Edge server deployment method, device, computer equipment and storage medium

Abstract

The present application relates to an edge server deployment method, device, computer equipment and storage medium. The method comprises: obtaining a reference deployment scheme set and a standard deployment scheme set of edge servers; for each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated; generating a derivative deployment scheme according to the deployment status of edge servers in different base stations in the deployment scheme to be updated; controlling the update of the standard deployment scheme set according to the size relationship between each evaluation index of the derivative deployment scheme and each evaluation index corresponding to each standard deployment scheme; when the current number of iterations reaches the preset number of iterations, generating a target deployment scheme set for the edge server according to the standard deployment scheme set under the current number of iterations. The use of this method improves the accuracy of server deployment.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an edge server deployment method, apparatus, computer equipment and storage medium. Background Art

[0002] With the development of computer technology, edge servers have emerged. The location of edge servers determines the response time of edge servers. Therefore, how to choose a suitable location for edge servers is crucial.

[0003] In traditional technologies, due to the distribution of edge server resources and the differences in loads of different servers, many factors need to be considered when deploying edge servers, so existing edge server deployment is usually based on previous manual experience.

[0004] Although this method can complete the deployment of edge servers, it is highly subjective, which leads to inaccurate edge server deployment. Summary of the invention

[0005] Based on this, it is necessary to provide an edge server deployment method, apparatus, computer equipment and storage medium that can improve the accuracy of edge server deployment in response to the above technical problems.

[0006] In a first aspect, the present application provides an edge server deployment method, comprising:

[0007] Obtain a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0008] For each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated;

[0009] Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated;

[0010] According to the size relationship between each evaluation index of the derived deployment scheme and each evaluation index corresponding to each standard deployment scheme, the set of standard deployment schemes is controlled and updated;

[0011] When the current number of iterations reaches the preset number of iterations, a target deployment solution set for the edge server is generated according to the standard deployment solution set under the current number of iterations;

[0012] The evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment scheme.

[0013] In one embodiment, when there is only one deployment scheme to be updated, generating a derived deployment scheme according to the deployment status of edge servers in different base stations in the deployment scheme to be updated includes:

[0014] Determine the adjustment difference between the historical adjustment number of the deployment plan to be updated and the preset adjustment number;

[0015] When the adjustment difference is greater than a preset adjustment threshold, the deployment plan to be updated is split into two deployment sub-plans to be updated according to a preset splitting method, and each deployment sub-plan to be updated is extended to obtain a derivative deployment plan corresponding to each deployment sub-plan to be updated;

[0016] When the adjustment difference is not greater than a preset adjustment threshold, the deployment states of the edge servers in different base stations in the deployment scheme to be updated are randomly adjusted.

[0017] In one embodiment, when there are two deployment schemes to be updated, generating a derived deployment scheme according to the deployment status of edge servers in different base stations in the deployment scheme to be updated includes:

[0018] For each deployment plan to be updated, determine the plan kinetic energy value of the deployment plan to be updated;

[0019] When the preset scheme kinetic energy values ​​corresponding to the two deployment schemes to be updated are not greater than the preset kinetic energy threshold, the two deployment schemes to be updated are integrated to obtain a derived deployment scheme;

[0020] If there is a situation where the scheme value corresponding to any deployment scheme to be updated is greater than the preset kinetic energy threshold, the edge server deployment states of the base stations to be updated in the two deployment schemes to be updated are selected for cross-replacement to obtain a derivative deployment scheme corresponding to the deployment scheme to be updated.

[0021] In one embodiment, controlling the updating of the standard deployment solution set according to the magnitude relationship between each evaluation indicator of the derived deployment solution and each evaluation indicator corresponding to each standard deployment solution in the standard deployment solution set includes:

[0022] Determine whether each evaluation index of each standard deployment scheme in the set of standard deployment schemes is less than a corresponding evaluation index of the derived deployment scheme;

[0023] If so, it is prohibited to add the derived deployment scheme to the set of standard deployment schemes;

[0024] If not, the derived deployment solution is added to the standard deployment solution set to update the standard deployment solution set.

[0025] In one embodiment, the standard deployment solution set includes a convergent deployment solution set and a diverse deployment solution set; there is no preset dominance relationship between the standard deployment solutions in the convergent deployment solution set; there is a preset dominance relationship between the standard deployment solutions in the diverse deployment solution set; accordingly, adding the derived deployment solution to the standard deployment solution set to update the standard deployment solution set includes:

[0026] Determine whether there is a standard deployment plan where each evaluation index is not less than the corresponding evaluation index of the derived deployment plan;

[0027] If so, the derived deployment solution is added to the set of standard deployment solutions, and the determined standard deployment solution is deleted;

[0028] If not, the derived deployment solution is added to the diverse deployment solution set.

[0029] In one embodiment, generating a target deployment solution set for the edge server according to a standard deployment solution set at a current iteration number includes:

[0030] Determine the number of standard deployment solutions in the standard deployment solution set under the current iteration number;

[0031] When the number of solutions is not greater than a preset number threshold, the standard deployment solution set is used as the target deployment solution set for the edge server;

[0032] When the number of solutions is greater than a preset number threshold, a target deployment solution set for the edge server is generated according to the distances between the standard deployment solutions in the standard deployment solution set.

[0033] In one embodiment, the set of standard deployment solutions includes a convergent deployment solution set and a diverse deployment solution set; there is no preset dominance relationship between the standard deployment solutions in the convergent deployment solution set; there is a preset dominance relationship between the standard deployment solutions in the diverse deployment solution set; according to the distance between the standard deployment solutions in the standard deployment solution set, generating a target deployment solution set for the edge server includes:

[0034] Selecting the distance between each standard deployment scheme in the diverse deployment scheme set and each convergent deployment scheme in the convergent deployment scheme set;

[0035] According to the distance between each standard deployment solution in the diverse deployment solution set, a preset number of standard deployment solutions are deleted from the diverse deployment solution set to update the diverse deployment solution set;

[0036] A target deployment solution set for the edge server is generated according to the converged deployment solution set and the updated diverse deployment solution set.

[0037] In a second aspect, the present application also provides an edge server deployment device, including:

[0038] A set acquisition module, used to acquire a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0039] A scheme selection module, used for selecting at least one reference deployment scheme from a reference deployment scheme set as a deployment scheme to be updated for each iteration process;

[0040] A solution generation module, used to generate a derivative deployment solution according to the deployment status of the edge servers in different base stations in the deployment solution to be updated;

[0041] A set updating module, used for controlling the updating of the set of standard deployment solutions according to the magnitude relationship between the evaluation indicators of the derived deployment solutions and the corresponding evaluation indicators of the standard deployment solutions;

[0042] A set generation module is used to generate a target deployment solution set for the edge server according to a standard deployment solution set under the current number of iterations when the current number of iterations reaches a preset number of iterations; wherein the evaluation index includes at least one of a delay index, a load index and a quality index of the edge server under the current deployment solution.

