A large quantity of access point device deployment method based on check swarm

Abstract

The application provides a large quantity of access point device deployment method based on check bee colony, S1, an initial deployment scheme is generated according to the obtained individual deployment position and individual access point device in combination with expert knowledge; S2, according to the initial deployment scheme, an improved neighborhood optimization module is respectively called in the stages of the employed bee and the follower bee, neighborhood optimization processing is carried out, and in combination with the processing in the scout bee stage, an improved deployment scheme is obtained; S3, the improved deployment scheme is checked in combination with position characteristics, and the optimal initial deployment scheme is obtained and expressed as; the position characteristics include natural factors such as topography, climate and vegetation and human factors such as city planning and building distribution. The application introduces expert knowledge to optimize the random initial scheme, carries out neighborhood optimization processing through the improved neighborhood optimization module, and finally checks the deployment scheme through the position characteristics.

Description

Technical Field

[0001] This invention belongs to the field of communication technology, specifically relating to a method for deploying a large number of access point devices based on a verification bee colony. Background Technology

[0002] In modern wireless communication systems, access point equipment deployment is a crucial component. Access point equipment location optimization aims to rationally plan the deployment locations of access point equipment using technological means, based on specific user needs and deployment environments, to ensure wireless network signal coverage, communication quality, and user experience.

[0003] Optimizing access point deployment locations is essentially a constrained combinatorial optimization problem, a classic nondeterministic polynomial problem. Algorithms such as artificial bee colony optimization and ant colony optimization are commonly used to find the optimal solution. Because user mobility and traffic distribution are constantly changing, an optimal access point deployment scheme needs to be determined within a very short time. However, when there are many deployment locations and types of access points, the time required for traditional optimization algorithms to find the optimal solution increases significantly, and it may even become unsolvable. Therefore, in optimizing access point deployment locations, incorporating expert knowledge and location characteristics into the initialization scheme can significantly reduce the optimization time of traditional algorithms, increase the wireless network signal coverage, and improve user communication quality. Furthermore, it can reduce construction costs and increase operational revenue. Summary of the Invention

[0004] The purpose of this invention is to provide a method for deploying a large number of access point devices based on a verification bee colony. This method introduces expert knowledge to optimize the random initialization scheme, performs neighborhood optimization through an improved neighborhood optimization module, and finally verifies the deployment scheme through location features.

[0005] The specific invention solution is as follows:

[0006] A method for deploying a large number of access point devices based on a verification bee colony includes the following steps:

[0007] S1, based on the obtained Deployment locations and Each access point device, combined with expert knowledge, generates an initial deployment plan. ;

[0008] The aforementioned The set consisting of deployment locations is represented as This is called the deployment location set, where, Indicates the first One deployment location, , Each element in the table corresponds to a location's latitude, longitude, and altitude; adjacent elements represent adjacent geographical locations.

[0009] The Each access point device consists of The access point devices are composed of, and are represented by their numbers as follows: That is, the access point device number The 1st to element This represents the first type of access point equipment, and so on; among them, , Indicates the first The number of access point devices and ;

[0010] The expert knowledge includes terrain and environmental factors, user needs and behaviors, investment costs and returns, technical standards and specifications, as well as competitive situation and market demand, and the expert's prior information on whether access point equipment can be deployed in a certain area.

[0011] S2, according to the initial deployment plan The improved neighborhood optimization module is invoked during both the mercenary bee and follower bee phases to perform neighborhood optimization processing. Combined with the processing during the scout bee phase, an improved deployment scheme is obtained. ;

[0012] S3. Improved deployment scheme based on location characteristics The optimal initial deployment scheme is obtained through verification, and is represented as follows: ;

[0013] The location features include natural factors such as topography, climate, and vegetation, as well as human factors such as urban planning and building distribution.

[0014] In some specific implementations, step S1, which involves generating an initial deployment scheme by incorporating expert knowledge, includes the following sub-steps:

[0015] S11, Initialize the number of iterations ;

[0016] S12, From deployment location set Random selection The deployment location forms the first The actual deployment location set of the next iteration ,in, , ;

[0017] S13, in the selected The first The actual deployment location of the next iteration Access point devices are placed on top respectively. , , forming the first Random deployment scheme in the next iteration ,in, Indicates the deployment location The access point device number deployed is The equipment;

[0018] S14, according to the... The actual deployment location of the next iteration Read the first The set of access point device type constraints for the next iteration ;

[0019] The set of access point device types Generated by expert knowledge extraction, used to identify whether a certain type of access point device is suitable for placement in a certain deployment location;

[0020] The first The set of device type constraints for the next iteration Represented as ,in , Indicates the deployment location The first should not be deployed. Access point devices;

[0021] It is worth noting that when At this time, it indicates the deployment location. Any type of access point device can be deployed here;

[0022] S5, Determine the first Random deployment scheme in the next iteration Does the constraint set satisfy? If the condition is met, execute S16; otherwise, execute S17 and S18.

