Communication network configuration method, system, electronic device and storage medium

Abstract

This application provides a communication network configuration method, system, electronic device, and storage medium, belonging to the field of communication technology. The method includes: acquiring communication factors for each communication link in the communication network and calculating the factor cost-effectiveness of each communication factor; performing a greedy search based on the factor cost-effectiveness to determine the initial configuration factor for the communication link based on the greedy search results; performing an iterative optimization process on the initial configuration factor of the communication link based on the factor cost, stopping the iteration after reaching a preset number of iterations, and outputting the optimized configuration factor of the communication link; using the optimized configuration factor as the search center, randomly replacing the optimized configuration factors of at least two communication links simultaneously to obtain candidate configuration factors corresponding to each communication link; for each communication link, selecting the target configuration factor based on the factor cost and delay confidence of the candidate configuration factors; and configuring the communication network based on multiple target configuration factors.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication network configuration method, system, electronic device, and storage medium. Background Technology

[0002] The communication process of a communication network typically involves multiple intermediate links. The complete process from the terminal to the terminal includes communication links such as the core network, transmission network, and service platform. These communication links cooperate with each other to ensure that data and information can be transmitted to the destination.

[0003] The processing latency of data packets is closely related to the configuration of the communication network. In related technologies, the communication network is usually configured based on default values. However, in the configuration problem of the communication network, the distribution of the random variables involved is unknown, and it is impossible to accurately know or predict the specific distribution of the random variables. Therefore, it is often impossible to accurately configure the communication network, which makes it difficult to improve the confidence of latency and increases the consumption of transmission resources. Summary of the Invention

[0004] The main objective of this application is to propose a communication network configuration method, system, electronic device, and storage medium that can fully consider the distribution of random variables in the configuration of the communication network, thereby improving the confidence level of delay while reducing the consumption of transmission resources.

[0005] To achieve the above objectives, a first aspect of this application proposes a communication network configuration method, the method comprising: acquiring multiple communication factors for each communication link in the communication network, and calculating the factor cost-effectiveness of each communication factor; performing a greedy search in each communication link based on the factor cost-effectiveness to obtain a greedy search result, and determining an initial configuration factor for each communication link based on the greedy search result; acquiring the factor cost of each communication factor, performing an iterative optimization process on the initial configuration factor of each communication link based on the factor cost, stopping the iteration after reaching a preset number of iterations, and outputting an optimized configuration factor for each communication link; using the optimized configuration factor as the search center, randomly replacing the optimized configuration factors of at least two communication links simultaneously to obtain multiple candidate configuration factors corresponding to each communication link; calculating the delay confidence for each communication link, and selecting a target configuration factor for each communication link based on the factor cost of each candidate configuration factor and the delay confidence; and configuring the communication network based on the multiple target configuration factors.

[0006] According to some embodiments of this application, each communication factor includes multiple factor samples; calculating the factor cost-effectiveness of each communication factor includes: calculating the sample mean and sample standard deviation of the factor samples for each communication factor; calculating the factor weight value of the communication factor based on the sample mean and the sample standard deviation; selecting the largest factor cost in the communication network as a reference cost; and obtaining the factor cost-effectiveness of the communication factor by dividing the difference between the reference cost and the factor cost by the factor weight value.

[0007] According to some embodiments of this application, the method further includes: obtaining the sample delay of each factor sample; sorting the factor samples in each communication factor according to the sample delay to obtain a sorting result, and selecting the factor sample corresponding to the largest sample delay from the sorting result as the target factor sample; adding the target factor samples of multiple communication factors to obtain the total sample delay; if the total sample delay is greater than a preset delay threshold, filtering out the multiple communication factors corresponding to the total sample delay.

[0008] According to some embodiments of this application, the step of obtaining the factor cost of each communication factor, performing an iterative optimization process on the initial configuration factor of each communication link based on the factor cost, stopping the iteration after reaching a preset number of iterations, and outputting the optimized configuration factor of each communication link includes: obtaining the factor cost of the communication factor; performing an iterative optimization process on multiple initial configuration factors based on the factor cost, wherein the iterative optimization process includes: performing local optimization processing on each initial configuration factor in the corresponding communication link to obtain a local configuration factor; randomly selecting at least one communication link, and randomly selecting one communication factor from the communication link, and optimizing the local configuration factor. Randomly replace the configuration factor to obtain a random configuration factor; verify the feasibility of the random configuration factor to obtain a verification result; if the verification result indicates that the random configuration factor is feasible in the communication network configuration, then output the random configuration factor as an optimized configuration factor; if the verification result indicates that the random configuration factor is not feasible in the communication network configuration, then continue to randomly replace the communication factor in the communication link until the communication factor in the communication link is completely replaced, then randomly select a communication link to replace the local configuration factor; repeat the iterative optimization process until a preset number of iterations, then stop the iteration and output the optimized configuration factor for each communication link.

[0009] According to some embodiments of this application, the step of performing local optimization processing on each initial configuration factor in the corresponding communication link to obtain a local configuration factor includes: in each communication link, traversing the factor cost of each communication factor; comparing the factor costs of the initial configuration factor and the communication factor, selecting the communication factor whose factor cost is lower than that of the initial configuration factor as a candidate configuration factor; performing feasibility verification on the candidate configuration factor to obtain a first verification result; if the first verification result indicates that the candidate configuration factor is feasible in the communication network configuration, replacing the initial configuration factor with the candidate configuration factor and outputting it as a local configuration factor.

[0010] According to some embodiments of this application, the step of using the optimized configuration factor as the search center and simultaneously randomly replacing the optimized configuration factor of at least two communication links to obtain multiple candidate configuration factors corresponding to each communication link includes: using the optimized configuration factor as the search center to search for communication factors within adjacent communication links; simultaneously randomly replacing the optimized configuration factor within at least two communication links according to the optimized configuration factor to obtain multiple replacement factors; performing feasibility verification on the multiple replacement factors in the communication links corresponding to the optimized configuration factor to obtain a second verification result; if the second verification result indicates that the multiple replacement factors are feasible in the communication network configuration, outputting the multiple replacement factors as candidate configuration factors.

