gain corresponding to the target cell.

For example, assuming that the signal quality report of the serving cell corresponding to the antenna parameter k by the UE i is RSRPi, k, and the DOA angle corresponding to the UE is (h, v), when the new antenna parameter j is selected, the calculation method of RSRPi, j of the UE is as shown in the following formula (5):

RSRPi, j= RSRPi, k+ AntGainTbl [ j ] [ h ] [ v ] -AntGainTbl [ k ] [ h ] [ v ] equation (5)

Wherein AntGainTbl is a stored 3D antenna gain table.

S203, determining an aggregation function value corresponding to the child individual based on m objective function values corresponding to the child individual and an aggregation function of a multi-objective optimization algorithm based on decomposition.

In some embodiments, the aggregate function of the decomposition-based multi-objective optimization algorithm may be determined from the aggregate function of the weight summation method and the aggregate function of chebyshev's method. Therefore, the aggregation function of the decomposition-based multi-objective optimization algorithm can have the characteristics of high convergence speed of the weight summation method and good distribution of the Chebyshev method.

Illustratively, the aggregate function of the decomposition-based multi-objective optimization algorithm can be expressed as:

Wherein, x is E omega, For each i=1, …, m, there is Is a set of weight vectors that, for all i=1, 2, …, m,P is a preset constant.

S204, judging whether to replace the individuals in the population corresponding to the adjacent sub-questions of the single target sub-question with the child individuals based on the aggregation function values corresponding to the child individuals.

As one possible implementation, if the aggregate function value corresponding to the child individual is less than or equal to the aggregate function value corresponding to the individual in the population corresponding to the adjacent child problem, the child individual is substituted for the individual in the population corresponding to the adjacent child problem. Or if the aggregate function value corresponding to the child individuals is larger than the aggregate function value corresponding to the individuals in the population corresponding to the adjacent sub-problems, the child individuals are not used for replacing the individuals in the population corresponding to the adjacent sub-problems.

S205, removing solutions governed by child individuals in the external population based on m objective function values corresponding to the child individuals; and, adding the offspring individuals to the outer population without the offspring individuals being dominated by the solution in the outer population. Wherein the external population is used to store non-dominant solutions.

The following describes the solving process of the multi-objective optimization problem in full with reference to specific examples. As shown in fig. 6, the solving process of the multi-objective optimization problem may include the steps of:

S301, initializing N weight vectors, and decomposing the multi-objective optimization problem into N single-objective sub-problems according to the N weight vectors.

In some embodiments, the proximity between two weight vectors is measured in terms of the Euclidean distance between the two weight vectors. Based on this, set B (i) is defined to contain the T closest index vectors from weight vector λ ⁱ. It should be appreciated that i e B (i) is due to the fact that the weight vector nearest to the weight vector lambda ⁱ is itself. If j ε B (i), the j-th sub-problem can be considered as a neighbor of the i-th sub-problem.

S302, initializing and setting corresponding populations for N single-target sub-problems.

In some embodiments, individuals in the population may be generated using random extraction from a candidate set of antenna parameters.

S303, initializing reference points of m objective functions.

In some embodiments, for each objective function, an optimal value may be selected from the function values of the objective functions corresponding to the individual individuals in the population corresponding to the N single objective sub-problems as a reference point.

S304, initializing an external population.

In some embodiments, the external population is empty after initialization.

S305, generating offspring individuals in the population corresponding to the single target sub-problem by utilizing a genetic variation mechanism based on the candidate value set of the antenna parameters.

S306, judging whether to update the reference points of the m objective functions based on the child individuals.

As a possible implementation manner, the function values of m objective functions corresponding to the child individuals can be calculated first; for each objective function, if the function value of the objective function corresponding to the child individual is better than the reference point of the objective function, the function value of the objective function corresponding to the child individual is taken as a new reference point of the objective function.

Illustratively, the formula may be expressed as: for each j=1, …, m, if z _i＜f_j (y '), z _i＝f_j (y') can be made.

S307, updating the neighborhood solution (namely updating the individuals in the population corresponding to the adjacent sub-problems).

As one possible implementation, the neighborhood solution is updated based on chebyshev criteria: for each j e B (i), if g ^AT(y′|λ^j,z)≤g^AT(x^j|λ^j, z), let x ^j＝y′,FV^j =f (y').

