A resource allocation optimization method, device, medium and product

Abstract

The present application discloses a resource allocation optimization method, device, medium and product, which relates to the field of resource allocation. The method includes constructing a lower bound model of resource allocation amount according to the total benefit generated by the resources to be configured and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount; constructing a simulation evaluation model of the resource allocation effect according to the resource allocation amount, the benefit actually generated by simulating a single component resource and the service level; the simulation evaluation model is used to output the probability that the benefit generated by the resource allocation amount reaches the service level; using the output of the lower bound model of the resource allocation amount as the initial value of the resource allocation amount, using the dichotomy method, iteratively calculating the resource allocation amount, and using the simulation evaluation model for evaluation to obtain the optimal resource allocation amount. The present application can not only ensure that the efficiently determined resource allocation meets the resource allocation requirements, but also greatly reduce the cost of resource allocation evaluation during the resource allocation process.

Description

Technical Field

[0001] The present application relates to the field of resource allocation, and in particular to a resource allocation optimization method, device, medium and product. Background Art

[0002] In the fields of social production, emergency rescue, etc., resource allocation issues are involved. When resources are limited, how to quickly allocate resources while meeting the resource allocation requirements is an issue worthy of in-depth consideration. Generally speaking, the more resources are allocated within a certain range, the better the benefits. In the process of resource allocation, it is often necessary to evaluate the benefits of allocating different quantities of the same resources, find the optimal resource allocation amount that meets the resource allocation requirements, and optimize resource allocation. Obviously, evaluating the benefits of resource allocation itself also requires a certain amount of time, financial resources, and material resources. In order to reduce waste and save costs, it is necessary to further optimize resource allocation, achieve resource allocation, and reduce the cost of resource allocation.

[0003] In order to solve the resource allocation problem, given the resource allocation requirements, the simplest allocation method is the enumeration method, that is, starting from zero, gradually increasing the allocation amount of resources, and evaluating the degree to which the resource allocation requirements are met until the allocated amount of resources meets the resource allocation requirements. This method can find a configuration that meets the resource allocation requirements, but the number of times to evaluate the benefits of different resource configurations is too many, resulting in a waste of time, financial resources and material resources.

[0004] Therefore, how to achieve optimal resource allocation with the lowest cost and high efficiency in the resource allocation process is an urgent problem to be solved. Summary of the invention

[0005] The purpose of this application is to provide a resource allocation optimization method, device, medium and product, which can not only ensure that the efficiently determined resource allocation meets the resource allocation requirements, but also significantly reduce the cost of resource allocation evaluation during the resource allocation process.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a resource configuration optimization method, the resource configuration optimization method comprising:

[0008] Constructing a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount;

[0009] A simulation evaluation model for resource allocation effect is constructed based on the resource allocation amount, the actual benefit generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefit generated by the resource allocation amount reaches the service level;

[0010] The output of the lower bound model of resource allocation is used as the initial value of resource allocation. The resource allocation is iteratively calculated using the dichotomy method and evaluated using the simulation evaluation model to obtain the optimal resource allocation.

[0011] Optionally, the lower bound model of resource allocation amount is constructed according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions, specifically including:

[0012] Using the formula Determine the lower bound model of resource allocation;

[0013] in, is the lower bound of resource allocation, To obtain the total benefit of the resources to be allocated, The benefit generated under ideal circumstances for a single machine resource.

[0014] Optionally, the evaluation process of the simulation evaluation model specifically includes:

[0015] Obtain resource allocation and the benefits generated by a single component resource under ideal conditions , Service Level and reliability ;

[0016] Get the k The actual benefits generated by each configured resource during the simulation;

[0017] The sum of the actual benefits generated by each resource and the service level Compare and determine the simulation results;

[0018] The probability that the benefits generated by the resource allocation amount will reach the service level is determined based on the simulation results and the total number of simulations.

[0019] Optionally, the sum of the actual benefits generated by each piece of resource and the service level Compare and determine the simulation results, including:

[0020] ;

[0021] in, For the simulation results, For the i The actual benefits of the hardware resources, Allocate the amount for the resource.