[0011] According to some embodiments of this application, the step of calculating the latency confidence for each communication link and selecting the target configuration factor for each communication link based on the factor cost of each candidate configuration factor and the latency confidence includes: for each communication link, obtaining the factor cost and latency confidence of each candidate configuration factor; obtaining a preset latency confidence threshold, selecting candidate configuration factors with latency confidence greater than the latency confidence threshold, and then selecting the candidate configuration factor with the lowest factor cost as the target configuration factor; or, ranking multiple candidate configuration factors according to the factor cost and the latency confidence to obtain a factor cost ranking list. The system generates a first score for each candidate configuration factor based on the factor cost ranking list and the latency confidence ranking list; generates a second score for each candidate configuration factor based on the latency confidence ranking list; adds the first score and the second score of each candidate configuration factor to obtain multiple total configuration scores; selects the candidate configuration factor corresponding to the highest total configuration score as the target configuration factor; or, selects multiple candidate configuration factors corresponding to the top N rankings of the factor cost ranking list and / or the latency confidence ranking list, and selects the target configuration factor from the multiple candidate configuration factors; wherein, N is a positive integer greater than or equal to 2.

[0012] To achieve the above objectives, a second aspect of this application proposes a communication network configuration system, the system comprising: a factor cost-effectiveness calculation module, which acquires multiple communication factors for each communication link in the communication network and calculates the factor cost-effectiveness of each communication factor; an initial configuration factor acquisition module, which performs a greedy search in each communication link based on the factor cost-effectiveness to obtain a greedy search result and determines an initial configuration factor for each communication link based on the greedy search result; and an optimized configuration factor output module, which acquires the factor cost of each communication factor and performs iterative optimization processing on the initial configuration factor of each communication link based on the factor cost. The process involves stopping iteration after reaching a preset number of iterations and outputting the optimized configuration factor for each communication link. A candidate configuration factor acquisition module is used to randomly replace the optimized configuration factors of at least two communication links simultaneously, using the optimized configuration factors as the search center, to obtain multiple candidate configuration factors corresponding to each communication link. A target configuration factor acquisition module is used to calculate the delay confidence level for each communication link and, based on the factor cost of each candidate configuration factor and the delay confidence level, select the target configuration factor for each communication link. A communication network configuration module is used to configure the communication network based on the multiple target configuration factors.

[0013] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the communication network configuration method described in any one of the embodiments of the first aspect of this application.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the communication network configuration method described in any one of the embodiments of the first aspect of the present application.

[0015] The communication network configuration method, system, electronic device, and storage medium proposed in this application can calculate the cost-effectiveness of factors, perform a greedy search based on the cost-effectiveness of factors to select communication factors with high cost-effectiveness as initial configuration factors, and then perform an iterative optimization process based on the factor cost to continuously optimize the initial configuration factors to obtain optimized configuration factors. To prevent the omission of locally optimal and most suitable communication factors, the optimized configuration factors of at least two communication links are randomly replaced simultaneously, resulting in multiple candidate configuration factors after searching a wider range. Finally, based on the factor cost and delay confidence of each candidate configuration factor, the candidate configuration factors of each link are screened to obtain the target configuration factor. This allows for full consideration of the distribution of random variables in the communication network configuration, improving delay confidence while reducing transmission resource consumption and optimizing the communication network configuration. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of the communication network configuration system provided in the embodiments of this application;

[0017] Figure 2 This is a flowchart of the communication network configuration method provided in the embodiments of this application;

[0018] Figure 3 This is a flowchart illustrating the cost-effectiveness of the calculation factor provided in the embodiments of this application;

[0019] Figure 4 This is a flowchart of a communication network configuration method provided in another embodiment of this application;

[0020] Figure 5 yes Figure 2 A flowchart of step S103 in the process;

[0021] Figure 6 This is a flowchart of calculating the local configuration factor provided in an embodiment of this application;

[0022] Figure 7 yes Figure 2The flowchart of step S104 in the process;

[0023] Figure 8 yes Figure 2 The flowchart of step S105 in the process;

[0024] Figure 9 This is a general flowchart of the communication network configuration method provided in the embodiments of this application;

[0025] Figure 10 This is a schematic diagram of the functional modules of the communication network configuration system provided in the embodiments of this application;

[0026] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0028] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0030] In related technologies, the configuration problem of communication networks typically involves chance-constrained optimization and the distribution of random variables. Because specific constraints need to be considered in the configuration of communication networks, such as network performance requirements and customer needs, failure to consider these constraints may render the configuration infeasible, thus consuming configuration resources and affecting the data transmission process.

[0031] In addition, since the distribution of random variables involved in network configuration problems is unknown, it is impossible to accurately know or predict the specific distribution of random variables. That is, the optimal communication factor cannot be known for each communication link, which increases the difficulty of configuring the communication network.

[0032] Based on this, embodiments of this application provide a communication network configuration method, system, electronic device, and storage medium that can fully consider the distribution of random variables in the configuration of the communication network, thereby improving the confidence level of delay while reducing the consumption of transmission resources and optimizing the configuration of the communication network.

[0033] The communication network configuration method, system, electronic device, and storage medium provided in this application are specifically described through the following embodiments. First, the communication network configuration system in this application is described.

[0034] Please refer to Figure 1 In some embodiments, the communication network configuration system includes a controller 101, a transmitter 102, a communication link 103, and a terminal 104.

[0035] It is understood that the controller 101 can be the nerve center and command center of the system. The controller 101 can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions. For example, the controller can generate operation control signals to control the transmitting end 102, the communication link 103, and the terminal 104, and execute corresponding operations. In some embodiments, the transmitting end 102 refers to the device or module responsible for sending data packets. The communication link 103 refers to the various intermediate links or channels through which the data packets pass during transmission, and the terminal 104 refers to the device or module receiving the data packets.

[0036] The communication network configuration method in this application can be illustrated through the following embodiments.

[0037] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent will be obtained first. Furthermore, the collection, use, and processing of this data will comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user will be obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent will the necessary user-related data for the normal operation of the embodiments of this application be obtained.

[0038] Figure 2 This is an optional flowchart of the communication network configuration method provided in the embodiments of this application. Figure 2 The method may include, but is not limited to, steps S101 to S106.

[0039] Step S101: Obtain multiple communication factors for each communication link in the communication network, and calculate the cost-effectiveness of each communication factor.

[0040] In some embodiments, a communication network refers to a network that connects different devices and systems, enabling them to transmit data and information to each other. Communication networks can be 5G E2E (End-to-End) networks, as well as other types of networks such as wired networks, wireless networks, local area networks (LANs), wide area networks (WANs), and the Internet. Each communication network includes multiple communication links, which are the various stages in the transmission of data or information from the sender to the receiver. These links are connected in series, and their latency distributions are independent. Each communication link includes multiple communication factors, which are various random factors affecting network performance, including traffic models, network load, external environment, and faults. These random factors affect the processing latency of data packets by the communication network. Therefore, it is necessary to select low-latency, low-cost communication factors for each communication link, and then configure the communication network based on these factors.