Where FV ⁱ is the objective function value of x ⁱ, FV ⁱ＝F(xⁱ), in a population of size N, x ¹,…,x^N ε Ω, where x ⁱ is the current solution to the ith sub-problem.

As another possible implementation, the penalty-based boundary crossing method updates the neighborhood solution: for each j e B (i), if g ^pbi(y′|λ^j,z)≤g^pbi(x^j|λ^j, z), let x ^j＝y′,FV^j =F (y')

ming^pbi(x|λ,z^*)＝d₁+θd₂

d₂＝|F(x)-(z^*-d₁λ)|

Wherein θ is a preset penalty parameter.

S308, updating the external population.

S309, repeating the steps S305-S308 until the iteration stop condition is met.

In some embodiments, as shown in fig. 7, the present application further provides a method for determining the above-mentioned cell cluster to be optimized, where the method includes the following steps:

S401, acquiring coverage problem attribute parameters and position information of each cell in a plurality of cells.

Wherein the coverage problem attribute parameter of the cell is used to characterize the severity of the network coverage problem existing in the cell.

In some embodiments, the coverage problem attribute parameter of the cell is determined based on at least one of overlap coverage, weak coverage, signal to noise ratio quality differential, and handover coverage of the cell.

In some embodiments, the problem attribute parameters of a cell may include a severe proportion of the individual problems of the cell. Such as a severe proportion of overlapping coverage problems, a severe proportion of weak coverage problems, etc. Of course, the problem corresponding to the greatest serious proportion is the network coverage problem which is the most needed to be optimized in the cell.

Wherein the serious proportion of the overlapping coverage problem can be determined based on the proportion of the overlapping coverage of the cell to the sum of the overlapping coverage, weak coverage, signal-to-noise ratio quality difference and cross-zone coverage of the cell. For example, the severe proportion of overlapping coverage problems can be expressed as: overlap coverage/(overlap coverage + weak coverage + signal to noise ratio quality difference + cross-zone coverage).

Accordingly, the serious proportion of the weak coverage problem may be determined based on the proportion of the weak coverage of the cell to the sum of the overlapping coverage, the weak coverage, the signal-to-noise ratio quality difference, and the handover coverage of the cell. For example, a serious proportion of weak coverage problems can be expressed as: weak coverage/(overlap coverage + weak coverage + signal to noise ratio quality difference + cross-zone coverage).

The serious proportion of the signal-to-noise ratio quality difference problem can be determined based on the proportion of the signal-to-noise ratio quality difference of the cell to the sum of the overlapping coverage, the weak coverage, the signal-to-noise ratio quality difference and the handover coverage of the cell. For example, a severe proportion of the signal-to-noise ratio poor quality problem can be expressed as: signal to noise ratio quality difference/(overlap coverage + weak coverage + signal to noise ratio quality difference + cross-zone coverage).

The serious proportion of the coverage problem may be determined based on the proportion of the coverage of the cell to the sum of the coverage of the cell overlap, weak coverage, signal to noise ratio quality difference, and coverage. For example, a significant proportion of the coverage problem can be expressed as: cross coverage/(overlap coverage + weak coverage + signal to noise ratio quality difference + cross coverage).

The coverage of overlapping, weak coverage, signal to noise ratio quality difference and handover coverage of the cells are described as follows:

(1) Overlap coverage ratio

Wherein the overlapping coverage of the cells is determined according to the ratio between the number of repeated coverage sampling points in the cells and the total number of sampling points of the cells.

By way of example, the overlap coverage α of a cell can be expressed as the following formula (6):

in some embodiments, the duplicate cap sampling points are sampling points that satisfy the following conditions:

the measured signal quality of the cell is greater than or equal to a first signal quality threshold;

the measured signal quality of the neighbor cell of the cell is greater than or equal to a second signal quality threshold;

And the difference between the measured signal quality of the cell and the measured signal quality of a neighbor cell of the cell is greater than or equal to a third signal quality threshold.

Illustratively, the first and second signal quality thresholds may range in value from-156 dBm to-31 dBm.

If the number of overlapping coverage sampling points is not less than the overlapping coverage sampling point threshold and the proportion of overlapping coverage sampling points is not less than the overlapping coverage sampling point proportion threshold, the current service cell can be marked as a main overlapping coverage cell, and the adjacent cell can be marked as an auxiliary overlapping coverage cell.