[0022] Optionally, determining the probability that the benefit generated by the resource configuration amount reaches the service level according to the simulation result and the total number of simulations specifically includes:

[0023] ;

[0024] in, The probability that the benefits generated by the resource allocation amount reach the service level, is the total number of simulations.

[0025] Optionally, the output of the lower bound model of the resource configuration amount is used as the initial value of the resource configuration amount, the resource configuration amount is iteratively calculated using the dichotomy method, and the simulation evaluation model is used for evaluation to obtain the optimal resource configuration amount, which specifically includes:

[0026] Step 1: Initialize the direction factor of the dichotomy , step length ;

[0027] Step 2, , if the step length , then output the optimal resource allocation result;

[0028] Step 3: If the direction factor , then the current resource allocation = , is the lower bound of resource allocation; otherwise, the formula Calculate the current resource allocation ; Allocate the amount for the previous resource;

[0029] Step 4: Current resource allocation estimate ; Determine the current resource allocation based on the simulation evaluation model The probability that the benefits generated reach the service level ;

[0030] Step 5: If , then execute step 7; otherwise, the current resource allocation As the current optimal resource allocation , the current resource allocation The probability that the benefits generated reach the service level The probability that the benefits generated by the current optimal resource allocation will reach the service level ;

[0031] Step 6: If the benefit generated by the current optimal resource allocation reaches the service level, the probability Reliability , then update the step size to , the direction factor Update to -1 and return to step 2; otherwise, the update step size is , update the direction factor to 1, and return to step 2;

[0032] Step 7: If the current optimal resource allocation , the update step length is , otherwise go to step 8; if , then update the current optimal resource allocation Configure the current resource , update the confidence level to achieve the service level for , update the direction factor to -1 and return to step 2; otherwise, update the direction factor If it is 1, return to step 2;

[0033] Step 8: If , update the direction factor for , the update step length is ,when Update the direction factor is 0; otherwise, update the direction factor is 1, and the update step size is , and use the formula Determine an updated resource allocation estimate; where, Indicates rounding;

[0034] Step 9, if , then Updated to ; The current optimal resource allocation Updated to ,Will Updated to , and return to step 2.

[0035] In a second aspect, the present application provides a resource configuration optimization device, the resource configuration optimization device comprising:

[0036] A lower bound model building module is used to build a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount;

[0037] A simulation evaluation model building module is used to build a simulation evaluation model of resource allocation effect according to the resource allocation amount, the benefits actually generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefits generated by the resource allocation amount reach the service level;

[0038] The optimal resource configuration amount determination module is used to use the output of the lower bound model of the resource configuration amount as the initial value of the resource configuration amount, adopt the dichotomy method, iteratively calculate the resource configuration amount, and use the simulation evaluation model to evaluate to obtain the optimal resource configuration amount.

[0039] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the resource configuration optimization method.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the resource configuration optimization method when executed by a processor.

[0041] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the resource configuration optimization method when executed by a processor.

[0042] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0043] The present application provides a resource allocation optimization method, device, medium and product, which constructs a lower bound model of the resource allocation amount according to the total benefits generated by the resources to be configured and the benefits generated by a single component resource under ideal conditions, and uses the lower bound of the resource allocation amount as the initial value of the resource allocation amount; then constructs a simulation evaluation model of the resource allocation effect according to the resource configuration amount, the actual benefits generated by simulating a single component resource, and the service level; and then uses the lower bound of the resource configuration amount as the initial value of the resource configuration amount, and further uses the secant method of finding the root of the equation on the basis of the bisection method to iteratively calculate the resource configuration amount (estimated value), and evaluates until the resource configuration amount that meets the resource configuration requirements is obtained, while effectively reducing the time, financial and material resource consumption of the resource configuration evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be 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.

[0045] Figure 1 A schematic diagram of a process flow of a resource configuration optimization method in an embodiment of the present application;

[0046] Figure 2 This is a schematic diagram of the overall process of a resource allocation optimization method in an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram of an island in one embodiment of the present application;

[0048] Figure 4 Schematic diagram of the deployment location of 5G base stations on the island after configuration (unit: meters). DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0051] In an exemplary embodiment, Figure 1 As shown, a resource configuration optimization method is provided, which includes the following S101 to S103.