[0041] In some embodiments, the factor cost-effectiveness is calculated by subtracting the factor cost from the reference cost and dividing by the factor weight value. In some embodiments, multiple communication factors for each communication link in the communication network can be obtained, and the cost-effectiveness of each communication factor can be calculated. Based on the cost-effectiveness, the communication factors for each communication link can be screened to obtain communication factors with high cost-effectiveness.

[0042] Step S102: Based on the factor cost-effectiveness, a greedy search is performed in each communication link to obtain the greedy search result, and the initial configuration factor of each communication link is determined according to the greedy search result.

[0043] It is understandable that greedy search is a heuristic search algorithm based on a greedy strategy. In greedy search, the optimal solution is selected to construct the search path based on the current state. In some embodiments, greedy search can be performed at each stage based on the cost-effectiveness of factors, which can quickly obtain the communication factor with the highest cost-effectiveness and use it as the initial configuration factor.

[0044] Step S103: Obtain the factor cost of each communication factor, perform iterative optimization processing on the initial configuration factor of each communication link according to the factor cost, stop the iteration after reaching the preset number of iterations, and output the optimized configuration factor of each communication link.

[0045] It is understandable that factor cost is the cost required to obtain various communication factors, such as bandwidth, latency, signal strength, etc. Factor cost can be obtained based on pre-calculated or pre-acquired network data, or it can be obtained based on real-time calculation.

[0046] In some embodiments, an iterative optimization process can be performed on the initial configuration factors of each communication link based on the factor cost of each communication factor. During this process, the feasibility of communication factors other than the initial configuration factors in the communication network configuration is continuously verified. Factors with lower costs than the initial configuration factors and which are feasible in the communication network configuration are then used as optimized configuration factors.

[0047] It is understandable that during the iterative optimization process, a local iterative optimization process can be performed first. After the local iterative optimization process is completed, in order to prevent the new communication factor from falling into a local optimum, a degradation operation is performed to finally obtain the optimized configuration factor.

[0048] In some embodiments, the local iterative optimization process involves retracing the communication links corresponding to the initial configuration factor. For example, if the initial configuration factor corresponds to communication link 1, a search can be performed within communication link 1. If a communication factor with a cost lower than the initial configuration factor exists, its feasibility is verified. If the verification result indicates that the communication factor is feasible in the communication network configuration, the initial configuration factor is replaced. It is understood that if multiple communication factors are verified to be feasible, the communication factor with the lowest cost is selected to replace the initial configuration factor.

[0049] In some embodiments, the degradation operation involves randomly selecting multiple communication factors in the communication link and verifying the feasibility of the randomly selected second communication factor. If the verification result indicates that the second communication factor is feasible in the configuration, the first communication factor obtained from the local iterative optimization process is replaced, and the second communication factor is output as the optimized configuration factor. If the verification result indicates that the second communication factor is not feasible in the configuration, random selection is continued in the first communication link. If there is still no feasible communication factor in the first communication link, the first communication factor is randomly selected to replace the second communication link.

[0050] In some embodiments, restrictions on random replacement can be imposed, such as only randomly replacing communication factors whose factor cost is less than communication factor number 1.

[0051] Step S104: Using the optimized configuration factor as the search center, the optimized configuration factors of at least two communication links are randomly replaced to obtain multiple candidate configuration factors corresponding to each communication link.

[0052] In some embodiments, the optimization configuration factors can be searched over a larger area to avoid overlooking communication factors that are better for the current communication link. It is understood that the optimization configuration factors of two or more communication links can be randomly replaced simultaneously, with the replacement scope encompassing all communication factors in the communication network.

[0053] For example, the No. 1 optimization configuration factor corresponding to the No. 1 communication link and the No. 2 optimization configuration factor corresponding to the No. 2 communication link can be randomly replaced in the communication network at the same time, and the feasibility can be continuously verified during the random replacement process. The communication node sub-factors that are feasible in the network configuration are used as candidate configuration factors.

[0054] Step S105: For each communication link, calculate the delay confidence level, and select the target configuration factor for each communication link based on the factor cost and delay confidence level of each candidate configuration factor.

[0055] In some embodiments, the latency confidence level can be calculated for each communication link, and the candidate configuration factors can be ranked or listed according to their factor cost and latency confidence level, thereby quickly filtering out the target configuration factors based on the ranking or list.

[0056] Understandably, the latency confidence list and factor cost list can be combined to calculate the total score of each candidate configuration factor, thus selecting the target configuration factor for each communication stage. Alternatively, technical personnel can manually select the target configuration factor based on the latency confidence ranking list and factor cost list.

[0057] Step S106: Configure the communication network according to multiple target configuration factors.

[0058] In some embodiments, each communication link can be configured according to the target configuration factor, such as setting parameters like bandwidth, to complete the configuration process of the communication network.

[0059] The communication network configuration method, system, electronic device, and storage medium proposed in this application can calculate the cost-effectiveness of factors, perform a greedy search based on the cost-effectiveness of factors to select communication factors with high cost-effectiveness as initial configuration factors, and then perform an iterative optimization process based on the factor cost to continuously optimize the initial configuration factors to obtain optimized configuration factors. To prevent the omission of locally optimal and most suitable communication factors, the optimized configuration factors of at least two communication links are randomly replaced simultaneously, resulting in multiple candidate configuration factors after searching a wider range. Finally, based on the factor cost and delay confidence of each candidate configuration factor, the candidate configuration factors of each link are screened to obtain the target configuration factor. This allows for full consideration of the distribution of random variables in the communication network configuration, improving delay confidence while reducing transmission resource consumption and optimizing the communication network configuration.

[0060] Please refer to Figure 3 In some embodiments, each communication factor includes multiple factor samples; calculating the cost-effectiveness of each communication factor includes, but is not limited to, steps S201 to S204:

[0061] Step S201: Calculate the sample mean and sample standard deviation of the factor samples for each communication factor.

[0062] In some embodiments, each communication link includes multiple communication factors, and each communication factor includes multiple factor samples. For example, the factor sample of the l-th largest delay of the j-th communication factor in the i-th communication link can be denoted as t. ijl .