(2) Weak coverage

Wherein the weak coverage of the cell is determined from the ratio between the number of weak coverage sampling points in the cell and the total number of sampling points of the cell.

Illustratively, the weak coverage β of a cell may be expressed as the following equation (7):

in some embodiments, the weak coverage sample points are sample points where the measured signal quality of the cell is less than or equal to a fourth signal quality threshold.

Illustratively, the fourth signal quality threshold may have a value in the range of [ -156dBm, -31dBm ].

If the number of the weak coverage sampling points is not less than the weak coverage sampling point threshold and the proportion of the weak coverage sampling points is not less than the weak coverage sampling point proportion threshold, marking the cell as a weak coverage cell, and indicating that the network coverage problem which is most required to be optimized in the cell is the weak coverage problem.

(3) Signal to noise ratio quality difference

The signal-to-noise ratio quality difference of the cell is determined according to the ratio between the number of signal-to-noise ratio quality difference sampling points in the cell and the total number of sampling points of the cell.

Illustratively, the signal-to-noise quality difference γ of a cell may be expressed as the following formula (8):

In some embodiments, the snr quality difference sampling point is a sampling point where the measured snr of the cell is less than or equal to the snr quality difference threshold.

If the number of the signal-to-noise ratio quality difference sampling points is not smaller than the signal-to-noise ratio quality difference sampling point threshold and the ratio of the signal-to-noise ratio quality difference sampling points is not smaller than the signal-to-noise ratio quality difference sampling point ratio threshold, marking the cell as the signal-to-noise ratio quality difference cell, and indicating that the network coverage problem which is most required to be optimized in the cell is the signal-to-noise ratio quality difference problem.

In some embodiments, the signal-to-noise ratio of the serving cell of the sampling point may be obtained by an offline calculation. Illustratively, the UE SINR calculation method may be expressed as the following equation (9):

Wherein the white noise power may be determined to be-125 dBm based on a noise figure of a user equipment (User Experience, UE) receiver. Furthermore, RSRP needs to be converted into a linear value before calculation.

In addition, the SINR calculation needs to be protected by maximum/minimum value, and the value range can be set as SINR epsilon-20 dBm and 40dBm. ]

(4) Coverage of the area of hand-off

Wherein the cell coverage is determined from the ratio between the cell coverage sampling points and the total number of sampling points of the cell.

Illustratively, the cell's coverage phi may be expressed as the following equation (10):

In some embodiments, the coverage sample point is a sample point that is outside the planned coverage area of the cell and where the signal quality of the cell is measured to be greater than a fifth signal quality threshold.

The location information may be a latitude and longitude location of each cell. Can be determined in public parameter information of each cell.

S402, clustering the cells according to coverage problem attribute parameters and position information of each cell in the cells to obtain one or more cell clusters to be optimized.

In some embodiments, density-based noise application spatial clustering (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) may be employed to cluster multiple cells. The clustering method can define clusters as the largest set of points connected in density, can divide a region with a sufficiently high density into clusters, and can find clusters of arbitrary shape in a noisy spatial database.

Wherein, DBSCAN needs to determine the E neighborhood and the core object.

E neighborhood: the region within the given object radius of the E is called the E neighborhood of the object, the neighborhood radius can be expressed as Eps, and the neighborhood radius can be preset radius values which are manually set or determined in other possible manners.

Core object: if the number of the sample points in the neighborhood of the given object E is greater than or equal to MinPts, the object is called as a core object. Wherein MinPts may be manually set or otherwise determined.

Step 1, inputting data: cell problem attribute dataset D, minPts and Eps.

Step 2, defining a core sample, a boundary sample and a noise sample.

Specifically, a sampling point having a number of sampling points in the neighborhood greater than MinPts may be defined as a core sample. The sampling points in the neighborhood with the number of sampling points smaller than MinPts are defined as boundary samples. Samples that do not belong within the neighborhood of any core samples are defined as noise samples.

And 3, marking all sample points as non-accessed states, randomly selecting one non-accessed sample p, and marking the non-accessed sample p as an accessed state.

In some embodiments, it may be determined that sample p has at least MinPts samples in its E neighborhood.