[0043] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0044] Obtain a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0045] For each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated;

[0046] Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated;

[0047] According to the size relationship between each evaluation index of the derived deployment scheme and each evaluation index corresponding to each standard deployment scheme, the set of standard deployment schemes is controlled and updated;

[0048] When the current number of iterations reaches the preset number of iterations, a target deployment solution set for the edge server is generated according to the standard deployment solution set under the current number of iterations;

[0049] The evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment scheme.

[0050] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0051] Obtain a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0052] For each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated;

[0053] Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated;

[0054] According to the size relationship between each evaluation index of the derived deployment scheme and each evaluation index corresponding to each standard deployment scheme, the set of standard deployment schemes is controlled and updated;

[0055] When the current number of iterations reaches the preset number of iterations, a target deployment solution set for the edge server is generated according to the standard deployment solution set under the current number of iterations;

[0056] The evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment scheme.

[0057] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0058] Obtain a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0059] For each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated;

[0060] Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated;

[0061] According to the size relationship between each evaluation index of the derived deployment scheme and each evaluation index corresponding to each standard deployment scheme, the set of standard deployment schemes is controlled and updated;

[0062] When the current number of iterations reaches the preset number of iterations, a target deployment solution set for the edge server is generated according to the standard deployment solution set under the current number of iterations;

[0063] The evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment scheme.

[0064] The above-mentioned edge server deployment method, device, computer equipment and storage medium obtain a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution; for each iteration process, at least one reference deployment solution is selected from the reference deployment solution set as the deployment solution to be updated; according to the deployment status of the edge servers in different base stations in the deployment solution to be updated, a derivative deployment solution is generated; according to the size relationship between each evaluation indicator of the derivative deployment solution and each evaluation indicator corresponding to each standard deployment solution, the standard deployment solution set is controlled to be updated; when the current number of iterations reaches the preset number of iterations, a target deployment solution set of the edge server is generated according to the standard deployment solution set under the current number of iterations; wherein the evaluation indicator includes at least one of the delay indicator, load indicator and quality indicator of the edge server under the current deployment solution. In the process of deploying edge servers for different base stations, the embodiment of the present application introduces evaluation indicators, comprehensively considers factors such as the delay, load and quality of the edge server, so that the generated target deployment solution set is more in line with the actual application scenario, thereby improving the rationality and accuracy of the target deployment solution set, and further improving the accuracy of server deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 An application environment diagram of an edge server deployment method provided in this embodiment;

[0067] Figure 2 A schematic diagram of a flow chart of an edge server deployment method provided in this embodiment;

[0068] Figure 3 A schematic diagram for generating the first derivative deployment solution provided in this embodiment;

[0069] Figure 4A schematic diagram for generating a second derivative deployment solution provided in this embodiment;

[0070] Figure 5 A structural block diagram of an edge server deployment device provided in this embodiment;

[0071] Figure 6 This is a diagram of the internal structure of a computer device provided in this embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] The edge server deployment method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The computer device obtains a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution; for each iteration process, at least one reference deployment solution is selected from the reference deployment solution set as the deployment solution to be updated; according to the deployment status of the edge servers in different base stations in the deployment solution to be updated, a derivative deployment solution is generated; according to the size relationship between each evaluation indicator of the derivative deployment solution and each evaluation indicator corresponding to each standard deployment solution, the standard deployment solution set is controlled to be updated; when the current number of iterations reaches the preset number of iterations, the target deployment solution set of the edge server is generated according to the standard deployment solution set under the current number of iterations; wherein the evaluation indicator includes at least one of the delay indicator, load indicator and quality indicator of the edge server under the current deployment solution. Among them, the computer device can be either a terminal or a server. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0074] In an exemplary embodiment, Figure 2 As shown, a method for deploying an edge server is provided, and the method is applied to Figure 1The computer device in the example is used to illustrate, including the following steps 201 to 205. Among them:

[0075] Step 201: Obtain a reference deployment solution set and a standard deployment solution set of an edge server.

[0076] Among them, the edge server is a server to which the base station is to be assigned. The deployment scheme may be a scheme for allocating different base stations to different edge servers for deployment. Both the reference deployment scheme and the standard deployment scheme may be generated by allocation based on the geographical location of the base station and the geographical location of the edge server. The reference deployment scheme set includes at least one reference deployment scheme. The standard deployment scheme set includes at least one standard deployment scheme. The standard deployment scheme in the standard deployment scheme set is the same as some of the reference deployment schemes in the reference deployment scheme set.

[0077] Specifically, obtaining a set of reference deployment plans for the edge server includes: generating a reference deployment plan based on a weighted random initialization strategy according to the geographic location of the base station and the geographic location of the edge server; adding the reference deployment plan to the reference deployment plan set until the number of reference deployment plans in the reference deployment plan set reaches a preset reference deployment plan number threshold, thereby completing the generation of the reference deployment plan set.

[0078] Exemplarily, in the reference deployment scheme, both rows and columns represent base stations, and the order of the numbering of the rows and columns represents the geographical distance of the base stations; for each row in the reference deployment scheme, the location number i of base station i is used as the server allocation reference; a The random number r is randomly selected; the positive or negative decreasing method is randomly selected, and the positions are decreased by |i+r| (if the positive decreasing method is selected, |i+r| positions are decreased in the direction of increasing numbers; if the negative decreasing method is selected, |i+r| positions are decreased in the direction of decreasing numbers); the position number corresponding to the decreasing result is used as the number of the position where the edge server is located; W[i][|i+r|] is marked as 1, indicating that the reference deployment scheme assigns base station i to the edge server where W[i][|i+r|] is located, and the other positions in this row are set to 0, completing the configuration of this row in the reference deployment scheme. As shown in the coding table corresponding to the reference deployment scheme in Table 1 below, if base station i is assigned to the edge server located at the location of base station j, W[i][j] is marked as 1, otherwise it is marked as 0. The third column of the first row in the table (W[1][3]) is marked as 1, indicating that base station No. 1 is assigned to the edge server located at the location of base station No. 3. The second column of the nth row (W[n][2]) is marked as 1, indicating that base station n is assigned to the edge server where base station 2 is located.