[0063] In some embodiments, the formula for calculating the sample mean of the factor samples is as follows:

[0064] μ ij =E(t) ij )

[0065] Where, μ ij t represents the sample mean. ijl This represents the factor sample with the l-th largest delay of the j-th communication factor in the i-th communication link.

[0066] In some embodiments, the formula for calculating the sample standard deviation of a factor sample is as follows:

[0067]

[0068] in, σ represents the sample variance. ij t represents the sample standard deviation. ijl The factor sample representing the l-th largest delay of the j-th communication factor in the i-th communication link.

[0069] Step S202: Calculate the factor weight value of the communication factor based on the sample mean and sample standard deviation.

[0070] In some embodiments, the factor weight value of the communication factor is calculated using the following formula:

[0071] w ij =μ ij +λσ ij

[0072] Among them, w ij Represents the factor weight value, μ ij σ represents the sample mean, λ represents the factor parameter, and σ represents the factor parameter. ij This represents the sample standard deviation.

[0073] Step S203: Select the largest factor cost in the communication network as the reference cost.

[0074] In some embodiments, all factor costs in the current communication network can be sorted, and the largest factor cost can be selected as the reference cost.

[0075] Step S204: Divide the difference between the reference cost and the factor cost by the factor weight value to obtain the factor cost-effectiveness of the communication factor.

[0076] r ij =(c max -c ij ) / w ij

[0077] Where, r ij c represents the cost-effectiveness of the factor. max c represents the reference cost. ij w represents the factor cost for which the cost-effectiveness is to be calculated. ij This represents the factor weight value. As can be understood, the factor weight value refers to the weight value used to measure the importance of the communication factor in the overall calculation; the larger the communication factor weight value, the higher the importance of the communication factor in the overall calculation. In some embodiments, the factor weight value can be obtained from pre-configured parameters or calculated.

[0078] Understandably, the factor cost-effectiveness reflects the score of minimizing the factor cost while meeting the time delay threshold constraint. It allows for a more comprehensive and accurate comparison of various communication factors, and the selection of the optimal communication factor.

[0079] Please refer to Figure 4 In some embodiments, the communication network configuration method further includes, but is not limited to, steps S301 to S304:

[0080] Step S301: Obtain the sample latency for each factor sample.

[0081] In some embodiments, the sample latency of each factor sample can be obtained using network analysis tools, network monitoring devices, or a measurement tool custom-developed according to actual needs. Step S302: Based on the sample latency, the factor samples are sorted within each communication factor to obtain a sorting result. The factor sample with the largest sample latency is selected from the sorting result as the target factor sample.

[0082] In some embodiments, in each communication factor, the factor samples are sorted according to the sample delay, which can be either reverse sorting or sequential sorting. After obtaining the sorting results, the factor sample corresponding to the largest sample delay is selected as the target factor sample.

[0083] For example, in factor sample 1, the sample latency of factor sample 1 is 12 milliseconds, the latency of factor sample 2 is 18 milliseconds, and the latency of factor sample 3 is 15 milliseconds. Then, the factor samples are sorted in reverse order according to the sample latency, and the sorting result is: factor sample 2: 18 milliseconds; factor sample 3: 15 milliseconds; factor sample 1: 12 milliseconds.

[0084] Furthermore, the factor sample corresponding to the largest sample time delay is selected, namely factor sample number 2, and factor sample number 2 is used as the target factor sample.

[0085] Step S303: Add the target factor samples of multiple communication factors together to obtain the total sample delay.

[0086] In some embodiments, the target factor samples of each communication factor in the communication network can be summed to obtain the total sample delay.

[0087] Step S304: If the total sample delay is greater than the preset delay threshold, the multiple communication factors corresponding to the total sample delay are filtered out.

[0088] In some embodiments, a time delay threshold can be preset, such as 200 milliseconds. If the total sample time delay is greater than 200 milliseconds, it means that the total sample time delay does not meet the requirements, and the time delay of the factor samples corresponding to the total sample time delay also does not meet the requirements. In this case, the factor samples corresponding to the total sample time delay are screened out.

[0089] Understandably, after filtering out the factor sample with the largest delay for each communication factor, the total sample delay can be calculated for the factor sample corresponding to the second largest delay for each communication factor. Following the example of step S302, the factor sample corresponding to the second largest delay for communication factor 1 is factor sample 3: 15 milliseconds. At this point, the factor samples corresponding to the second largest delay for each communication factor in the communication network are summed to obtain the total sample delay. The total sample delay is compared with a delay threshold; if it is greater than the threshold, it is filtered out. The process continues, obtaining the factor sample corresponding to the third largest delay for each communication factor and summing them until the total sample delay is less than the delay threshold, at which point the filtering stops.

[0090] It is understandable that since factor samples with a delay greater than the delay threshold will not meet the requirements, the delay confidence of communication factors will decrease. By filtering out factor samples with a total sample size less than the delay threshold, the proportion of feasible solutions in the total space can be increased.

[0091] Please refer to Figure 5 In some embodiments, step S103 includes, but is not limited to, steps S401 to S403:

[0092] Step S401: Obtain the factor cost of the communication factor.

[0093] In some embodiments, factor cost refers to the resources and overhead required to use a specific communication factor. These resources and overheads include, but are not limited to, hardware equipment, network bandwidth, power consumption, and maintenance costs. Factor cost can be calculated using algorithms or evaluated by technical personnel. It is understood that factor cost is typically a specific evaluation value, determined based on the parameters being evaluated.

[0094] Step S402: Perform an iterative optimization process on multiple initial configuration factors based on factor costs. The iterative optimization process includes: performing local optimization on each initial configuration factor in its corresponding communication link to obtain a local configuration factor; randomly selecting at least one communication link and randomly selecting a communication factor from the communication link to randomly replace the local configuration factor, obtaining a random configuration factor; verifying the feasibility of the random configuration factor to obtain a verification result; if the verification result indicates that the random configuration factor is feasible in the communication network configuration, then the random configuration factor is output as the optimized configuration factor; if the verification result indicates that the random configuration factor is not feasible in the communication network configuration, then continue to randomly replace the communication factor in the communication link until the communication factor in the communication link is replaced, and then randomly select a communication link to replace the local configuration factor.

[0095] In some embodiments, an iterative optimization process can be performed on multiple initial configuration factors based on factor costs to find communication factors with lower factor costs that are feasible in the communication network configuration to replace the initial configuration factors.