If there are at least MinPts samples in the E-neighborhood of sample p, then the following step 4 is performed.

Otherwise, if the e neighborhood of the sample p has no MinPts samples, the following step 5 is performed.

And 4, creating a new cluster C, and adding p to the C. Traversing all samples p ' of a sample set in an E neighborhood with N being p, and adding the objects to N if p ' is not accessed and the E neighborhood of p ' has at least MinPts samples; if p 'is not yet a member of any cluster, p' is added to C.

And 5, marking the sample p as a noise sample.

And 6, traversing all the objects until no object marked as an unaccessed state exists.

In this way, one or more problem area clustering clusters (i.e. cell clusters to be optimized) based on the coverage problem density are obtained, and the network coverage optimization method can take the clusters as basic optimization units.

In some embodiments, other possible clustering methods besides the DBSCAN clustering algorithm may be employed, such as, but not limited to, K-means clustering (Kmeans) algorithm.

In the embodiment of the application, a plurality of cells which have coverage problems and are adjacent in geographic position can be divided into the same cell cluster to be optimized by a clustering method, so that the coverage problems of the cell cluster to be optimized can be optimized by adopting a multi-objective optimization algorithm in the follow-up process, and the optimization efficiency is improved.

It will be appreciated that the electronic device, in order to achieve the above-described functions, includes corresponding hardware structures and/or software modules that perform the respective functions. Those skilled in the art will readily appreciate that the algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the application can divide the functional modules of the electronic device according to the embodiment of the method, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one functional module. The integrated modules may be implemented in hardware or software. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation. The following description will take an example of dividing each function module into corresponding functions.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device may execute the network coverage optimization method provided by the foregoing method embodiment. As shown in fig. 8, the electronic device 800 includes an acquisition module 801 and a processing module 802.

The acquiring module 801 is configured to acquire initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized, and measurement information of a plurality of terminals in the cell cluster to be optimized.

And a processing module 802, configured to solve a multi-objective optimization problem related to network coverage by using a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals, so as to obtain a non-dominant solution set, where one non-dominant solution in the non-dominant solution set is used to indicate target values of antenna parameters of the plurality of cells in the cell cluster to be optimized.

The processing module 802 is further configured to select a non-dominant solution from the non-dominant solution set, and set antenna parameters of a plurality of cells in the cell cluster to be optimized based on the selected non-dominant solution.

In some embodiments, the above-described multi-objective optimization problem is determined from a plurality of the following objective functions: an objective function with minimized overlap coverage as an optimization objective; an objective function with minimized weak coverage as an optimization objective; taking the minimum signal-to-noise ratio quality difference as an objective function of an optimization target; an objective function with minimized handoff coverage as an optimization objective; an objective function with maximized signal-to-noise ratio as an optimization target; an objective function with maximized signal quality as an optimization target; taking the maximized signal-to-dry ratio as an objective function of an optimization target; an objective function with the maximized transmission rate as an optimization target; and taking the maximized split ratio as an objective function of the optimization target, wherein the split ratio is used for representing the ratio between the flow of the target service and the flow of all the services.

In some embodiments, the processing module 802 is specifically configured to: solving a multi-objective optimization problem based on a multi-objective optimization algorithm of decomposition based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals to obtain a non-dominant solution set; the decomposition dimension of the decomposition-based multi-objective optimization algorithm is determined according to the number of cells contained in the cell cluster to be optimized and the number of objective functions related to the multi-objective optimization problem.

In some embodiments, the processing module 802 is specifically configured to: decomposing the multi-objective optimization problem into a plurality of single-objective sub-problems, and configuring a corresponding population for each single-objective sub-problem in the plurality of single-objective sub-problems; and carrying out iterative optimization on the population corresponding to each single-target sub-problem in the plurality of single-target sub-problems based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized, measurement information of a plurality of terminals and an aggregation function of a decomposition-based multi-target optimization algorithm until an iteration stopping condition is met, and stopping and outputting a non-dominant solution set.

In some embodiments, the aggregate function of the decomposition-based multi-objective optimization algorithm is determined from an aggregate function of a weight summation method and an aggregate function of chebyshev's method.