[0052] S101, constructing a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount;

[0053] Specifically, the total benefits generated by the resources to be configured may be the total area of ​​the region served by the configured resources, the total amount of equipment guaranteed by the maintenance services, etc.

[0054] The benefits generated by a single equipment resource can be the service support area, the number of equipment provided by the service, etc.

[0055] For example, the service area is: ;in, is the radius of the service support area;

[0056] S101 specifically includes:

[0057] Using the formula Determine the lower bound of resource allocation;

[0058] in, is the lower bound of resource allocation, is the total benefit generated by the resources to be allocated, The benefit generated under ideal circumstances for a single machine resource.

[0059] S102, constructing a simulation evaluation model for resource allocation effect according to the resource allocation amount, the actual benefit generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefit generated by the resource allocation amount reaches the service level;

[0060] The evaluation process of the simulation evaluation model specifically includes:

[0061] S21, obtain the resource allocation amount and the benefits generated by a single component resource under ideal conditions , Service Level and reliability ;

[0062] S22, obtain the k The actual benefits generated by each configured resource during the simulation;

[0063] S23, the sum of the actual benefits generated by each piece of resource and the service level Compare and determine the simulation results;

[0064] The simulation results include:

[0065] ;

[0066] in, For the simulation results, is the actual benefit generated by the i-th resource, resource number , Allocate the amount for the resource.

[0067] S24, determining the probability that the benefits generated by the resource allocation amount reach the service level based on the simulation results and the total number of simulations.

[0068] The probability that the benefits generated by resource allocation reach the service level is: ;

[0069] in, The probability that the benefits generated by the resource allocation amount reach the service level, is the total number of simulations.

[0070] S103, taking the output of the lower bound model of the resource allocation amount as the initial value of the resource allocation amount, adopting the dichotomy method, iteratively calculating the resource allocation amount, and adopting the simulation evaluation model to evaluate, so as to obtain the optimal resource allocation amount.

[0071] S103 specifically includes:

[0072] Step 1: Initialize the direction factor of the dichotomy , step length ;

[0073] Step 2, , if the step length , then output the optimal resource allocation result;

[0074] Step 3: If the direction factor , then the current resource allocation = , is the lower bound of resource allocation; otherwise, the formula Calculate the current resource allocation ; Allocate the amount for the previous resource;

[0075] Step 4: Current resource allocation estimate ; Determine the current resource allocation based on the simulation evaluation model The probability that the benefits generated reach the service level ;

[0076] Step 5: If , then execute step 7; otherwise, the current resource allocation As the current optimal resource allocation , the current resource allocation The probability that the benefits generated reach the service level The probability that the benefits generated by the current optimal resource allocation will reach the service level ;

[0077] Step 6: If the benefit generated by the current optimal resource allocation reaches the service level, the probability Reliability , then update the step size to , the direction factor Update to -1 and return to step 2; otherwise, the update step size is , update the direction factor to 1, and return to step 2;

[0078] Step 7: If the current optimal resource allocation , the update step length is , otherwise go to step 8; if , then update the current optimal resource allocation Configure the current resource , update the confidence level to achieve the service level for , update the direction factor to -1 and return to step 2; otherwise, update the direction factor If it is 1, return to step 2;

[0079] Step 8: If , update the direction factor for , the update step length is ,when Update the direction factor is 0; otherwise, update the direction factor is 1, and the update step size is , and use the formula Determine an updated resource allocation estimate; where, Indicates rounding;

[0080] Step 9, if , then Updated to ; The current optimal resource allocation Updated to ,Will Updated to , and return to step 2.

[0081] The resource allocation optimization method in the present application realizes the optimal allocation of resources, ensures that the resources reach the required service level, and effectively reduces the resource allocation amount; the resource allocation optimization method in the present application realizes the optimal allocation of resources with fewer searches, effectively reduces the number of different resource configuration evaluations during the resource allocation process, and effectively saves time, manpower and material resources.