[0096] In some embodiments, local optimization can be performed on each initial configuration factor to obtain local configuration factors. Specifically, local optimization can be performed in the communication link corresponding to each initial configuration factor. For example, if initial configuration factor 1 corresponds to communication link 1, then in communication link 1, local optimization is performed based on the factor cost of each communication factor. It is understood that during the local optimization process, communication factors with lower factor costs than the initial configuration factors can be selected to verify feasibility. If feasible, the communication factor replaces the initial configuration factor. If multiple communication factors have lower factor costs than the initial configuration factor, then the communication factor with the lowest factor cost is selected as the local configuration factor.

[0097] In some embodiments, to prevent local optimization from getting stuck in local optima and missing more suitable communication factors, a degradation operation can be used to randomly search for communication factors within each communication link. Specifically, one or more communication links can be randomly selected to replace the communication factor.

[0098] In some embodiments, if, during the degradation operation, communication link 1 is randomly selected for random replacement of initial configuration factor 1, then random replacement can be performed first in communication link 1. For example, if random configuration factor 1 is randomly selected in communication link 1, the feasibility of random configuration factor 1 can be verified. If the verification result indicates that random configuration factor 1 is feasible in the communication network configuration, then random configuration factor 1 is output as the optimized configuration factor. If the verification result indicates that random configuration factor 1 is not feasible in the communication network configuration, then random replacement can continue in communication link 1. If all communication factors in communication link 1 have been replaced, but the verification result indicates that it is not feasible in the communication network configuration, then initial configuration factor 1 is randomly replaced in other communication links, such as communication link 2, communication link 3, etc., until the verification result of a random configuration factor indicates that it is feasible, then the replacement stops, or after reaching a preset number of iterations, the replacement stops.

[0099] In some embodiments, the random replacement object of the degradation operation can be all communication factors, or communication factors with a factor cost smaller than the initial configuration factor, or communication factors with a factor weight value lower than the initial configuration factor, or communication factors with a factor cost-effectiveness lower than the initial configuration factor, depending on the actual situation.

[0100] Step S403: Repeat the iterative optimization process until the preset number of iterations is reached, then stop the iteration and output the optimization configuration factor for each communication link.

[0101] In some embodiments, a preset number of iterations can be set. The preset number of iterations can be set according to the network size of the communication network, or it can be set randomly or by technicians.

[0102] In some embodiments, the iteration optimization process is repeated until a preset number of iterations is reached, such as 10, then the iteration stops and the optimization configuration factor for each communication link is output.

[0103] Please refer to Figure 6 In some embodiments, local optimization processing is performed on each initial configuration factor in the corresponding communication link to obtain a local configuration factor, including but not limited to steps S501 to S504:

[0104] Step S501: In each communication link, iterate through the factor costs of each communication factor.

[0105] In some embodiments, by iterating through the factor costs of each communication factor, the communication factor corresponding to the lower factor cost can be selected, thereby using the lowest possible factor cost and reducing the consumption of transmission resources.

[0106] Step S502: Compare the factor costs of the initial configuration factor and the communication factor, and select the communication factor with a factor cost lower than that of the initial configuration factor as the candidate configuration factor.

[0107] In some embodiments, the initial configuration factor and other communication factors can be compared in the current communication process, and communication factors with lower costs than the initial configuration factor can be selected as candidate configuration factors. It is understood that if there are no communication factors with lower costs than the initial configuration factor in the current communication process, the initial configuration factor is directly output as a local configuration factor; if there are multiple communication factors with lower costs than the initial configuration factor in the current communication process, the communication factor with the lowest cost is selected as a candidate configuration factor, or multiple communication factors with lower costs than the initial configuration factor can be output as candidate configuration factors.

[0108] Step S503: Perform feasibility verification on the alternative configuration factors to obtain the first verification result.

[0109] In some embodiments, to verify whether alternative configuration factors are usable in a communication network, feasibility verification can be performed on the alternative configuration factors. In some embodiments, a network management system or specialized testing tools can be used to perform real-time testing on each alternative configuration factor or its corresponding communication link.

[0110] It is understood that different verification methods may be used to verify the feasibility of alternative configuration factors for different use cases, and this application embodiment does not impose specific restrictions on this.

[0111] In some embodiments, the first verification result is used to characterize whether it is feasible to configure the communication network using the current alternative configuration factors.

[0112] Step S504: If the first verification result indicates that the alternative configuration factor is feasible in the communication network configuration, the alternative configuration factor replaces the initial configuration factor and is output as a local configuration factor.

[0113] In some embodiments, if there is one alternative configuration factor, then after the first verification result indicates that the alternative configuration factor is feasible, the alternative configuration factor is output as a local configuration factor; if the alternative configuration factor is not feasible, then the initial configuration factor is output as a local configuration factor.

[0114] In some embodiments, if there are multiple alternative configuration factors, then for the first verification result that represents a feasible alternative configuration factor, the alternative configuration factor with the lowest factor cost is output as a local configuration factor.

[0115] It is understandable that outputting the alternative configuration factor with the lowest factor cost as a local configuration factor can save transmission resources as much as possible.

[0116] Please refer to Figure 7 In some embodiments, step S104 includes, but is not limited to, steps S601 to S604:

[0117] Step S601: Using the optimized configuration factor as the search center, search for communication factors within adjacent communication links.

[0118] In some embodiments, in order to fully consider the distribution of random variables and find the optimal configuration of communication factors as much as possible, the optimal configuration factor can be used as the search center, or the current communication link can be used as the search center to search for communication factors in adjacent communication links, or any communication factor in the communication network can be randomly searched to obtain multiple candidate configuration factors.

[0119] Step S602: Based on the optimization configuration factor, randomly replace the optimization configuration factor in at least two communication links simultaneously to obtain multiple replacement factors.

[0120] In some embodiments, communication factors in two communication links can be randomly replaced simultaneously based on the optimized configuration factor, or communication factors in the communication network whose factor cost is less than the optimized configuration factor can be randomly replaced to obtain multiple replacement factors.

[0121] Step S603: In the communication link corresponding to the optimized configuration factor, the feasibility of multiple replacement factors is verified to obtain the second verification result.

[0122] In some embodiments, to verify whether the replacement factor can be used normally in the communication network, a feasibility verification can be performed on the replacement factor. In some embodiments, a network management system or specialized detection tools can be used to perform real-time detection on each replacement factor or the corresponding communication link.

[0123] In some embodiments, a corresponding threshold can be set according to the network requirements and performance indicators. When the performance data of a communication link exceeds the preset threshold, it indicates that the replacement factor of that communication link is unavailable.