[0023] S16. Initial Deployment Plan That is, the initial deployment plan Take the first Random deployment scheme in the next iteration ;

[0024] S17, Number of Update Iterations ;

[0025] S18. Determine the number of iterations. If true, return to execute S12, S13, S14, and S15; otherwise, execute S19.

[0026] S19. Initial Deployment Plan That is, the initial deployment plan Take the last random deployment plan ;

[0027] Maximum number of iterations Based on engineering experience.

[0028] In some specific implementations, the improved neighborhood optimization module in step S2 includes the following sub-steps in the hired bee and follower bee steps:

[0029] S21. Generate two unequal random numbers. and ;

[0030] S22. According to the initial deployment plan ,when and If the condition is met, proceed to step S23; otherwise, return to step S21.

[0031] S23. Based on random numbers and Initial deployment plan With deployment location set , position and By switching the access point device types deployed on top, an improved deployment scheme is obtained. .

[0032] In some specific implementations, the verification of the improved deployment scheme based on location features in step S3 includes the following sub-steps:

[0033] S31. Initialize the number of iterations ;

[0034] S32, Based on the improved deployment plan actual deployment location set , Read the first The set of position constraints for the next iteration ;

[0035] The set of position constraints Generated by extracting features from the corresponding deployment location, used to identify whether the location is suitable for deploying access point devices;

[0036] The set of position constraints Represented as ,in, , , Indicates the deployment location This location is suitable for deploying access point equipment. This indicates the deployment location. This location is not suitable for deploying access point equipment.

[0037] S33, Determine the Improved Deployment Plan Does it satisfy the first requirement? The set of position constraints for the next iteration If satisfied, execute S38; otherwise, execute S34, S35, S36, and S37.

[0038] S34, Calculate the first The set of remaining deployment locations in the next iteration ;

[0039] S35, Updated and Improved Deployment Plan From the first The set of remaining deployment locations in the next iteration In, randomly select Improved deployment solution for replacing individual deployment locations The set of elements that do not satisfy positional constraints The deployment location, among which, For the first Next-iteration improved deployment scheme The set of elements that do not satisfy positional constraints The number of positions;

[0040] S36, Number of Update Iterations ;

[0041] S37. Determine the number of iterations If the condition is met, return to execute S32 and S33; otherwise, execute S38.

[0042] S38. Optimal Initial Deployment Scheme That is, an improved deployment solution For the optimal initial deployment scheme .

[0043] This invention initializes the deployment scheme based on a set of access point device type constraints constructed from expert prior knowledge, rather than relying entirely on the random initialization of traditional optimization algorithms. On one hand, this initialization scheme, by incorporating expert knowledge, can be considered an optimized deployment scheme; on the other hand, it accelerates the convergence speed of the solution and reduces iteration time. Simultaneously, an improved neighborhood optimization module is invoked during the hired bee and follower bee phases to perform neighborhood optimization processing. Combined with the processing in the scout bee phase, an improved deployment scheme is obtained. Finally, the improved deployment scheme is validated based on location features to obtain the optimal initialization deployment scheme.

[0044] Compared to traditional access point device deployment optimization algorithms, this invention optimizes the random initialization scheme by introducing expert knowledge and a constraint set formed by deployment location features. Simultaneously, an improved neighborhood optimization module is invoked during both the hired bee and follower bee phases to perform neighborhood optimization processing. Therefore, this invention reduces the solution space for traditional optimization algorithms to find the optimal solution, thereby accelerating solution convergence. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the process of the present invention;

[0046] Figure 2 This is a schematic diagram illustrating the process of generating an initial deployment plan using expert knowledge according to the present invention.

[0047] Figure 3 This is a schematic diagram of the process of neighborhood optimization performed by the improved neighborhood optimization module of the present invention;

[0048] Figure 4 This is a schematic diagram illustrating the process of verifying the improved deployment scheme using location features according to the present invention. Detailed Implementation

[0049] The present invention will now be described in detail with reference to the embodiments and accompanying drawings. However, it should be understood that the embodiments and drawings are for illustrative purposes only and do not constitute any limitation on the scope of protection of the present invention. All reasonable modifications and combinations included within the scope of the inventive spirit of the present invention fall within the scope of protection of the present invention.