[0079] It should be noted that due to the limitations of the edge server deployment problem and the assumption that the edge server is deployed at the base station, the markings in the reference deployment scheme should also follow the following scheme rule constraints: (1) Each row of the scheme must have one mark and at most one mark. (2) If the xth (1≤x≤m)th column has one or more marks, the xth column and the xth row must be marked. Take the coding table corresponding to the reference deployment scheme in Table 1 as an example. Since the W[1][3] position is marked as 1 in the reference deployment scheme, the W[3][3] position mark must be adjusted to 1. The advantage of this setting is that considering that the allocation of base stations to edge nodes is a one-to-many mapping relationship, all base stations are potential placement locations. Traditional binary coding is not convenient for solving the problem, so a two-dimensional matrix is ​​used as the coding scheme. Using such a coding scheme, the edge server location in the scheme is easy to find, the allocation method of the base station is clear, and the constraint violation judgment can be simplified. At the same time, most of the base stations are allocated to nearby edge servers to reduce the extreme situation where the allocated edge servers are very far away, improve the search efficiency of the optimization algorithm, and ensure the diversity of the reference deployment schemes in the reference deployment scheme set.

[0080] Table 1 Reference deployment scheme corresponding coding table

[0081]

[0082] Specifically, the method of obtaining the standard deployment solution set of the edge server may be to randomly generate at least one standard deployment solution according to the geographical location of the base station and the geographical location of the edge server, and combine the standard deployment solutions to obtain the standard deployment solution set. Alternatively, some reference deployment solutions in the reference deployment solution set may be selected as standard deployment solutions, and the standard deployment solutions may be combined to obtain the standard deployment solution set.

[0083] Step 202: For each iteration process, at least one reference deployment solution is selected from a reference deployment solution set as a deployment solution to be updated.

[0084] Specifically, a random number is generated, and the interval of the random number is [0,1]. The relationship between the random number and the preset multi-scheme selection threshold is determined. When the random number is greater than the preset multi-scheme selection threshold, at least two reference deployment schemes are selected from the reference deployment scheme set as the deployment schemes to be updated. When the random number is not greater than the preset multi-scheme selection threshold, a reference deployment scheme is selected from the reference deployment scheme set as the deployment scheme to be updated.

[0085] For example, if the preset multi-scheme selection threshold is set to 0.8. When the generated random number is 0.5, it is determined that the random number is not greater than the preset multi-scheme selection threshold (0.5 < 0.8), and a reference deployment scheme is selected from the reference deployment scheme set as the deployment scheme to be updated; when the generated random number is 0.9, it is determined that the random number is greater than the preset multi-scheme selection threshold (0.9 > 0.8), and two reference deployment schemes are selected from the reference deployment scheme set as the deployment scheme to be updated.

[0086] Step 203: Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated.

[0087] The deployment status is whether the edge server in the base station has been allocated. For example, in the coding table corresponding to the deployment scheme in Table 1 above, if the second column (W[n][2]) in the nth row is marked as 1, it proves that the edge server in base station No. 2 has been deployed, that is, base station No. n is deployed in the edge server where base station No. 2 is located.

[0088] One optional embodiment may be to adjust the deployment status of edge servers in different base stations in the deployment scheme to be updated based on a chemical reaction optimization algorithm (Chemical Reaction Optimization, CRO) to obtain a derived deployment scheme.

[0089] Another optional implementation may be to randomly adjust the deployment status of edge servers in different base stations in the deployment scheme to be updated; select the base stations (base stations corresponding to the rows) that do not meet the scheme rule constraints in the adjusted deployment scheme to be updated, clear the deployment status of the base stations corresponding to the row, and adjust the base stations corresponding to the row to an unallocated state; reallocate the base stations in the unallocated state to obtain a fully allocated deployment scheme to be updated; and use the fully allocated deployment scheme to be updated as a derived deployment scheme.

[0090] Step 204 , controlling the updating of the set of standard deployment solutions according to the magnitude relationship between the evaluation indicators of the derived deployment solutions and the corresponding evaluation indicators of the standard deployment solutions.

[0091] The evaluation index is used to evaluate the quality of the derived deployment solution, and the evaluation index includes at least one of the latency index, load index and quality index of the edge server under the current deployment solution. The quality index is used to measure the comprehensive quality of the deployment solution.

[0092] In one of the optional embodiments, each evaluation indicator of the derived deployment plan and each evaluation indicator of each standard deployment plan are determined; based on the size relationship between each evaluation indicator of the derived deployment plan and each corresponding evaluation indicator of each standard deployment plan, an update method of the standard deployment plan set is determined; based on the update method, the update of the standard deployment plan set is controlled.

[0093] In another optional embodiment, each evaluation indicator of the derived deployment scheme and each evaluation indicator of each standard deployment scheme are determined; it is determined whether each evaluation indicator of each standard deployment scheme in the standard deployment scheme set is smaller than the corresponding evaluation indicator of the derived deployment scheme; if so, it is prohibited to add the derived deployment scheme to the standard deployment scheme set; if not, the derived deployment scheme is added to the standard deployment scheme set to update the standard deployment scheme set.

[0094] For example, if there are two standard deployment schemes in the standard deployment scheme set, the evaluation index 1 of the first standard deployment scheme is 4, the evaluation index 2 is 5, and the evaluation index 3 is 5, then the evaluation indexes of the first standard deployment scheme are marked as (4, 5, 5); the evaluation index 1 of the second standard deployment scheme is 6, the evaluation index 2 is 3, and the evaluation index 3 is 3, then the evaluation indexes of the second standard deployment scheme are marked as (6, 3, 3). Assuming that the evaluation index 1 of the derivative deployment scheme 1 is 7, the evaluation index 2 is 7, and the evaluation index 3 is 7, then the evaluation indexes of the derivative deployment scheme 1 are marked as (7, 7, 7); obviously, the evaluation indexes of the first standard deployment scheme (4, 5, 5) and the evaluation indexes of the second standard deployment scheme (6, 3, 3) are both smaller than the evaluation indexes of the derivative deployment scheme 1 (7, 7, 7), therefore, it is forbidden to add the derivative deployment scheme 1 to the standard deployment scheme set. Assume that the evaluation index 1 of the derived deployment plan 2 is 4, the evaluation index 2 is 4, and the evaluation index 3 is 4, and mark the evaluation indexes of the derived deployment plan 3 as (4, 4, 4); obviously, the evaluation index 1, evaluation index 2 and evaluation index 3 in the first standard deployment plan are not less than the corresponding indicators of the derived deployment plan 2, and the evaluation index 1 in the second standard deployment plan is not less than the corresponding indicator of the derived deployment plan 2. Therefore, the derived deployment plan 2 can be added to the standard deployment plan set to update the standard deployment plan set.

