Network optimization method, network optimization system, communication device and storage medium

Abstract

The embodiment of the invention provides a network optimization method, a network optimization system, a communication device and a storage medium, relates to the technical field of communication, and is used for improving the accuracy of network optimization. The network optimization method comprises the steps of determining a to-be-optimized first configuration parameter based on a network optimization requirement of a physical network; based on a digital twin network corresponding to the physical network, optimizing the first configuration parameter to obtain an optimal parameter value of the first configuration parameter; and issuing the optimal parameter value of the first configuration parameter to the physical network.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a network optimization method, a network optimization system, a communication device and a storage medium. Background Art

[0002] With the development of communication technology, there may be various network problems. In order to ensure the network performance, it is necessary to optimize the problem network. Network optimization is to determine the reasons that affect the network quality by analyzing, collecting and checking the hardware of the existing running network, and to ensure the high-quality operation of the network by modifying parameters or adjusting the network structure. In the process of network optimization, it is necessary to accurately analyze the network problems existing in the network and determine the corresponding solutions to the network problems in order to complete the network optimization.

[0003] At present, the system simulation method can be used to establish a model, and then the network optimization can be completed based on the model. However, due to the difficulty of network data collection and the inability to frequently adjust the wireless network parameters to ensure the stability of the wireless communication network, the authenticity of the created model is low, which in turn affects the accuracy of network optimization. Summary of the invention

[0004] The present application provides a network optimization method, a network optimization system, a communication device and a storage medium for improving the accuracy of network optimization.

[0005] In order to achieve the above purpose, this application adopts the following technical solutions:

[0006] In a first aspect, a network optimization method is provided, the method comprising:

[0007] Based on the network optimization requirements of the physical network, determine the first configuration parameter to be optimized;

[0008] Based on the digital twin network corresponding to the physical network, optimizing the first configuration parameter to obtain an optimal parameter value of the first configuration parameter;

[0009] The optimal parameter value of the first configuration parameter is sent to the physical network.

[0010] In a second aspect, a network optimization system is also provided, which includes a network optimization module, a digital twin module and an artificial intelligence module:

[0011] An artificial intelligence module, used for determining a first configuration parameter to be optimized based on a network optimization requirement of a physical network;

[0012] The digital twin module is used to build a digital twin network corresponding to the physical network based on the construction parameters of the physical network;

[0013] An artificial intelligence module, used to optimize the first configuration parameter based on the digital twin network corresponding to the physical network to obtain an optimal parameter value of the first configuration parameter;

[0014] The network optimization module is used to send the optimal parameter value of the first configuration parameter to the physical network.

[0015] In a third aspect, a communication device is also provided, which includes a memory and a processor; the memory and the processor are coupled; the memory is used to store instructions executable by the processor; when the processor executes the instructions, it performs a method as described in any one of the first aspects.

[0016] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed on a computer, the computer executes any one of the methods provided in the first aspect.

[0017] According to a fifth aspect, a computer program product comprising computer instructions is provided. When the computer instructions are executed on a computer, the computer executes any one of the methods provided in the first aspect.

[0018] The present application provides a network optimization method, which can optimize the configuration parameters of the physical network in combination with the digital twin network to determine the configuration parameters that meet the current network optimization requirements. In this way, the digital twin network can be used to perform multiple high-level simulations of the physical network to be optimized during the optimization process, and the status of the digital twin network and the physical network can be obtained in real time to correct the digital twin network, so as to improve the efficiency and accuracy of network optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0020] Figure 1 A schematic diagram of a physical network provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the composition of a network optimization system provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a network optimization method provided in an embodiment of the present application;

[0023] Figure 4 A flowchart of another network optimization method provided in an embodiment of the present application;

[0024] Figure 5A schematic diagram of another network optimization system provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of an internal circulation process provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of an external circulation process provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of another external circulation process provided in an embodiment of the present application;

[0028] Fig. 9 A flowchart of another network optimization method provided in an embodiment of the present application;

[0029] Fig.10 A schematic diagram of another internal circulation process provided in an embodiment of the present application;

[0030] Fig.11 A schematic diagram of another internal circulation process provided in an embodiment of the present application;

[0031] Fig.12 A schematic diagram of the structure of a communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] 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.

[0033] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0034] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0035] To facilitate understanding, some basic concepts of terms or technologies involved in the embodiments of the present invention are first briefly introduced and explained.