In some embodiments, the processing module 802 is specifically configured to: generating offspring individuals in the population corresponding to the single target sub-problem by utilizing a genetic variation mechanism based on the candidate value set of the antenna parameters; determining m objective function values corresponding to child individuals based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized, measurement information of a plurality of terminals and the child individuals; determining an aggregation function value corresponding to the child individual based on m objective function values corresponding to the child individual and an aggregation function of a multi-objective optimization algorithm based on decomposition; judging whether to replace the individuals in the population corresponding to the adjacent sub-problems of the single target sub-problem with the child individuals based on the aggregation function values corresponding to the child individuals; removing solutions of the external population, which are dominated by the child individuals, based on m objective function values corresponding to the child individuals; and, adding the offspring individuals to the outer population without the offspring individuals being dominated by the solution in the outer population; wherein the external population is used to store non-dominant solutions.

In some embodiments, the processing module 802 is specifically configured to: according to initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and child individuals, respectively updating measurement information of a plurality of terminals to obtain updated measurement information of the plurality of terminals; and determining the function values of m objective functions corresponding to the child individuals according to the updated measurement information of the plurality of terminals.

In some embodiments, the measurement information of the terminal includes signal quality of a plurality of cells in the cell cluster to be optimized; the updated measurement information of the terminal includes updated signal quality of a plurality of cells in the cell cluster to be optimized.

In some embodiments, for measurement information of each terminal, the signal quality of the target cell in the cell cluster to be optimized is updated by: determining initial antenna gain corresponding to a target cell according to an initial value of an antenna parameter of the target cell; determining a target antenna gain corresponding to a target cell according to a target value of an antenna parameter of the target cell indicated by the child individual; and determining the updated signal quality of the target cell according to the signal quality of the target cell, the initial antenna gain corresponding to the target cell and the target antenna gain corresponding to the target cell.

In some embodiments, the antenna parameters include at least one of azimuth, downtilt, horizontal bandwidth, and vertical bandwidth.

In some embodiments, the processing module 802 is further to: acquiring coverage problem attribute parameters and position information of each cell in a plurality of cells, wherein the coverage problem attribute parameters of the cells are used for representing the severity of network coverage problems existing in the cells; and clustering the cells according to the coverage problem attribute parameters and the position information of each cell in the cells to obtain one or more cell clusters to be optimized.

In some embodiments, the overlap coverage of a cell is determined from a ratio between the number of duplicate coverage samples in the cell and the total number of samples in the cell; wherein, the repeated cover sampling point is a sampling point satisfying the following conditions: the measured signal quality of the cell is greater than or equal to a first signal quality threshold; the measured signal quality of the neighbor cell of the cell is greater than or equal to a second signal quality threshold; and the difference between the measured signal quality of the cell and the measured signal quality of a neighbor cell of the cell is greater than or equal to a third signal quality threshold.

In some embodiments, the weak coverage of the cell is determined from a ratio between the number of weak coverage sampling points in the cell and the total number of sampling points of the cell; the weak coverage sampling point is a sampling point of which the measured signal quality of the cell is smaller than or equal to a fourth signal quality threshold.

In some embodiments, the signal-to-noise ratio quality of the cell is determined from a ratio between a number of signal-to-noise ratio quality difference sampling points in the cell and a total number of sampling points of the cell; the signal-to-noise ratio quality difference sampling point is a sampling point of which the signal-to-noise ratio of the measured cell is smaller than or equal to the signal-to-noise ratio quality difference threshold.

In some embodiments, the coverage of a cell is determined from a ratio between a cell's coverage sampling points and the total number of sampling points of the cell; the coverage sampling point is a sampling point which is located outside the planned coverage of the cell and is used for measuring the signal quality of the cell to be larger than a fifth signal quality threshold.

In the case of implementing the functions of the integrated modules in the form of hardware, the embodiment of the application provides a schematic structural diagram of the electronic device. As shown in fig. 9, the electronic device 900 includes: a processor 902, a bus 904. In some embodiments, the electronic device may also include memory 901. In some embodiments, the electronic device may also include a communication interface 903.

The processor 902 may be any logic block, module, or circuitry that implements or performs various examples described in connection with embodiments of the application. The processor 902 may be a central processor, general purpose processor, digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with embodiments of the application. The processor 902 may also be a combination that performs computing functions, e.g., including one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

A communication interface 903 for connecting to other devices via a communication network. The communication network may be an ethernet, a radio access network, a wireless local area network (wireless local area networks, WLAN), etc.