[0124] It is understood that different verification methods may be used to verify the feasibility of the replacement factor for different use cases, and the embodiments of this application do not impose specific restrictions on this.

[0125] In some embodiments, the second verification result can be used to characterize whether the replacement factor is available.

[0126] Step S604: If the second verification result indicates that multiple replacement factors are feasible in the communication network configuration, output the multiple replacement factors as candidate configuration factors.

[0127] In some embodiments, if the second verification result indicates that the replacement factor is feasible in the communication network configuration, then the replacement factor indicated as feasible is output as a candidate configuration factor. If it is partially feasible and partially infeasible, then the replacement factor indicated as feasible and the original optimized configuration factor are output as candidate configuration factors, and the replacement factor indicated as infeasible is filtered out.

[0128] It is understandable that if there is no feasible replacement factor in the current communication process, then the optimization configuration factor will be used as a candidate configuration factor.

[0129] Please refer to Figure 8 In some embodiments, step S105 includes, but is not limited to, steps S701 to S704:

[0130] Step S701: For each communication link, obtain the factor cost and delay confidence of each candidate configuration factor.

[0131] Understandably, when configuring a communication network, a high latency confidence level means that the configuration of the communication network can guarantee the stability and reliability of data transmission. Therefore, the latency confidence level of each candidate configuration factor should be given priority, and then the cost should be minimized to avoid solutions that do not meet the constraints due to excessive pursuit of cost minimization.

[0132] In some embodiments, the latency confidence level can be determined by setting a latency threshold. For example, if the threshold is set to less than 20 milliseconds, and there are 99.99% of the latency periods that are less than 20 milliseconds, then the latency confidence level for latency periods less than 20 milliseconds is 99.99%.

[0133] In some embodiments, the factor cost and latency confidence of each candidate configuration factor can be obtained in order to comprehensively consider each candidate configuration factor.

[0134] Step S702: Obtain the preset latency confidence threshold, select candidate configuration factors whose latency confidence is greater than the latency confidence threshold, and then select the candidate configuration factor with the lowest factor cost as the target configuration factor.

[0135] In some embodiments, the latency confidence threshold can be preset according to the performance of different communication networks. Specifically, it can be generated according to the latency confidence command generated by the control module, or a default latency confidence threshold can be selected or set manually. This application embodiment does not impose specific limitations on this.

[0136] In some embodiments, if the latency confidence threshold is 0.99, then the candidate configuration factors are screened to obtain candidate configuration factors with a latency confidence greater than 0.99, such as candidate configuration factors with a latency confidence of 0.995.

[0137] In some embodiments, due to limited sample size, candidate allocation factors can be screened based on time delay confidence and then further screened based on factor cost. Specifically, the candidate allocation factor with the lowest factor cost can be selected and output as the target allocation factor.

[0138] Understandably, at this point, the feasibility of the target configuration factor can be verified again to ensure the reliability of the results.

[0139] Alternatively, in step S703, multiple candidate configuration factors are ranked according to factor cost and latency confidence to obtain a factor cost ranking list and a latency confidence ranking list; a first score is generated for each candidate configuration factor based on the factor cost ranking list; a second score is generated for each candidate configuration factor based on the latency confidence ranking list; the first and second scores of each candidate configuration factor are added together to obtain multiple total configuration scores; and the candidate configuration factor corresponding to the highest total configuration score is selected as the target configuration factor.

[0140] In some embodiments, the factor cost can be assigned a decreasing score according to its ranking in the factor cost ranking list and the latency confidence ranking list, so as to generate a first score based on the factor cost ranking list and a second score based on the latency confidence ranking list. The first score and the second score are added together to obtain multiple total configuration scores. In each communication link, the candidate configuration factor with the highest total configuration score is selected as the target configuration factor.

[0141] For example, if there are 30 candidate configuration factors, to obtain the total configuration score of candidate configuration factor #1, one can obtain the scores of candidate configuration factor #1 in both the factor cost ranking list and the latency confidence ranking list. If candidate configuration factor #1 ranks 2nd in the factor cost ranking list and 18th in the latency confidence ranking list, then the total configuration score is 29 + 13 = 42 points. It can be understood that the factor cost ranking list in the above example is sorted from low to high based on factor cost, and the latency confidence ranking list is sorted from high to low based on latency confidence.

[0142] In some embodiments, the ranking method of the factor cost ranking list and the time delay confidence ranking list can be adjusted according to the actual situation. The first score and the second score can be assigned by decreasing or increasing scores. This application embodiment does not impose specific restrictions on this.

[0143] In some embodiments, candidate configuration factors can be scored according to preset scoring rules. For example, different delay confidence levels can be assigned different scores in different intervals of a preset delay confidence threshold, and different factor costs can be assigned different scores in different factor cost intervals, and so on.

[0144] Alternatively, in step S704, select multiple candidate configuration factors corresponding to the top N rankings of the factor cost ranking list and / or the time delay confidence ranking list, and select the target configuration factor from the multiple candidate configuration factors; where N is a positive integer greater than or equal to 2.

[0145] In some embodiments, if the factor costs are sorted from low to high, the top 5 rankings of the factor cost ranking list can be selected, and the target configuration factor can be selected by a technician or randomly selected according to the control instructions issued by the control module.

[0146] In some embodiments, if the time delay confidence is sorted from high to low, the top 5 rankings of the factor cost ranking list can be selected, and the target configuration factor can be selected by a technician or randomly selected according to the control instructions issued by the control module.

[0147] In some embodiments, after selecting five candidate allocation factors from the factor cost list, the ranking of these five candidate allocation factors in the delay confidence ranking list is queried, and the candidate allocation factor with the highest delay confidence is selected as the target allocation factor. Alternatively, five candidate allocation factors can be selected first from the delay confidence ranking list, and then the ranking of these five candidate factors in the factor cost list is queried, selecting the candidate allocation factor with the lowest cost as the target allocation factor.

[0148] In some embodiments, ranking weights can be set to filter target configuration factors. Specifically, the ranking of a candidate configuration factor in the time-delay confidence ranking list can be set to account for 75% of the weight, and the ranking in the factor cost list can be set to account for 25% of the weight. The final score is calculated based on the actual ranking and ranking weight of the candidate configuration factor in the time-delay confidence ranking list and the factor cost list, and the target configuration factor is selected based on the final score.

[0149] It is understood that the solutions in the above embodiments can be used randomly and alternately, or in combination. The specific method can be selected according to the application scenario, and the embodiments of this application do not impose specific restrictions on this.