[0082] The following is a specific example in which a certain island will use 5G network to provide communication services. The area of ​​the island is about 10 square kilometers. Figure 3 The coordinates of the vertex of the boundary curve are shown in Table 1. The coverage range of a 5G base station is generally about 250 meters. The coverage range of a 5G base station is affected by factors such as frequency, terrain, and building density. Generally speaking, it is about 100 to 300 meters. In addition, due to the geographical environment on the island, the installation location of the 5G base station follows a normal distribution with the installation point as the center and a standard deviation of 10 meters. The 5G base station configuration is determined with a confidence level of 0.9 to meet the needs of 80% of customers in the area.

[0083] Table 1

[0084]

[0085] Take 5G base stations as resources and determine the configuration of 5G base stations. Here, we assume that the coverage range of 5G base stations is 250 meters. Due to the geographical environment restrictions on the island, the installation location of 5G base stations follows a normal distribution with the installation point as the center and a standard deviation of 10 meters.

[0086] like Figure 2 As shown in the figure, the specific resource allocation optimization process includes:

[0087] Step 1: Establish a lower bound model for 5G base station configuration;

[0088] Step 1.1: Enter the island area that needs 5G base station coverage m 2 ;

[0089] Step 1.2: Enter the area covered by a base station m 2 ;

[0090] Step 1.3: The lower bound of resource allocation is

[0091] (1)

[0092] in Indicates rounding up.

[0093] Step 2: Establish a simulation evaluation model for base station configuration effects;

[0094] Step 2.1: Enter the number of 5G base stations , the area covered by a base station m 2 , input the service level required by the base station (relative coverage) and reliability , enter the total number of simulations ;

[0095] Step 2.2: Assume that 5G base stations are evenly distributed on the island. Simulate the relative coverage area when the base station coverage area is the largest. Assume that During the simulation, the actual relative coverage area of ​​the configured i-th base station is , resource number .

[0096] Step 2.3: Evaluate The simulation results, that is, whether the configured 5G base station meets the requirements, are as follows:

[0097] (2)

[0098] Step 2.3: Statistically calculate the probability that the 5G base station configuration obtained by simulation can reach the required service level :

[0099] (3)

[0100] Output the result and exit the calculation.

[0101] Step 3: Solve the 5G base station configuration problem;

[0102] Step 3.1: Input the island area and its geometric shape to be provided with 5G base station service. The coordinates of the vertex of the boundary curve are shown in Table 1. Input the relative coverage area required to be provided with 5G base stations. and reliability =0.9, input the total number of simulation times =10000;

[0103] Step 3.2 Calculate the actual coverage area of ​​the configured 5G base station ;

[0104] Step 3.3: Calculate the coverage area of ​​a single 5G base station , that is, the service guarantee area is

[0105] (4)

[0106] in, The radius of the island area is guaranteed for service.

[0107] Step 3.4: Calculate the lower bound of the number of 5G base station configurations according to step 1 ;

[0108] Step 3.5: Let the direction factor , step length .

[0109] Step 3.6: If the step size , then output the optimal 5G base station configuration result and exit the calculation;

[0110] Step 3.7: If the direction factor , then the current 5G base station configuration is = Otherwise, calculate the current 5G base station configuration according to formula (5): :

[0111] (5)

[0112] Step 3.8: Calculate the service level of the currently configured 5G base station according to step 2 Probability ;

[0113] Step 3.9: Assume that the estimated 5G base station configuration is ;

[0114] Step 3.10: If the direction factor , execute step 3.13;

[0115] Step 3.11: The current optimal 5G base station configuration and the confidence level of reaching the service level are ;in, Indicates that The data on the left is updated to Data on the right;

[0116] Step 3.12: If the confidence level of the service level is achieved , then update the step size and direction factor, ;otherwise, . Return to step 3.6;

[0117] Step 3.13: If the current optimal 5G base station configuration , execute step 3.15;

[0118] Step 3.14: Update step size , .if , then update the current optimal 5G base station configuration , reliability in achieving service levels and direction factor , ; Otherwise update the direction factor , ; Execute step 3.6;

[0119] Step 3.15: If , then update the direction factor and step length , , ;when Update the direction factor ; Otherwise update the direction factor and step length , , calculate the estimated 5G base station configuration :

[0120] (6)

[0121] in Indicates rounding;

[0122] Step 3.16: If ,but ; Update the current optimal 5G base station configuration and the confidence to achieve service levels , ; Execute step 3.6.