[0036] Digital twin (DT) is a simulation process that integrates multiple disciplines, multiple physical quantities, multiple scales, and multiple probabilities using data such as physical models, sensor updates, and operation history. Based on digital twin technology, a physical device can be mapped into a virtual space to create a virtual model (or digital model) corresponding to the physical device. This virtual model can be called a "digital twin". A digital twin is a virtual representation of the real world, including physical objects, processes, relationships, and behaviors. It can reflect the entire life cycle of its corresponding physical device. It can use real-time data sent from sensors on the physical device and historical data on the operation of the physical device to simulate the behavior of the physical device.

[0037] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is also the study of the design principles and implementation methods of various intelligent machines, so that machines have the functions of perception, reasoning and decision-making. Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, basic AI theory, etc.

[0038] The above is an introduction to the technical terms involved in the embodiments of the present disclosure, which will not be repeated below.

[0039] In order to improve the accuracy of network optimization, an embodiment of the present application provides a network optimization method, which includes: determining a first configuration parameter to be optimized based on the network optimization requirements of the physical network, optimizing the first configuration parameter based on the digital twin network corresponding to the physical network, obtaining the optimal parameter value of the first configuration parameter, and sending the optimal parameter value of the first configuration parameter to the physical network. In this way, the digital twin network can be used to perform multiple high-level simulations on the physical network to be optimized during the optimization process, and the status of the digital twin network and the physical network can be obtained in real time to correct the digital twin network, so as to improve the efficiency and accuracy of network optimization.

[0040] A physical network is a network formed by connecting various physical devices (such as hosts, routers, switches, etc.) and media (optical cables, cables, twisted pairs, etc.) in the network. A physical network can include access networks for mobile communications and core networks. Alternatively, a physical network can also be a fixed communication network, etc.

[0041] like Figure 1 The physical network may include access networks, aggregation networks, and core networks. It may also include terminal devices, access switches, aggregation switches, and core switches. In some embodiments, the physical network may include network devices such as hubs, switches, bridges, routers, gateways, network interface cards, and wireless access points.

[0042] Among them, the access network refers to all the equipment between the backbone network and the user terminal, and is composed of a series of transmission entities between the service node interface and the user-network interface.

[0043] The core network can be composed of multiple functional units, which can be divided into functional entities of the control plane and the data plane, completing functions such as user access control, mobility management, session management, user security authentication, and billing. Among them, the access and mobility management function (AMF) is responsible for user access management, security authentication, and mobility management. The user plane function (UPF) is responsible for managing the transmission of user plane data, traffic statistics, and secure eavesdropping.

[0044] In some embodiments, the terminal device may be a device with wireless transceiver function, which may be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it may also be deployed on the water surface (such as ships, etc.); it may also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal may be a mobile phone, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present application do not limit the application scenarios. A terminal may sometimes also be referred to as a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication equipment, UE agent or UE device, etc., but the embodiments of the present application are not limited to this.

[0045] like Figure 2 As shown, the embodiment of the present application also provides a network optimization system, which can be applied to the above-mentioned mobile communication network. The network optimization system 200 may include a network optimization module 210, an artificial intelligence module 220, and a digital twin module 230. In some embodiments, the network optimization system 200 may also include a physical network 240.

[0046] In the embodiment of the present application, the network optimization module 210 is used to execute the network optimization method provided by the present application to analyze the network problems existing in the network and determine the solutions corresponding to the network problems.

[0047] In some embodiments, the network optimization module 210 also has intelligent decision-making functions, performance evaluation functions, and parameter delivery functions.

[0048] The intelligent decision-making function means that the network optimization module 210 can be used to judge the sub-service type according to the network optimization requirements of the physical network, and determine the sub-service type corresponding to the network optimization requirements, so as to complete the network optimization based on the sub-service type, such as traffic optimization service, interference optimization service, resource utilization service, etc.

[0049] In some embodiments, each sub-service type has its own corresponding artificial intelligence algorithm function, artificial intelligence algorithm structure and parameter configuration. The artificial intelligence algorithm structure includes a neural network structure, such as a convolutional network structure, or a non-neural network algorithm, such as Bayesian optimization, etc. Each sub-service type may also have a corresponding algorithm parameter setting, such as the number of iterations, optimization direction, etc.

[0050] In some embodiments, the network optimization module 210 can obtain a first digital twin result, which is a digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter, and when the first digital twin result meets the network optimization requirements, the optimal parameter value of the first configuration parameter is sent to the physical network.

[0051] In addition, the network optimization module 210 can also obtain the operation result of the physical network based on the optimal parameter value of the first configuration parameter; based on the relationship between the operation result and the first digital twin result, determine the adjustment strategy for the digital twin network; wherein the first digital twin result is the digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter. In the case where the operation result is inferior to the first digital twin result, the adjustment strategy includes performing performance correction processing on the digital twin network.