[0050] like Figure 1 As shown, a method for deploying a large number of access point devices based on a verification bee colony includes:

[0051] S1, based on the obtained Deployment locations and Each access point device, combined with expert knowledge, generates an initial deployment plan. ;

[0052] The aforementioned The set consisting of deployment locations is represented as This is called the deployment location set, where, Indicates the first One deployment location, , Each element in the table corresponds to a location's latitude, longitude, and altitude; adjacent elements represent adjacent geographical locations.

[0053] The Each access point device consists of The access point devices are composed of [types of] devices, represented by their numbers as follows: That is, the access point device number The 1st to element This represents the first type of access point equipment, and so on; among them, , Indicates the first The number of access point devices and ;

[0054] The expert knowledge includes terrain and environmental factors, user needs and behaviors, investment costs and returns, technical standards and specifications, as well as competitive situation and market demand, and the expert's prior information on whether access point equipment can be deployed in a certain area.

[0055] like Figure 2 As shown, in an embodiment of the present invention, step S1 specifically includes:

[0056] S11, Initialize the number of iterations ;

[0057] S12, From deployment location set Random selection The deployment location forms the first The actual deployment location set of the next iteration ,in, , ;

[0058] S13, in the selected The first The actual deployment location of the next iteration Access point devices are placed on top respectively. , , forming the first Random deployment scheme in the next iteration ,in, Indicates the deployment location The access point device number deployed is The equipment;

[0059] S14, according to the... The actual deployment location of the next iteration Read the first The set of access point device type constraints for the next iteration ;

[0060] The set of access point device types Generated by expert knowledge extraction, used to identify whether a certain type of access point device is suitable for placement in a certain deployment location;

[0061] The first The set of device type constraints for the next iteration Represented as ,in , Indicates the deployment location The first should not be deployed. Access point devices;

[0062] It is worth noting that when At this time, it indicates the deployment location. Any type of access point device can be deployed here;

[0063] S15, Determine the first Random deployment scheme in the next iteration Does the constraint set satisfy? If the condition is met, execute S16; otherwise, execute S17 and S18.

[0064] S16. Initial Deployment Plan That is, the initial deployment plan Take the first Random deployment scheme in the next iteration ;

[0065] S17, Number of Update Iterations ;

[0066] S18. Determine the number of iterations. If the condition is met, proceed to steps S12, S13, S14, and S15; otherwise, proceed to step S19.

[0067] S19. Initial Deployment Plan That is, the initial deployment plan Take the last random deployment plan ;

[0068] Maximum number of iterations Based on engineering experience;

[0069] S2, according to the initial deployment plan The improved neighborhood optimization module is invoked during both the mercenary bee and follower bee phases to perform neighborhood optimization processing. Combined with the processing during the scout bee phase, an improved deployment scheme is obtained. ;

[0070] like Figure 3 As shown, in an embodiment of the present invention, step S2 specifically includes:

[0071] S21. Generate two unequal random numbers. and ;

[0072] S22. According to the initial deployment plan ,when and If the condition is met, proceed to step S23; otherwise, return to step S21.

[0073] S23. Based on random numbers and Initial deployment plan With deployment location set , position and By switching the access point device types deployed on top, an improved deployment scheme is obtained. ;

[0074] S3. Improved deployment scheme based on location characteristics The optimal initial deployment scheme is obtained through verification, and is represented as follows: ;

[0075] The location features include natural factors such as topography, climate, and vegetation, as well as human factors such as urban planning and building distribution.

[0076] like Figure 4 As shown, in an embodiment of the present invention, step S3 specifically includes:

[0077] S31. Initialize the number of iterations ;

[0078] S32, Based on the improved deployment plan actual deployment location set , Read the first The set of position constraints for the next iteration ;

[0079] The set of position constraints Generated by extracting features from the corresponding deployment location, used to identify whether the location is suitable for deploying access point devices;

[0080] The set of position constraints Represented as ,in, , , Indicates the deployment location This location is suitable for deploying access point equipment. This indicates the deployment location. This location is not suitable for deploying access point equipment.

[0081] S33, Determine the Improved Deployment Plan Does it satisfy the first requirement? The set of position constraints for the next iteration If satisfied, execute S38; otherwise, execute S34, S35, S36, and S37.

[0082] S34, Calculate the first The set of remaining deployment locations in the next iteration ;

[0083] S35, Updated and Improved Deployment Plan From the first The set of remaining deployment locations in the next iteration In, randomly select Improved deployment solution for replacing individual deployment locations The set of elements that do not satisfy positional constraints The deployment location, among which, For the first Next-iteration improved deployment scheme The set of elements that do not satisfy positional constraints The number of positions;

[0084] S36, Number of Update Iterations ;

[0085] S37. Determine the number of iterations If the condition is true, return to execute S32 and S33; otherwise, execute S38.

[0086] S38. Optimal Initial Deployment Scheme That is, an improved deployment solution For the optimal initial deployment scheme .