[0095] Exemplary, the method for determining the delay index of the derived deployment solution includes: determining the transmission delay (TD) generated by each edge server in the derived deployment solution processing the request signal sent by the mobile user; taking the average value of the corresponding transmission delays of all edge servers as the delay index of the derived deployment solution. Among them, the transmission delay (TD) includes the user's service request delay to the base station and the delay of the base station forwarding the request to the edge server. Specifically, the delay index can be determined by the following formula (1-1):

[0096] (1-1)

[0097] Among them, ATD represents the delay index, TD represents the transmission delay, b j Base station b j Location, s i For edge servers i location, n represents the total number of transmission delays, and k represents the total number of base stations.

[0098] Exemplary methods for determining the load index of a derived deployment solution include: determining the load value corresponding to the service request processing task of the mobile network device forwarded by all base stations within the coverage area of ​​the edge server in the derived deployment solution; determining the load average value of the load values ​​corresponding to each edge server; determining the load standard deviation based on the load values ​​corresponding to each edge server and the load average value, and using the load standard deviation as the load index of the derived deployment solution. Specifically, the load index can be determined by the following formula (1-2):

[0099] (1-2)

[0100] Among them, LSD represents the load standard deviation, W i Characterizes the load value corresponding to edge server i, represents the load average, and k represents the total number of edge servers.

[0101] Exemplary methods for determining the quality index of a derived deployment solution include: determining a delay normalization result of the transmission delay corresponding to each edge server in the derived deployment solution; determining a load normalization result of the load value corresponding to each edge server in the derived deployment solution; performing weighted summation of the delay normalization result and the load normalization result to obtain the quality index of the derived deployment solution. Specifically, the quality index can be determined by the following formula (1-3):

[0102] (1-3)

[0103] Among them, SC represents the quality index, norm lsd Characterize the load normalization result, normsa td It represents the delay normalization result, and μ represents the weighting coefficient with a value range of [0,1].

[0104] Step 205: When the current number of iterations reaches a preset number of iterations, a target deployment solution set for the edge server is generated according to a standard deployment solution set under the current number of iterations.

[0105] In one of the optional embodiments, when the current number of iterations reaches a preset number of iterations, the standard deployment solution set under the current number of iterations is used as the target deployment solution set of the edge server.

[0106] In one of the optional embodiments, the number of standard deployment solutions in the standard deployment solution set under the current number of iterations is determined; when the number of solutions is not greater than a preset number threshold, the standard deployment solution set is used as a target deployment solution set for the edge server; when the number of solutions is greater than the preset number threshold, a target deployment solution set for the edge server is generated based on the distance between each standard deployment solution in the standard deployment solution set.

[0107] Specifically, the following method is used to generate a target deployment solution set for the edge server according to the distance between each standard deployment solution in the standard deployment solution set: determine the distance between each standard deployment solution in the standard deployment solution set; select a pair of standard deployment solutions with the smallest distance in turn and delete them, and update the standard deployment solution set until the number of standard deployment solutions in the standard deployment solution set is no more than a preset number threshold; and use the standard deployment solution set after the last update as the target deployment solution set for the edge server.

[0108] It should be noted that in this embodiment, the prerequisites for generating the target deployment solution set for the edge server based on the standard deployment solution set under the current number of iterations, in addition to the current number of iterations reaching the preset number of iterations, may also include the central processing unit (CPU) of the computer device reaching the maximum usage time corresponding to the current usage time, the evaluation indicators of the derived deployment solution are all less than the corresponding preset indicator threshold, there is no improvement after executing the preset number of iterations, or any other appropriate prerequisites.

[0109] The above-mentioned edge server deployment method obtains a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution; for each iteration process, at least one reference deployment solution is selected from the reference deployment solution set as the deployment solution to be updated; according to the deployment status of the edge servers in different base stations in the deployment solution to be updated, a derivative deployment solution is generated; according to the size relationship between each evaluation indicator of the derivative deployment solution and each evaluation indicator corresponding to each standard deployment solution, the standard deployment solution set is controlled to be updated; when the current number of iterations reaches the preset number of iterations, a target deployment solution set of the edge server is generated according to the standard deployment solution set under the current number of iterations; wherein the evaluation indicator includes at least one of the delay indicator, load indicator and quality indicator of the edge server under the current deployment solution. In the process of deploying edge servers for different base stations, the embodiment of the present application introduces evaluation indicators, comprehensively considers factors such as the delay, load and quality of the edge server, so that the generated target deployment solution set is more in line with the actual application scenario, thereby improving the rationality and accuracy of the target deployment solution set, and further improving the accuracy of server deployment.

[0110] In one embodiment, when there is only one deployment scheme to be updated, a derived deployment scheme is generated according to the deployment status of edge servers in different base stations in the deployment scheme to be updated, including: determining an adjustment difference between the historical adjustment times of the deployment scheme to be updated and a preset adjustment times; when the adjustment difference is greater than a preset adjustment threshold, splitting the deployment scheme to be updated into two deployment sub-schemes to be updated according to a preset splitting method, and expanding each deployment sub-scheme to be updated to obtain a derived deployment scheme corresponding to each deployment sub-scheme to be updated; when the adjustment difference is not greater than the preset adjustment threshold, randomly adjusting the deployment status of edge servers in different base stations in the deployment scheme to be updated.

[0111] Among them, the historical adjustment coefficient (NumHit) can be the number of iterations experienced by the deployment plan to be updated during the iteration process; the preset adjustment number (MinHit) can be the number of iterations required for the deployment plan to be updated to reach the corresponding preset optimal indicator value corresponding to each evaluation indicator.

[0112] Specifically, the deployment status of edge servers in different base stations in the deployment scheme to be updated is randomly adjusted in the following manner: a row corresponding to any base station in the deployment scheme to be updated is selected as the row to be adjusted; a position near the deployment position of the current edge server in the row to be adjusted is randomly selected as the target position, the deployment status of the target position is adjusted to deployed, the deployment status corresponding to the deployment position of the current edge server is adjusted to undeployed, and the adjusted deployment scheme to be updated is used as the derived deployment scheme.