The memory 901 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-only memory, EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

As a possible implementation, the memory 901 may exist separately from the processor 902, and the memory 901 may be connected to the processor 902 through the bus 904 for storing instructions or program code. The processor 902, when calling and executing instructions or program code stored in the memory 901, is capable of implementing the network coverage optimization method provided by the embodiment of the present application.

In another possible implementation, the memory 901 may also be integrated with the processor 902.

Bus 904, which may be an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus 904 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.

Some embodiments of the present application provide a computer readable storage medium (e.g., a non-transitory computer readable storage medium) having stored therein computer program instructions which, when run on a computer, cause the computer to perform a network coverage optimization method as described in any of the above embodiments.

By way of example, the computer-readable storage media described above can include, but are not limited to: magnetic storage devices (e.g., hard Disk, floppy Disk or tape, etc.), optical disks (e.g., compact Disk (CD), digital versatile Disk (DIGITAL VERSATILE DISK, DVD), etc.), smart cards, and flash Memory devices (e.g., erasable programmable read-Only Memory (EPROM), card, stick, or key drive, etc.). Various computer-readable storage media described herein can represent one or more devices and/or other machine-readable storage media for storing information. The term "machine-readable storage medium" can include, without being limited to, wireless channels and various other media capable of storing, containing, and/or carrying instruction(s) and/or data.

An embodiment of the present application provides a computer program product containing instructions, which when run on a computer, cause the computer to perform the network coverage optimization method according to any of the above embodiments.

The foregoing is merely illustrative of specific embodiments of the present application, and the scope of the present application is not limited thereto, but any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for optimizing network coverage, the method comprising:

acquiring initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of a plurality of terminals in the cell cluster to be optimized;

Solving a multi-objective optimization problem related to network coverage by a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in a cell cluster to be optimized and measurement information of the plurality of terminals to obtain a non-dominant solution set, wherein the non-dominant solution set comprises one or more non-dominant solutions, and the non-dominant solutions are used for indicating target values of the antenna parameters of the plurality of cells in the cell cluster to be optimized;

And selecting a target non-dominant solution from the non-dominant solution set, and setting antenna parameters of a plurality of cells in the cell cluster to be optimized based on the target non-dominant solution.

2. The method of claim 1, wherein the multi-objective optimization problem is determined from a plurality of the following objective functions:

an objective function with maximized signal quality as an optimization target;

And taking the maximized split ratio as an objective function of the optimization target, wherein the split ratio is used for representing the ratio between the flow of the target service and the flow of all the services.

3. The method according to claim 1, wherein the solving the network coverage related multi-objective optimization problem with a multi-objective optimization algorithm based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of the plurality of terminals to obtain a non-dominant solution set includes:

solving the multi-objective optimization problem based on a multi-objective optimization algorithm of decomposition based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized and measurement information of a plurality of terminals to obtain the non-dominant solution set; the decomposition dimension of the decomposition-based multi-objective optimization algorithm is determined according to the number of cells contained in the cell cluster to be optimized and the number of objective functions related to the multi-objective optimization problem.

4. The method of claim 3, wherein the solving the multi-objective optimization problem based on the decomposed multi-objective optimization algorithm based on the initial values of the antenna parameters of the plurality of cells in the cell cluster to be optimized and the measurement information of the plurality of terminals to obtain the non-dominant solution set comprises:

decomposing the multi-objective optimization problem into a plurality of single-objective sub-problems, and configuring a corresponding population for each single-objective sub-problem in the plurality of single-objective sub-problems;

And carrying out iterative optimization on the population corresponding to each single-target sub-problem in the plurality of single-target sub-problems based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized, measurement information of a plurality of terminals and an aggregation function of the decomposition-based multi-target optimization algorithm until the non-dominant solution set is stopped and output when the iterative stopping condition is met.

5. The method of claim 4, wherein the aggregate function of the decomposition-based multi-objective optimization algorithm is determined from an aggregate function of a weight summation method and an aggregate function of chebyshev's method.