[0052] In addition, the network optimization module 210 may also send the adjustment strategy to the digital twin module 230, so that the digital twin module 230 may adjust the digital twin network according to the adjustment strategy.

[0053] In some embodiments, the network optimization module 210 can also obtain a first digital twin result, which is a digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter; when the first digital twin result meets the network optimization requirements, the optimal parameter value of the first configuration parameter is sent to the physical network.

[0054] In some embodiments, the network optimization module 210 can also receive a second digital twin result uploaded by the artificial intelligence module 220, and when the second digital twin result meets the network optimization requirements, send the optimal parameter value of the second configuration parameter to the physical network.

[0055] In some embodiments, the network optimization module 210 is also used to send the parameter value of a third configuration parameter to the physical network when the second digital twin result does not meet the network optimization requirements. The parameter value of the third configuration parameter is the parameter value of the configuration parameter corresponding to the optimal digital twin result between the first digital twin result and the second digital twin result.

[0056] The parameter sending function means that the network optimization module 210 can be used to send digital twin network configuration parameters to the digital twin module 230, send artificial intelligence configuration parameters to the artificial intelligence module 220, and send the optimal parameter value of the first configuration parameter to the physical network when the first configuration parameter is determined. Exemplarily, the network optimization module 210 can first determine the sub-service type corresponding to the network optimization requirement, and determine the artificial intelligence algorithm function, artificial intelligence algorithm structure and parameter configuration that need to be sent based on the sub-service type, and then send the determined parameters to the corresponding module.

[0057] The performance evaluation function means that the network optimization module 210 can be used to analyze and evaluate the network performance of the digital twin network and the physical network based on the collected data of the two networks.

[0058] In an embodiment of the present application, the artificial intelligence module 220 is used to determine the first configuration parameter to be optimized based on the network optimization requirements of the physical network, and optimize the first configuration parameter based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the first configuration parameter.

[0059] In some embodiments, the artificial intelligence module 220 also has artificial intelligence algorithm parameter configuration function, artificial intelligence optimization function, configuration distribution function and result reporting function, etc.

[0060] Among them, the artificial intelligence algorithm parameter configuration function refers to the artificial intelligence module 220 determining the artificial intelligence algorithm parameters for this network optimization based on the received network configuration module 210, and configuring the artificial intelligence functions or services corresponding to the artificial intelligence algorithm parameters. Among them, the artificial intelligence algorithm parameters include artificial intelligence algorithm functions, artificial intelligence algorithm structures, etc. The artificial intelligence algorithm structure includes a neural network structure, such as a convolutional network structure, etc. or a non-neural network algorithm, such as Bayesian optimization, etc. Each sub-service type can also have corresponding algorithm parameter settings, such as the number of iterations, optimization direction, etc.

[0061] In some embodiments, the artificial intelligence module 220 may also perform a preset number of iterations on the parameter value of the first configuration parameter to obtain multiple parameter values ​​of the first configuration parameter. The artificial intelligence algorithm parameters may also include an artificial intelligence training set, and the multiple parameter values ​​obtained by the iteration update may also constitute an artificial intelligence training set.

[0062] The artificial intelligence optimization function refers to the function of optimizing the first configuration parameter by the artificial intelligence module 220. The artificial intelligence module 220 can input the multiple parameter values ​​obtained by the above iterative update into the digital twin network, obtain the digital twin results corresponding to the parameter values ​​of the first configuration parameter after each iterative update, and then determine the optimal parameter value of the first configuration parameter in the digital twin results corresponding to the multiple parameters.

[0063] In some embodiments, the artificial intelligence module 220 can iteratively update the parameter value of the first configuration parameter a preset number of times; input the parameter value of the first configuration parameter after each iterative update into the digital twin network to obtain the digital twin result corresponding to the parameter value of the first configuration parameter after each iterative update; use the optimal digital twin result among the digital twin results corresponding to the parameter value of the first configuration parameter after each iterative update as the first digital twin result; use the parameter value of the first configuration parameter corresponding to the first digital twin result as the optimal parameter value of the first configuration parameter.

[0064] In some embodiments, the artificial intelligence module 220 can also optimize the second configuration parameters based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the second configuration parameter and the second digital twin result, where the second digital twin result is the digital twin result obtained by the digital twin network based on the optimal parameter value of the second configuration parameter.

[0065] The configuration sending function means that the artificial intelligence module 220 can send multiple parameter values ​​obtained by iteratively updating the first configuration parameters to the digital twin module.