[0113] For example, Figure 3 The first schematic diagram of generating a derived deployment plan is shown in the figure, where (A) represents the method of generating a derived deployment plan when the adjustment difference is not greater than the preset adjustment threshold, W represents the deployment plan to be updated, W' represents the derived deployment plan, the yellow area in the figure represents the row to be adjusted, and the row corresponding to base station No. 1 in the deployment plan to be updated is randomly selected as the row to be adjusted, and the position W[1][3] near the position W[1][2] (i.e., the edge server deployment position) in the row to be adjusted is randomly selected, and the position is marked as 1, and the position W[1][2] is marked as 0 to obtain the derived deployment plan W'.

[0114] Specifically, the deployment scheme to be updated is split into two deployment sub-schemes to be updated according to a preset splitting method in the following manner, and each deployment sub-scheme to be updated is expanded to obtain a derivative deployment scheme corresponding to each deployment sub-scheme to be updated: the middle position of the deployment scheme to be updated W is selected, and the base station allocation scheme of the first half is reserved as the first half of the first deployment sub-scheme to be updated, and the base station allocation scheme of the second half of the deployment scheme to be updated is reserved as the second half of the second deployment sub-scheme to be updated. For the unallocated schemes of the remaining parts of the first deployment sub-scheme to be updated and the second deployment sub-scheme to be updated, they are generated based on a weighted random initialization strategy, thereby obtaining a derivative deployment scheme W1 corresponding to the first deployment sub-scheme to be updated, and a derivative deployment scheme W2 corresponding to the second deployment sub-scheme to be updated.

[0115] For example, Figure 3 The schematic diagram of generating the first derivative deployment scheme is shown, in which (B) represents the method of generating the derivative deployment scheme when the adjustment difference is greater than the preset adjustment threshold, W represents the deployment scheme to be updated, W1 represents the derivative deployment scheme generated according to the first sub-deployment scheme to be updated, and W2 represents the derivative deployment scheme generated according to the second sub-deployment scheme to be updated. The deployment scheme W to be updated is split to obtain the first deployment sub-scheme to be updated (i.e., the yellow area in W1) and the second deployment sub-scheme to be updated (i.e., the yellow area in W2), the first deployment sub-scheme to be updated is extended to obtain the derivative deployment scheme W1 corresponding to the first deployment sub-scheme to be updated; the second deployment sub-scheme to be updated is extended to obtain the derivative deployment scheme W2 corresponding to the second deployment sub-scheme to be updated.

[0116] In one embodiment, when there are two deployment schemes to be updated, a derived deployment scheme is generated according to the deployment status of edge servers in different base stations in the deployment schemes to be updated, including: determining the scheme kinetic energy value of the deployment scheme to be updated for each deployment scheme to be updated; when the preset scheme kinetic energy values ​​corresponding to the two deployment schemes to be updated are not greater than the preset kinetic energy threshold, the two deployment schemes to be updated are merged to obtain a derived deployment scheme; if there is a case where the preset scheme kinetic energy value corresponding to any deployment scheme to be updated is greater than the preset kinetic energy threshold, the edge server deployment status of the base station to be updated in the two deployment schemes to be updated is selected for cross-replacement to obtain a derived deployment scheme corresponding to the deployment scheme to be updated.

[0117] The scheme kinetic energy value may be an initial kinetic energy value preset during the generation phase of the deployment scheme to be updated.

[0118] Specifically, the edge server deployment states of the base stations to be updated in the two deployment schemes to be updated are selected for cross-replacement in the following manner to obtain a derivative deployment scheme corresponding to the deployment scheme to be updated: two integers n1 and n2 are randomly generated in the interval [1, n] as the numbers of the base station allocation schemes, and n1≠n2, and the allocation schemes between the two numbers in the deployment scheme to be updated are cross-replaced, and the deployment scheme to be updated after the cross-replacement is used as the derivative deployment scheme.

[0119] For example, Figure 4 The schematic diagram of generating the second derived deployment scheme is shown, in which (A) represents the method of generating the derived deployment scheme when there is any deployment scheme to be updated whose corresponding preset scheme kinetic energy value is greater than the preset kinetic energy threshold, W1 represents the first deployment scheme to be updated, W2 represents the second deployment scheme to be updated, base station No. 3 and base station No. 4 are selected, and the first allocation scheme corresponding to base station No. 3 and base station No. 4 is selected from the first deployment scheme to be updated W1 (W1 corresponds to the green area in the figure), and the second allocation scheme corresponding to base station No. 3 and base station No. 4 is selected from the second deployment scheme to be updated W2 (W2 corresponds to the yellow area in the figure), and the first allocation scheme is allocated to the corresponding positions of base station No. 3 and base station No. 4 in the second deployment scheme to be updated (W2' corresponds to the green area in the figure), and the derived deployment scheme W2' is obtained, and the second allocation scheme is allocated to the corresponding positions of base station No. 3 and base station No. 4 in the first deployment scheme to be updated (W1' corresponds to the green area in the figure), and the derived deployment scheme W1' is obtained.

[0120] Specifically, the following method is used to merge the two deployment schemes to be updated to obtain a derived deployment scheme: respectively retain the corresponding allocation schemes of some base stations in the two deployment schemes to be updated, and the base stations retained in the two deployment schemes to be updated are different; merge the corresponding allocation schemes of the reserved base stations to obtain a derived deployment scheme.

[0121] For example, Figure 4 The second derivative deployment scheme generation schematic diagram is shown, in which (A) represents the generation method of the derivative deployment scheme when the preset scheme kinetic energy values ​​corresponding to the two deployment schemes to be updated are not greater than the preset kinetic energy threshold, W1 represents the first deployment scheme to be updated, W2 represents the second deployment scheme to be updated, and the base stations No. 1, No. 2, No. 4 and No. 6 in the first deployment scheme to be updated W1 are retained corresponding to the first allocation scheme (i.e., the green area in W1 in the figure), and the base stations No. 3 and No. 5 in the second deployment scheme to be updated W2 are retained corresponding to the second allocation scheme (i.e., the yellow area in W2 in the figure), and the first allocation scheme and the second allocation scheme are merged to obtain the derived deployment scheme W'.

[0122] It should be noted that in the process of generating a derived deployment plan, the plan rule constraints must also be considered. Therefore, it is necessary to further delete and / or fill some allocation plans in the generated derived deployment plan to eliminate the violation constraints. Specifically, the deletion operation includes: checking the derived deployment plan row by row. If a row that violates the plan rule constraints is found, the allocation plan of the row is cleared; if the deleted allocation number is a number on the diagonal, all allocation marks in the same column are cleared (that is, all marks are 0). This is because the edge server is deleted and its allocation relationship with other base stations will also become invalid. Exemplarily, as shown in the following Table 2, the corresponding coding table of the derived deployment plan, it can be seen from the table that there are two marks of 1 in the third row, which violates the first plan rule constraint, so all marks in the row need to be cleared to 0. At the same time, since the mark corresponding to the position [3,3] in the row is a mark on the diagonal, all marks in the third column need to be cleared to 0.