[0150] Please refer to Figure 9 The embodiments of this application are implemented through Figure 9 This section provides an overview of communication network configuration methods.

[0151] In some embodiments, a greedy search can be performed based on the cost-effectiveness of factors to construct feasible initial configuration factors for each communication link. Then, an iterative optimization process is executed based on these initial configuration factors. This iterative optimization process includes local optimization (locally searching for and exchanging communication factors) to improve the quality of the current solution. That is, the initial configuration factors may not be optimal, and the optimal solution for each communication link can be sought through iterative optimization. Furthermore, after local optimization, to avoid the updated solution getting trapped in local optima, a degradation operation can be performed. This degradation operation involves randomly replacing communication factors in the current communication link and verifying the feasibility of the replaced communication factors. If the verification result indicates that the corresponding communication factor is feasible in the communication network configuration, then the communication factor is used as the optimized configuration factor. It is understood that the iterative optimization process can be performed based on factor cost; that is, communication factors with lower costs than the initial configuration factors are randomly replaced. Furthermore, the iterative optimization process can be repeated continuously, i.e., the local optimization process and degradation operation can be repeated until a preset number of iterations is reached, at which point the iteration stops, and the optimized configuration factor for each communication link is output.

[0152] In some embodiments, due to the randomness of random variables, the optimal communication configuration factor may appear in other links of the communication network. In this case, a deep exchange search can be performed, with at least two communication links simultaneously performing random replacement of the communication factor. This not only improves search efficiency but also increases the likelihood of finding a better solution.

[0153] In some embodiments, target configuration factors can be screened using latency confidence and factor costs to more comprehensively evaluate candidate configuration factors, thereby selecting the target configuration factor. It is understood that during the screening process, latency confidence should be ensured first to guarantee the feasibility of the solution, and factor costs should be considered only secondarily.

[0154] In some embodiments, after outputting the target configuration factor, the communication network is configured according to the target configuration factor.

[0155] In some embodiments, this application generates test samples based on parameters from a telecommunications company's actual business scenario. It assumes that the distribution of latency for different configuration samples in the 5G E2E network link satisfies five common continuous distributions (uniform distribution, truncated normal distribution, fatigue life distribution, bimodal distribution, and gamma distribution), and introduces a retransmission mechanism, meaning that each transmission exceeding a certain time will be considered a failure and require retransmission, further enhancing the algorithm's solution capabilities. The test problem is set to 10 stages, with 20 communication factors available for each stage, and a sample size of 500 for each communication factor. The confidence constraint P0 is set to 99%. Simultaneously, this application also tests the following comparative methods:

[0156] 1) Method A: A method based on greedy search;

[0157] 2) Method B: A method based on genetic algorithm construction;

[0158] 3) Method C: A method based on the distribution estimation algorithm.

[0159] Each of the three methods was run 10 times, and the results were recorded as “mean ± standard deviation”.

[0160] Tables 1 and 2 show the different T values ​​respectively. max The results of each method are set, with different T values. max This represents the proportion of different real feasible solutions in the entire solution space. Experimental results show that the algorithm proposed in this application can obtain the network configuration scheme with the lowest cost and high latency confidence while ensuring that the proportion of feasible solutions is 1.

[0161] It is understandable that T in Tables 1 and 2 max The time delay threshold is used. Tables 1 and 2 show the performance comparison of this application and different algorithms under different time delay thresholds.

[0162]

[0163] Table 1. Performance comparison of different algorithms on test samples.

[0164]

[0165]

[0166] Table 2 shows the performance comparison of different algorithms on the test samples.

[0167] Please see Figure 10 This application also provides a communication network configuration system that can implement the above-described communication network configuration method. The communication network configuration system includes:

[0168] The factor cost-effectiveness calculation module 1001 obtains multiple communication factors for each communication link in the communication network and calculates the factor cost-effectiveness of each communication factor.

[0169] The initial configuration factor acquisition module 1002 is used to perform a greedy search in each communication link based on the factor cost-effectiveness, obtain the greedy search result, and determine the initial configuration factor of each communication link based on the greedy search result.

[0170] The optimized configuration factor output module 1003 is used to obtain the factor cost of each communication factor, perform iterative optimization processing on the initial configuration factor of each communication link according to the factor cost, stop the iteration after reaching the preset number of iterations, and output the optimized configuration factor of each communication link.

[0171] The candidate configuration factor acquisition module 1004 is used to randomly replace the optimized configuration factors of at least two communication links with the optimized configuration factors as the search center, so as to obtain multiple candidate configuration factors corresponding to each communication link.

[0172] The target configuration factor acquisition module 1005 is used to calculate the delay confidence for each communication link, and to select the target configuration factor for each communication link based on the factor cost and delay confidence of each candidate configuration factor.

[0173] The communication network configuration module 1006 is used to configure the communication network based on multiple target configuration factors.

[0174] The specific implementation of this communication network configuration system is basically the same as the specific embodiments of the communication network configuration method described above, and will not be repeated here. Subject to meeting the requirements of the embodiments of this application, the communication network configuration system may also be equipped with other functional modules to implement the communication network configuration method in the above embodiments.

[0175] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described communication network configuration method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0176] Please see Figure 11 , Figure 11 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0177] The processor 1101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0178] The memory 1102 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1102 and is called and executed by the processor 1101 using the communication network configuration method of the embodiments of this application.

[0179] Input / output interface 1103 is used to implement information input and output;

[0180] The communication interface 1104 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0181] Bus 1105 transmits information between various components of the device (e.g., processor 1101, memory 1102, input / output interface 1103, and communication interface 1104);

[0182] The processor 1101, memory 1102, input / output interface 1103 and communication interface 1104 are connected to each other within the device via bus 1105.

[0183] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described communication network configuration method.