[0123] The calculation shows that the number of 5G base stations that meet the required service level is 42 5G base stations, and the 5G base stations are deployed in the following locations: Figure 4 As shown, Figure 4 middle Indicates the deployment locations of 5G base stations.

[0124] like Figure 4 As shown, the 5G base stations are evenly distributed on the island. According to the required service level, the method of the present invention can provide the optimal configuration of 5G base stations when the coverage range (radius) of the 5G base station is fixed. In practical applications, considering the actual situation, 5G base stations in different locations are affected by factors such as terrain, and the optimal configuration of 5G base stations may need to be appropriately increased or decreased based on the actual situation.

[0125] In order to reveal the efficiency of the calculation of the resource configuration optimization method in this application, this application is compared with the calculation of the enumeration method. When the enumeration method searches for the optimal configuration, the number of 5G base stations starts from 1 until the requirements are met. The method of the present invention starts searching from the lower bound (41) of the 5G base station configuration problem until the 5G base station configuration quantity that meets the requirements is obtained.

[0126] The enumeration method is used to calculate the optimal configuration of 5G base stations. When the number of 5G base station configurations is different, the probability of the 5G base station reaching the required service level and the consumed computing time are shown in Table 2.

[0127] Table 2

[0128]

[0129] This application is used to calculate the optimal configuration of 5G base stations. When the configuration amounts of 5G base stations are different, the probability of the 5G base stations reaching the required service level and the consumed calculation time obtained after evaluation are shown in Table 3.

[0130] Table 3

[0131]

[0132] Comparing Table 2 and Table 3, we can see that: using the enumeration method, a total of 42 different configurations of 5G base stations were searched, and the optimal configuration of 5G base stations was obtained, which took 2361.100 seconds; using this application, a total of 3 different configurations of 5G base stations were searched, and the optimal configuration of 5G base stations was obtained, which took 495.198 seconds, accounting for about 21% of the time required by the enumeration method. Obviously, this application saves 79% of the time.

[0133] Based on the same inventive concept, the embodiment of the present application also provides a resource configuration optimization device for implementing the resource configuration optimization 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 one or more resource configuration optimization device embodiments provided below can refer to the limitations of the resource configuration optimization method above, and will not be repeated here.

[0134] In an exemplary embodiment, a resource configuration optimization device is provided, comprising:

[0135] A lower bound model building module is used to build a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount;

[0136] A simulation evaluation model building module is used to build a simulation evaluation model of resource allocation effect according to the resource allocation amount, the benefits actually generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefits generated by the resource allocation amount reach the service level;

[0137] The optimal resource configuration amount determination module is used to use the output of the lower bound model of the resource configuration amount as the initial value of the resource configuration amount, adopt the dichotomy method, iteratively calculate the resource configuration amount, and use the simulation evaluation model to evaluate to obtain the optimal resource configuration amount.

[0138] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via 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 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 via a network connection. When the computer program is executed by the processor, a resource configuration optimization method is implemented.

[0139] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0140] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application 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.

[0142] 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. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0143] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. 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 is not limited thereto.

[0144] The technical features of the above embodiments may be combined arbitrarily. 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.