[0123] Table 2 Corresponding coding table of derived deployment schemes

[0124]

[0125] Specifically, the filling operation includes: checking the allocation scheme of the derived deployment scheme row by row, and finding the row of the base station corresponding to the undeployed edge server; if there is an allocatable edge server near the base station corresponding to the row (i.e., whether there is a mark 1 on the diagonal position of the adjacent base station), then the base station is allocated to the base station corresponding to the undeployed edge server, and the corresponding position of the base station is marked as 1 in the derived deployment scheme; if there is no allocatable edge server nearby, then an edge server is placed at the base station and the corresponding position of the base station is marked as 1 in the derived deployment scheme. Exemplarily, as shown in the above-mentioned derived deployment scheme corresponding coding table in Table 2, it can be seen from the table that no edge server is deployed on base stations 5 and 6, that is, all column marks in rows 5 and 6 are 0; for base station 5, there is an allocatable edge server near base station 5 (i.e., the corresponding position of [4,4] is marked as 1), so the corresponding position of [5,4] can be marked as 1, indicating that base station 5 is allocated to the edge server where base station 4 is located. For base station 6, there is no assignable edge server near base station 6 (that is, the position corresponding to [5,5] is marked as 0), so the position corresponding to [6,6] can be marked as 1, indicating that base station 6 is assigned to the edge server where base station 6 is located.

[0126] In this embodiment, according to the number of selected deployment schemes to be updated, the deployment status of edge servers in different base stations in the deployment scheme to be updated is adjusted accordingly, so as to obtain a derived deployment update scheme, so that the generation of the derived deployment scheme has strong randomness and diversity, improves the richness of the derived deployment scheme, and further improves the accuracy of the generation of the derived deployment scheme, so as to provide a guarantee for the subsequent updating of the standard deployment scheme according to the derived deployment scheme.

[0127] In one embodiment, a derived deployment scheme is added to a set of standard deployment schemes to update the set of standard deployment schemes, including: determining whether there is a standard deployment scheme in which each evaluation indicator is not less than the corresponding evaluation indicator of the derived deployment scheme; if so, adding the derived deployment scheme to the set of standard deployment schemes and deleting the determined standard deployment scheme; if not, adding the derived deployment scheme to the set of diverse deployment schemes.

[0128] Among them, the standard deployment plan set includes a convergent deployment plan set and a diverse deployment plan set; the standard deployment plan in the standard deployment plan set can be the same as or different from the reference deployment plan; there is no preset dominance relationship between the standard deployment plans in the convergent deployment plan set, and the standard deployment plans in the convergent deployment plan set are convergently distributed in the target space (that is, the distribution of the standard deployment plans gradually tends to a specific distribution mode over time, such as a normal distribution); there is a preset dominance relationship between the standard deployment plans in the diverse deployment plan set, and the standard deployment plans in the diverse deployment plan set are evenly distributed in the target space.

[0129] Among them, the preset dominance relationship between each standard deployment scheme can be determined according to each evaluation index of the standard deployment scheme. Exemplarily, it is assumed that the smaller the value of the evaluation index is, the better the standard deployment scheme is. Among them, the evaluation indexes of standard deployment scheme 1 are (5, 5, 5), the evaluation indexes of standard deployment scheme 2 are (4, 5, 6), and the evaluation indexes of standard deployment scheme 3 are (2, 2, 2). Obviously, evaluation index 1 in standard deployment scheme 1 is inferior to evaluation index 1 in standard deployment scheme 2, but evaluation index 3 in standard deployment scheme 1 is better than evaluation index 3 in standard deployment scheme 2. Therefore, it is determined that there is no preset dominance relationship between standard deployment scheme 1 and standard deployment scheme 2. Each evaluation index in standard deployment scheme 1 is inferior to the corresponding evaluation index in standard deployment scheme 3. Therefore, it is determined that there is a preset dominance relationship between standard deployment scheme 1 and standard deployment scheme 3, and standard deployment scheme 3 can dominate standard deployment scheme 1.

[0130] Exemplarily, a method for determining a convergent deployment plan set includes: obtaining at least one standard deployment plan; determining whether there is a preset dominance relationship between the standard deployment plans, and adding the standard deployment plans with the preset dominance relationship to the standard deployment plan set until the number of standard deployment plans in the convergent deployment plan set reaches an upper limit.

[0131] Exemplarily, a method for determining a set of diverse deployment solutions includes: obtaining at least one standard deployment solution; selecting a standard deployment solution that does not have a preset dominance relationship; determining the diversity results of each standard deployment solution based on a diversity determination algorithm (such as a distance-based metric, a target space-based division, etc.); and determining whether to add the standard deployment solution to the set of standard deployment solutions based on the diversity results, until the number of standard deployment solutions in the set of diverse deployment solutions reaches an upper limit.

[0132] Specifically, for each standard deployment plan, determine whether each evaluation indicator of the standard deployment plan is not less than the corresponding evaluation indicator of the derived deployment plan; if so, replace the standard deployment plan determined in the standard deployment plan with the derived deployment plan; if not, add the derived deployment plan to the diverse deployment plan set.

[0133] In this embodiment, it is determined whether there is a standard deployment solution whose evaluation index is not less than the corresponding evaluation index of the derived deployment solution; if so, the derived deployment solution is added to the standard deployment solution set and the determined standard deployment solution is deleted; if not, the derived deployment solution is added to the diverse deployment solution set. This embodiment maintains the diversity of the standard deployment solution set and improves the richness and accuracy of the standard deployment solution set update.

[0134] In one embodiment, a target deployment solution set for an edge server is generated based on the distance between each standard deployment solution in the standard deployment solution set, including: selecting the distance between each standard deployment solution in the diverse deployment solution set and each convergent deployment solution in the convergent deployment solution set; deleting a preset number of standard deployment solutions from the diverse deployment solution set based on the distance between each standard deployment solution in the diverse deployment solution set to update the diverse deployment solution set; generating a target deployment solution set for the edge server based on the convergent deployment solution set and the updated diverse deployment solution set.