Claims

1. A method for deploying a large number of access point devices based on a verification bee colony, characterized in that, Includes the following steps: S1, based on the obtained Deployment locations and Each access point device, combined with expert knowledge, generates an initial deployment plan. ; The aforementioned The set consisting of deployment locations is represented as This is called the deployment location set, where, Indicates the first One deployment location, , Each element in the table corresponds to a location's latitude, longitude, and altitude; adjacent elements represent adjacent geographical locations. The Each access point device consists of The access point devices are composed of [types of] devices, represented by their numbers as follows: That is, the access point device number The 1st to element This represents the first type of access point equipment, and so on; among them, , Indicates the first The number of access point devices and ; The expert knowledge includes terrain and environmental factors, user needs and behaviors, investment costs and returns, technical standards and specifications, as well as competitive situation and market demand, and the expert's prior information on whether access point equipment can be deployed in a certain area. S2. According to the initial deployment plan The improved neighborhood optimization module is invoked during both the mercenary bee and follower bee phases to perform neighborhood optimization processing. Combined with the processing during the scout bee phase, an improved deployment scheme is obtained. ; Step S2, the improved neighborhood optimization module, includes the following sub-steps in the hired bee and follower bee steps: S21. Generate two unequal random numbers. and ; S22. According to the initial deployment plan ,when and If the condition is met, proceed to step S23; otherwise, return to step S21. S23. Based on random numbers and Initial deployment plan With deployment location set , position and By switching the access point device types deployed on top, an improved deployment scheme is obtained. ; S3. Improved deployment scheme based on location characteristics The optimal initial deployment scheme is obtained through verification, and is represented as follows: ; The location features include natural factors such as topography, climate, and vegetation, as well as human factors such as urban planning and building distribution.

2. The method for deploying a large number of access point devices based on a verification bee colony according to claim 1, characterized in that, The specific requirements of S1 include the following sub-steps: S11, Initialize the number of iterations ; S12, From deployment location set Random selection The deployment location forms the first The actual deployment location set of the next iteration ,in, , ; S13, in the selected The first The actual deployment location of the next iteration Access point devices are placed on top respectively. , , forming the first Random deployment scheme in the next iteration ,in, Indicates the deployment location The access point device number deployed is The equipment; S14, according to the... The actual deployment location of the next iteration Read the first The set of access point device type constraints for the next iteration ; The set of access point device types Generated by expert knowledge extraction, used to identify whether a certain type of access point device is suitable for placement in a certain deployment location; The first The set of device type constraints for the next iteration Represented as ,in , Indicates the deployment location The first should not be deployed. Access point devices; when At this time, it indicates the deployment location. Any type of access point device can be deployed there; S15, Determine the first Random deployment scheme in the next iteration Does the constraint set satisfy? If the condition is met, execute S16; otherwise, execute S17 and S18. S16. Initial Deployment Plan That is, the initial deployment plan Take the first Random deployment scheme in the next iteration ; S17, Number of Update Iterations ; S18. Determine the number of iterations. If the condition is met, proceed to steps S12, S13, S14, and S15; otherwise, proceed to step S19. S19. Initial Deployment Plan That is, the initial deployment plan Take the last random deployment plan ; Maximum number of iterations Based on engineering experience.

3. The method for deploying a large number of access point devices based on a verification bee colony according to claim 2, characterized in that, Step S3 specifically requires the following sub-steps: S31. Initialize the number of iterations ; S32, Based on the improved deployment plan actual deployment location set , Read the first The set of position constraints for the next iteration ; The set of position constraints Generated by extracting features from the corresponding deployment location, used to identify whether the location is suitable for deploying access point devices; The set of position constraints Represented as ,in, , , Indicates the deployment location This location is suitable for deploying access point equipment. This indicates the deployment location. This location is not suitable for deploying access point equipment. S33, Determine the Improved Deployment Plan Does it satisfy the first requirement? The set of position constraints for the next iteration If satisfied, execute S38; otherwise, execute S34, S35, S36, and S37. S34, Calculate the first The set of remaining deployment locations in the next iteration ; S35, Updated and Improved Deployment Plan From the first The set of remaining deployment locations in the next iteration In, randomly select Improved deployment solution for replacing individual deployment locations The set of elements that do not satisfy positional constraints The deployment location, among which, For the first Next-iteration improved deployment scheme The set of elements that do not satisfy positional constraints The number of positions; S36, Number of Update Iterations ; S37. Determine the number of iterations If the condition is true, return to execute S32 and S33; otherwise, execute S38. S38. Optimal Initial Deployment Scheme That is, an improved deployment solution For the optimal initial deployment scheme .

Images