[0145] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A resource allocation optimization method, characterized in that: The resource configuration optimization method comprises: Constructing a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount; A simulation evaluation model for resource allocation effect is constructed based on the resource allocation amount, the actual benefit generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefit generated by the resource allocation amount reaches the service level; The output of the lower bound model of resource allocation is used as the initial value of resource allocation, the resource allocation is iteratively calculated using the dichotomy method, and the simulation evaluation model is used for evaluation to obtain the optimal resource allocation; The output of the lower bound model of the resource configuration amount is used as the initial value of the resource configuration amount, the resource configuration amount is iteratively calculated using the dichotomy method, and the simulation evaluation model is used for evaluation to obtain the optimal resource configuration amount, which specifically includes: Step 1: Initialize the direction factor of the dichotomy , step length ; Step 2, , if the step length , then the optimal resource configuration result is output; the resource configuration is the 5G base station configuration; Step 3: If the direction factor , then the current resource allocation = , is the lower bound of resource allocation; otherwise, the formula Calculate the current resource allocation ; The previous resource configuration amount; the resource configuration amount is the number of 5G base station configurations; Step 4: Current resource allocation estimate ; Determine the current resource allocation based on the simulation evaluation model The probability that the benefits generated reach the service level ; The resource configuration estimate is the 5G base station configuration estimate; Step 5: If , then execute step 7; otherwise, the current resource allocation As the current optimal resource allocation , the current resource allocation The probability that the benefits generated reach the service level The probability that the benefits generated by the current optimal resource allocation will reach the service level ; Step 6: If the benefit generated by the current optimal resource allocation reaches the service level, the probability Reliability , then update the step size to , the direction factor Update to -1 and return to step 2; otherwise, the update step size is , update the direction factor to 1, and return to step 2; where, for service levels; Step 7: If the current optimal resource allocation , the update step length is , otherwise go to step 8; if , then update the current optimal resource allocation Configure the current resource , update the probability of reaching the service level for , update the direction factor to -1 and return to step 2; otherwise, update the direction factor If it is 1, return to step 2; Step 8: If , update the direction factor for , the update step length is ,when Update the direction factor is 0; otherwise, update the direction factor is 1, and the update step size is , and using the formula Determine an updated resource allocation estimate; where, Indicates rounding; Step 9: If , then Updated to ; The current optimal resource allocation Updated to ,Will Updated to , and return to step 2.

2. The resource allocation optimization method according to claim 1, characterized in that: The lower bound model of resource allocation quantity is constructed based on the total benefits generated by the resources to be allocated and the benefits generated by a single component resource under ideal conditions, specifically including: Using the formula Determine the lower bound model of resource allocation; in, is the lower bound of resource allocation, is the total benefit generated by the resources to be allocated, The benefit generated under ideal circumstances for a single machine resource.

3. The resource allocation optimization method according to claim 1, characterized in that: The evaluation process of the simulation evaluation model specifically includes: Obtain resource allocation and the benefits generated by a single component resource under ideal conditions , Service Level and reliability ; Get the k The actual benefits generated by each configured resource during the simulation; The sum of the actual benefits generated by each resource and the service level Compare and determine the simulation results; The probability that the benefits generated by the resource allocation amount will reach the service level is determined based on the simulation results and the total number of simulations.

4. The resource allocation optimization method according to claim 3, characterized in that: The sum of the actual benefits generated by each resource and the service level Compare and determine the simulation results, including: ； in, For the simulation results, is the actual benefit generated by the i-th resource, Allocate the amount for the resource.

5. The resource allocation optimization method according to claim 4, characterized in that: Determining the probability that the benefits generated by the resource allocation amount reach the service level based on the simulation results and the total number of simulations specifically includes: ； in, The probability that the benefits generated by the resource allocation amount reach the service level, is the total number of simulations.

6. A resource configuration optimization device, used to implement the resource configuration optimization method according to any one of claims 1 to 5, characterized in that: The resource configuration optimization device comprises: A lower bound model construction module is used to construct a lower bound model of resource allocation amount according to the total benefit generated by the resources to be allocated and the benefit generated by a single component resource under ideal conditions; the lower bound model is used to output the lower bound of the resource allocation amount; A simulation evaluation model building module is used to build a simulation evaluation model of resource allocation effect according to the resource allocation amount, the benefits actually generated by simulating a single component resource, and the service level; the simulation evaluation model is used to output the probability that the benefits generated by the resource allocation amount reach the service level; The optimal resource configuration amount determination module is used to use the output of the lower bound model of the resource configuration amount as the initial value of the resource configuration amount, adopt the dichotomy method, iteratively calculate the resource configuration amount, and use the simulation evaluation model to evaluate to obtain the optimal resource configuration amount.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the resource configuration optimization method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the resource configuration optimization method described in any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the resource configuration optimization method described in any one of claims 1 to 5 is implemented.

Images