[0135] Specifically, for each standard deployment scheme in the diverse deployment scheme set, determine the distance between the standard deployment scheme and each convergent deployment scheme in the convergent deployment scheme set; each time select the standard deployment scheme in the diverse deployment scheme set corresponding to the minimum distance and delete it to update the diverse deployment scheme set until the number of standard deployment schemes in the diverse deployment scheme set and the convergent deployment scheme set is no more than a preset number threshold, and stop updating the diverse deployment scheme set; combine the convergent deployment scheme set and the updated diverse deployment scheme set to obtain the target deployment scheme set for the edge server.

[0136] In this embodiment, the distance between each standard deployment scheme in the diverse deployment scheme set and each convergent deployment scheme in the convergent deployment scheme set is selected; according to the distance between each standard deployment scheme in the diverse deployment scheme set, a preset number of standard deployment schemes are deleted from the diverse deployment scheme set to update the diverse deployment scheme set; according to the convergent deployment scheme set and the updated diverse deployment scheme set, a target deployment scheme set for the edge server is generated. In this embodiment, the overflowed standard deployment schemes in the diverse deployment scheme set are truncated according to the distance between each standard deployment scheme in the diverse deployment scheme set and each convergent deployment scheme in the convergent deployment scheme set, thereby maintaining the convergence of the standard deployment schemes.

[0137] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0138] Based on the same inventive concept, the embodiment of the present application also provides an edge server deployment device for implementing the edge server deployment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more edge server deployment device embodiments provided below can refer to the limitations of the edge server deployment method above, and will not be repeated here.

[0139] In an exemplary embodiment, Figure 5 As shown, an edge server deployment device is provided, comprising: a set acquisition module 10, a solution selection module 11, a solution generation module 12, a set update module 13 and a set generation module 14, wherein:

[0140] A set acquisition module 10 is used to acquire a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution;

[0141] A solution selection module 11 is used to select at least one reference deployment solution from the reference deployment solution set as the deployment solution to be updated for each iteration process;

[0142] A solution generation module 12, configured to generate a derived deployment solution according to the deployment status of the edge servers in different base stations in the deployment solution to be updated;

[0143] A set updating module 13, used for controlling the updating of the set of standard deployment solutions according to the magnitude relationship between the evaluation indicators of the derived deployment solutions and the evaluation indicators corresponding to the standard deployment solutions;

[0144] The set generation module 14 is used to generate a target deployment solution set for the edge server according to the standard deployment solution set under the current number of iterations when the current number of iterations reaches a preset number of iterations; wherein the evaluation index includes at least one of the delay index, load index and quality index of the edge server under the current deployment solution.

[0145] In one embodiment, the solution generation module 12 is also used to determine the adjustment difference between the historical adjustment times of the deployment solution to be updated and the preset adjustment times; when the adjustment difference is greater than the preset adjustment threshold, the deployment solution to be updated is split into two deployment sub-solutions to be updated according to a preset splitting method, and each deployment sub-solution to be updated is expanded to obtain a derivative deployment solution corresponding to each deployment sub-solution to be updated; when the adjustment difference is not greater than the preset adjustment threshold, the deployment status of the edge servers in different base stations in the deployment solution to be updated is randomly adjusted.

[0146] In one embodiment, the solution generation module 12 is also used to determine the solution kinetic energy value of the deployment solution to be updated for each deployment solution to be updated; when the preset solution kinetic energy values ​​corresponding to the two deployment solutions to be updated are not greater than the preset kinetic energy threshold, the two deployment solutions to be updated are merged to obtain a derived deployment solution; if there is a situation where the solution value corresponding to any deployment solution to be updated is greater than the preset kinetic energy threshold, the edge server deployment status of the base station to be updated in the two deployment solutions to be updated is selected for cross-replacement to obtain a derived deployment solution corresponding to the deployment solution to be updated.

[0147] In one embodiment, the set updating module 13 includes:

[0148] An indicator judgment unit, used to determine whether each evaluation indicator of each standard deployment solution in the standard deployment solution set is smaller than a corresponding evaluation indicator of the derived deployment solution;

[0149] The judgment result unit is used to, if yes, prohibit adding the derived deployment solution to the standard deployment solution set; if no, add the derived deployment solution to the standard deployment solution set to update the standard deployment solution set.

[0150] In one embodiment, the result judgment unit is also used to determine whether there is a standard deployment plan in which each evaluation indicator is not less than the corresponding evaluation indicator of the derived deployment plan; if so, the derived deployment plan is added to the standard deployment plan set and the determined standard deployment plan is deleted; if not, the derived deployment plan is added to the diverse deployment plan set.

[0151] In one embodiment, the set generation module 14 includes:

[0152] A quantity determination unit, used to determine the number of standard deployment solutions in the standard deployment solution set under the current number of iterations;

[0153] The set output unit is used to use the standard deployment solution set as the target deployment solution set of the edge server when the number of solutions is not greater than the preset number threshold; when the number of solutions is greater than the preset number threshold, generate the target deployment solution set of the edge server according to the distance between each standard deployment solution in the standard deployment solution set.

[0154] In one embodiment, the set output unit is also used to select the distance between each standard deployment scheme in the diverse deployment scheme set and each convergent deployment scheme in the convergent deployment scheme set; delete a preset number of standard deployment schemes from the diverse deployment scheme set according to the distance between each standard deployment scheme in the diverse deployment scheme set to update the diverse deployment scheme set; generate a target deployment scheme set for the edge server according to the convergent deployment scheme set and the updated diverse deployment scheme set.

[0155] Each module in the above-mentioned edge server deployment device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0156] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an edge server deployment method is implemented.