6. The method of claim 4 or 5, wherein the iterative optimization process of the population corresponding to the single target sub-problem comprises:

Generating offspring individuals in the population corresponding to the single target sub-problem by utilizing a genetic variation mechanism based on the candidate value set of the antenna parameter;

Determining m objective function values corresponding to the child individuals based on initial values of antenna parameters of a plurality of cells in the cell cluster to be optimized, measurement information of the plurality of terminals and the child individuals;

determining an aggregation function value corresponding to the child individual based on m objective function values corresponding to the child individual and an aggregation function of the decomposition-based multi-objective optimization algorithm;

Judging whether to replace the individual in the population corresponding to the adjacent sub-problem of the single target sub-problem with the child individual based on the aggregation function value corresponding to the child individual;

Removing solutions of the external population, which are dominated by the child individuals, based on m objective function values corresponding to the child individuals; and adding the child individuals to the outer population without the child individuals being dominated by the solution in the outer population; wherein the external population is used to store non-dominant solutions.

7. The method according to claim 6, wherein the determining the function values of the m objective functions corresponding to the child individuals based on the initial values of the antenna parameters of the plurality of cells in the cell cluster to be optimized, the measurement information of the plurality of terminals, and the child individuals includes:

respectively updating the measurement information of the plurality of terminals according to the initial values of the antenna parameters of the plurality of cells in the cell cluster to be optimized and the child individuals to obtain updated measurement information of the plurality of terminals;

And determining the function values of m objective functions corresponding to the child individuals according to the updated measurement information of the plurality of terminals.

8. The method of claim 7, wherein the step of determining the position of the probe is performed,

The measurement information of the terminal comprises signal quality of a plurality of cells in the cell cluster to be optimized;

9. The method according to claim 8, characterized in that for the measurement information of each terminal, the signal quality of the target cell in the cluster of cells to be optimized is updated by:

determining initial antenna gain corresponding to the target cell according to the initial value of the antenna parameter of the target cell;

determining a target antenna gain corresponding to the target cell according to a target value of an antenna parameter of the target cell indicated by the child individual;

And determining the updated signal quality of the target cell according to the signal quality of the target cell, the initial antenna gain corresponding to the target cell and the target antenna gain corresponding to the target cell.

10. The method of claim 1, wherein the antenna parameters include at least one of azimuth, downtilt, horizontal bandwidth, and vertical bandwidth.

11. The method according to claim 1, wherein the method further comprises:

Acquiring coverage problem attribute parameters and position information of each cell in a plurality of cells, wherein the coverage problem attribute parameters of the cells are used for representing the severity of network coverage problems existing in the cells;

And clustering the cells according to the coverage problem attribute parameters and the position information of each cell in the cells to obtain one or more cell clusters to be optimized.

12. The method of claim 11, wherein the coverage problem attribute parameter of the cell is determined based on at least one of overlap coverage, weak coverage, signal to noise ratio quality differential, and handover coverage of the cell.

13. The method of claim 12, wherein the overlap coverage of the cell is determined from a ratio between the number of duplicate cover samples in the cell and the total number of samples in the cell; wherein, the repeated cover sampling point is a sampling point meeting the following conditions:

14. The method of claim 12, wherein the weak coverage of the cell is determined from a ratio between a number of weak coverage samples in the cell and a total number of samples of the cell; the weak coverage sampling point is a sampling point of which the measured signal quality of the cell is smaller than or equal to a fourth signal quality threshold.

15. The method of claim 12, wherein the signal-to-noise ratio quality of the cell is determined from a ratio between a number of signal-to-noise ratio quality difference sampling points in the cell and a total number of sampling points of the cell; and the signal-to-noise ratio quality difference sampling point is a sampling point of which the measured signal-to-noise ratio of the cell is smaller than or equal to a signal-to-noise ratio quality difference threshold.

16. The method of claim 12, wherein the cell coverage is determined from a ratio between a cell's coverage sampling point and a total number of sampling points for the cell; the cross-region coverage sampling point is a sampling point which is located outside the planned coverage range of the cell and is used for measuring the signal quality of the cell to be larger than a fifth signal quality threshold.

17. An electronic device, comprising: a processor and a memory for storing instructions executable by the processor;

wherein the processor is configured to execute the instructions to cause the electronic device to perform the method of any one of claims 1-16.

18. A computer readable storage medium having stored thereon computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any of claims 1-16.