[0184] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0185] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0186] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0187] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0188] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0189] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0190] It should be understood that in this application, "at least one" and "several" refer to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0191] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0192] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0193] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0194] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0195] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method of configuring a communication network, characterized by, The method includes: Multiple communication factors are obtained for each communication link in the communication network, and the sample mean and sample standard deviation of the factor samples are calculated for each communication factor; the factor weight value of the communication factor is calculated based on the sample mean and sample standard deviation; the largest factor cost in the communication network is selected as the reference cost; the factor cost-effectiveness of the communication factor is obtained by dividing the difference between the reference cost and the factor cost by the factor weight value, wherein each communication factor includes multiple factor samples; Based on the cost-effectiveness of the factors, a greedy search is performed in each of the communication links to obtain the greedy search result, and the initial configuration factor of each of the communication links is determined according to the greedy search result. Obtain the factor cost of each of the communication factors, perform an iterative optimization process on the initial configuration factor of each of the communication links based on the factor cost, stop the iteration after reaching a preset number of iterations, and output the optimized configuration factor of each of the communication links. Using the optimized configuration factor as the search center, the optimized configuration factor of at least two of the communication links is randomly replaced to obtain multiple candidate configuration factors corresponding to each of the communication links. For each of the communication links, the delay confidence is calculated, and the target configuration factor for each of the communication links is selected based on the factor cost of each candidate configuration factor and the delay confidence. The communication network is configured based on several target configuration factors.

2. The communication network configuration method according to claim 1, characterized in that, The method further includes: Obtain the sample latency for each of the aforementioned factor samples; Based on the sample delay, the factor samples are sorted in each of the communication factors to obtain a sorting result, and the factor sample with the largest sample delay is selected from the sorting result as the target factor sample. The total sample delay is obtained by adding the target factor samples of multiple communication factors. If the total sample latency is greater than a preset latency threshold, the multiple communication factors corresponding to the total sample latency are filtered out.

3. The communication network configuration method according to claim 1, characterized in that, The process of obtaining the factor cost of each communication factor, performing iterative optimization on the initial configuration factors of each communication link based on the factor cost, stopping the iteration after reaching a preset number of iterations, and outputting the optimized configuration factor of each communication link includes: Obtain the factor cost of the communication factor; Based on the factor cost, an iterative optimization process is performed on multiple initial configuration factors. The iterative optimization process includes: performing local optimization on each initial configuration factor in the corresponding communication link to obtain a local configuration factor; randomly selecting at least one communication link and randomly selecting a communication factor from the communication link to randomly replace the local configuration factor to obtain a random configuration factor; performing feasibility verification on the random configuration factor to obtain a verification result; if the verification result indicates that the random configuration factor is feasible in the communication network configuration, then the random configuration factor is output as an optimized configuration factor; if the verification result indicates that the random configuration factor is not feasible in the communication network configuration, then the random replacement of the communication factor continues in the communication link until the communication factor in the communication link is completely replaced, and then a communication link is randomly selected to replace the local configuration factor. Repeat the iterative optimization process until the preset number of iterations is reached, then stop the iteration and output the optimization configuration factor for each communication link.

4. The communication network configuration method according to claim 3, characterized in that, The step of performing local optimization processing on each of the initial configuration factors in the corresponding communication link to obtain local configuration factors includes: In each of the communication links, the factor cost of each of the communication factors is traversed; The initial configuration factor and the communication factor are compared by factor cost, and the communication factor with a factor cost lower than the initial configuration factor is selected as the candidate configuration factor; The feasibility of the alternative configuration factors was verified, and a first verification result was obtained. If the first verification result indicates that the alternative configuration factor is feasible in the communication network configuration, the alternative configuration factor is used to replace the initial configuration factor and output as a local configuration factor.

5. The communication network configuration method according to claim 1, characterized in that, The step of using the optimized configuration factor as the search center and simultaneously randomly replacing the optimized configuration factor of at least two of the communication links to obtain multiple candidate configuration factors corresponding to each of the communication links includes: Using the optimized configuration factor as the search center, search for the communication factor within the adjacent communication links; Based on the optimized configuration factor, the optimized configuration factor in at least two of the communication links is randomly replaced to obtain multiple replacement factors. In the communication link corresponding to the optimized configuration factor, the feasibility of multiple replacement factors is verified to obtain a second verification result; If the second verification result indicates that the multiple replacement factors are feasible in the communication network configuration, the multiple replacement factors are output as candidate configuration factors.

6. The communication network configuration method according to claim 1, characterized in that, For each of the communication links, a delay confidence level is calculated, and a target configuration factor for each communication link is selected based on the factor cost of each candidate configuration factor and the delay confidence level, including: For each of the communication links, obtain the factor cost and delay confidence of each of the candidate configuration factors; Obtain a preset latency confidence threshold, select candidate configuration factors whose latency confidence is greater than the latency confidence threshold, and then select the candidate configuration factor with the lowest factor cost as the target configuration factor. Alternatively, the candidate configuration factors are ranked according to their factor costs and latency confidence levels to obtain a factor cost ranking list and a latency confidence level ranking list; a first score is generated for each candidate configuration factor based on the factor cost ranking list; a second score is generated for each candidate configuration factor based on the latency confidence level ranking list; the first and second scores of each candidate configuration factor are added together to obtain multiple total configuration scores; and the candidate configuration factor with the highest total configuration score is selected as the target configuration factor. Alternatively, select the top N rankings of the factor cost ranking list and / or the time delay confidence ranking list, corresponding to multiple candidate configuration factors, and select the target configuration factor from the multiple candidate configuration factors; wherein, N is a positive integer greater than or equal to 2.

7. A communication network configuration system, characterized in that, The system includes: The factor cost-effectiveness calculation module acquires multiple communication factors for each communication link in the communication network, and calculates the sample mean and sample standard deviation of the factor samples for each communication factor; calculates the factor weight value of the communication factor based on the sample mean and sample standard deviation; selects the largest factor cost in the communication network as the reference cost; and obtains the factor cost-effectiveness of the communication factor by dividing the difference between the reference cost and the factor cost by the factor weight value, wherein each communication factor includes multiple factor samples. The initial configuration factor acquisition module is used to perform a greedy search in each of the communication links based on the factor cost-effectiveness, obtain the greedy search result, and determine the initial configuration factor of each of the communication links based on the greedy search result; An optimized configuration factor output module is used to obtain the factor cost of each of the communication factors, perform an iterative optimization process on the initial configuration factor of each of the communication links according to the factor cost, stop the iteration after reaching a preset number of iterations, and output the optimized configuration factor of each of the communication links. The candidate configuration factor acquisition module is used to randomly replace the optimized configuration factor of at least two of the communication links with the optimized configuration factor as the search center, so as to obtain multiple candidate configuration factors corresponding to each of the communication links. The target configuration factor acquisition module is used to calculate the delay confidence for each of the communication links, and to select the target configuration factor for each of the communication links based on the factor cost of each candidate configuration factor and the delay confidence. The communication network configuration module is used to configure the communication network according to multiple target configuration factors.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the communication network configuration method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the communication network configuration method according to any one of claims 1 to 6.

Images