[0157] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0158] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0160] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0161] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0162] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0163] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for deploying an edge server, characterized in that: The method comprises: Acquire a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution; For each iteration process, selecting at least one reference deployment scheme from the reference deployment scheme set as the deployment scheme to be updated; Generate a derived deployment plan according to the deployment status of the edge servers in different base stations in the deployment plan to be updated; According to the magnitude relationship between each evaluation indicator of the derived deployment solution and each evaluation indicator corresponding to each standard deployment solution, controlling the updating of the standard deployment solution set; When the current number of iterations reaches the preset number of iterations, a target deployment solution set for the edge server is generated according to the standard deployment solution set under the current number of iterations; The evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment scheme; Generating a target deployment solution set for the edge server according to the standard deployment solution set under the current iteration number, including: determining the number of standard deployment solutions in the standard deployment solution set under the current iteration number; and generating a target deployment solution set for the edge server according to the distance between each standard deployment solution in the standard deployment solution set when the number of solutions is greater than a preset number threshold; The standard deployment scheme set includes a convergent deployment scheme set and a diverse deployment scheme set; there is no preset dominance relationship between the standard deployment schemes in the convergent deployment scheme set; there is a preset dominance relationship between the standard deployment schemes in the diverse deployment scheme set; generating a target deployment scheme set for the edge server based on the distance between the standard deployment schemes in the standard deployment scheme set includes: for each standard deployment scheme in the diverse deployment scheme set, determining the distance between each standard deployment scheme in the diverse deployment scheme set and each convergent deployment scheme in the convergent deployment scheme set; each time selecting the standard deployment scheme in the diverse deployment scheme set corresponding to the minimum distance to delete the standard deployment scheme in the diverse deployment scheme set to update the diverse deployment scheme set until the number of standard deployment schemes in the diverse deployment scheme set and the convergent deployment scheme set is no greater than the preset number threshold, and then stopping updating the diverse deployment scheme set; generating a target deployment scheme set for the edge server based on the convergent deployment scheme set and the updated diverse deployment scheme set.

2. The method according to claim 1, characterized in that In the case that there is only one deployment scheme to be updated, generating a derived deployment scheme according to the deployment status of edge servers in different base stations in the deployment scheme to be updated includes: Determine an adjustment difference between a historical adjustment number of the deployment scheme to be updated and a preset adjustment number; When the adjustment difference is greater than a preset adjustment threshold, the deployment scheme to be updated is split into two deployment sub-schemes to be updated according to a preset splitting method, and each deployment sub-scheme to be updated is extended to obtain a derivative deployment scheme corresponding to each deployment sub-scheme to be updated; When the adjustment difference is not greater than a preset adjustment threshold, the deployment states of the edge servers in different base stations in the deployment scheme to be updated are randomly adjusted.

3. The method according to claim 1, characterized in that In the case where there are two deployment schemes to be updated, generating a derived deployment scheme according to the deployment status of edge servers in different base stations in the deployment schemes to be updated includes: For each deployment scheme to be updated, determining a scheme kinetic energy value of the deployment scheme to be updated; When the scheme kinetic energy values ​​corresponding to the two deployment schemes to be updated are not greater than the preset kinetic energy threshold, the two deployment schemes to be updated are merged to obtain a derived deployment scheme; If the kinetic energy value of any of the deployment schemes to be updated is greater than the preset kinetic energy threshold, the edge server deployment states of the base stations to be updated in the two deployment schemes to be updated are selected for cross-replacement to obtain a derivative deployment scheme corresponding to the deployment scheme to be updated.

4. The method according to claim 1, characterized in that: According to the magnitude relationship between each evaluation indicator of the derived deployment solution and each evaluation indicator corresponding to each standard deployment solution in the standard deployment solution set, controlling to update the standard deployment solution set includes: Determining whether each evaluation indicator of each standard deployment solution in the set of standard deployment solutions is less than a corresponding evaluation indicator of the derived deployment solution; If so, prohibiting the derivative deployment solution from being added to the set of standard deployment solutions; If not, the derived deployment solution is added to the set of standard deployment solutions to update the set of standard deployment solutions.

5. The method according to claim 4, characterized in that The set of standard deployment solutions includes a convergent deployment solution set and a diverse deployment solution set; there is no preset dominance relationship between the standard deployment solutions in the convergent deployment solution set; there is a preset dominance relationship between the standard deployment solutions in the diverse deployment solution set; accordingly, adding the derived deployment solution to the set of standard deployment solutions to update the set of standard deployment solutions includes: Determining whether there is a standard deployment solution in which each evaluation indicator is not less than the corresponding evaluation indicator of the derived deployment solution; If yes, replacing the standard deployment solution determined in the set of standard deployment solutions with the derived deployment solution; If not, the derived deployment solution is added to the diverse deployment solution set.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: When the number of the solutions is not greater than a preset number threshold, the standard deployment solution set is used as a target deployment solution set for the edge server.

7. The method according to claim 1, characterized in that The method for determining the quality index includes: Determine a delay normalization result of a transmission delay corresponding to each edge server in the derived deployment scheme; Determine a load normalization result of a load value corresponding to each edge server in the derived deployment solution; The delay normalization result and the load normalization result are weightedly summed to obtain the quality index of the derived deployment solution.

8. An edge server deployment device, characterized in that: The device comprises: A set acquisition module, used to acquire a reference deployment solution set and a standard deployment solution set of the edge server; the reference deployment solution set includes at least one reference deployment solution; the standard deployment solution set includes at least one standard deployment solution; A solution selection module, configured to select at least one reference deployment solution from the reference deployment solution set as the deployment solution to be updated for each iteration process; A solution generation module, used to generate a derived deployment solution according to the deployment status of the edge servers in different base stations in the deployment solution to be updated; A set updating module, used for controlling the updating of the set of standard deployment solutions according to the magnitude relationship between the evaluation indicators of the derived deployment solutions and the evaluation indicators corresponding to the standard deployment solutions; A set generation module is used to generate a target deployment solution set for edge servers according to a set of standard deployment solutions under the current number of iterations when the current number of iterations reaches a preset number of iterations; wherein the evaluation index includes at least one of a delay index, a load index, and a quality index of the edge server under the current deployment solution; generating a target deployment solution set for edge servers according to a set of standard deployment solutions under the current number of iterations includes: determining the number of standard deployment solutions in the set of standard deployment solutions under the current number of iterations; generating a target deployment solution set for edge servers according to a distance between each standard deployment solution in the set of standard deployment solutions when the number of solutions is greater than a preset number threshold; the set of standard deployment solutions includes a convergent deployment solution set and a diverse deployment solution set; the distances between each standard deployment solution in the convergent deployment solution set are not There is a preset dominance relationship; there is a preset dominance relationship between the standard deployment schemes in the diverse deployment scheme set; the target deployment scheme set for the edge server is generated according to the distance between the standard deployment schemes in the standard deployment scheme set, including: for each standard deployment scheme in the diverse deployment scheme set, determining the distance between the standard deployment schemes in the diverse deployment scheme set and the convergent deployment schemes in the convergent deployment scheme set; each time the standard deployment scheme in the diverse deployment scheme set corresponding to the minimum distance is selected for deletion to update the diverse deployment scheme set, until the number of standard deployment schemes in the diverse deployment scheme set and the convergent deployment scheme set is no more than the preset number threshold, and then the updating of the diverse deployment scheme set is stopped; according to the convergent deployment scheme set and the updated diverse deployment scheme set, a target deployment scheme set for the edge server is generated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images