[0066] The result reporting function refers to that the artificial intelligence module 220 determines the optimal parameter value of the first configuration parameter in the digital twin results corresponding to multiple parameters, and can report the optimal parameter value to the network optimization module 210.

[0067] In the embodiment of the present application, the digital twin module 230 is used to construct a digital twin network corresponding to the physical network based on the construction parameters of the physical network. In some embodiments, the digital twin module 230 also has a mirror mapping function, a simulation function, and a result reporting function.

[0068] Among them, the mirror mapping function means that the digital twin module 230 can determine the construction parameters of the digital twin network based on the configuration parameters of the physical network, and execute the process of digital twin mirror mapping to build a digital twin network corresponding to the physical network. In some embodiments, when a change in the physical state of the physical network is detected, the construction parameters of the digital twin network can also be updated to obtain updated construction parameters, and based on the mirror mapping function of the digital twin module 230, the digital twin network is rebuilt based on the updated construction parameters.

[0069] The simulation function means that the digital twin module 230 receives the parameter value obtained by iteratively updating the first configuration parameter sent by the artificial intelligence module 220 to the digital twin module, and adjusts and updates the network configuration information of the digital twin network based on the parameter value to configure a digital twin network that matches the parameter value.

[0070] The result reporting function means that the digital twin module 230 can report the digital twin results obtained after each iterative update to the artificial intelligence module 220.

[0071] In some embodiments, the network optimization system 200 may further include a physical network 240. The physical network 240 is configured to receive an optimal parameter value of a first configuration parameter and adjust the physical network based on the optimal parameter value of the first configuration parameter.

[0072] In some embodiments, the physical network 240 may have a business service function and a status reporting function.

[0073] The business service function refers to that the physical network 240 can adjust the physical network based on the business needs of the user, that is, the physical network is adjusted according to the optimal parameter value of the first configuration parameter determined by the network optimization requirement based on the business needs of the user.

[0074] The status reporting function means that the physical network 240 can periodically or event-basedly report the real physical network status to the network optimization module 210. Event-based reporting of the real physical network status to the network optimization module 210 refers to reporting triggered by an event occurring in the physical network, which may be an event in which the physical status of the physical network changes, an event in which the physical status of the physical network is detected, etc.

[0075] The network optimization method provided by the present application is described below in conjunction with the accompanying drawings.

[0076] like Figure 3 As shown, an embodiment of the present application provides a network optimization method, the method comprising:

[0077] S101. Determine a first configuration parameter to be optimized based on a network optimization requirement of a physical network.

[0078] In some embodiments, the network optimization requirement includes any one of the following: environment configuration requirement, resource utilization requirement, retransmission number requirement, capacity requirement, and service experience requirement.

[0079] Exemplarily, the environmental configuration requirements may be requirements related to the geographic information configuration of the physical network, requirements related to the system information configuration, requirements related to the frequency information configuration, or requirements related to the access configuration. The resource utilization requirements may be requirements related to the average utilization of the uplink / downlink physical resource blocks (PRBs) of the physical network, such as improving the average utilization of PRBs in the uplink. The number of retransmission requirements may be requirements related to the uplink / downlink packet loss rate of the physical network, requirements related to the uplink / downlink retransmission rate, such as reducing the downlink packet loss rate. The capacity requirements may be requirements related to the average throughput per PRB in the uplink / downlink of the physical network, such as improving the average throughput per PRB in the uplink. The service experience requirements may be requirements for traffic optimization, etc.

[0080] In some embodiments, the network optimization requirements of the physical network may be determined based on different types of network problem feedback or network requirement feedback information received. Different types of network problem feedback may include network problem feedback or network requirement feedback information from users, operators, network planning or network optimization engineers, etc.

[0081] For example, the above Figure 2 Taking the network optimization system 200 shown as an example, the users of the network optimization system 200 may include users, operators, network planners or network optimization engineers, etc. When the network optimization system 200 receives network demand feedback information input by a user, such as "how to speed up video downloading?", or network demand feedback information input by an operator, such as "how to obtain the maximum capacity?", or network demand feedback information input by a network planner or network optimization engineer, such as "how to configure the AMC algorithm or power control algorithm parameters to obtain the maximum uplink and downlink throughput?", it can be determined that the network optimization demand of the physical network is to obtain the maximum data volume without changing the physical state of the physical network.

[0082] In some embodiments, the first configuration parameter includes at least one of the following: geographic information configuration parameter, system information configuration parameter, frequency information configuration parameter, access configuration parameter, physical layer parameter, regulation algorithm parameter, power control algorithm parameter, adaptive modulation and coding (AMC) parameter.

[0083] In some embodiments, the target parameter is determined based on the network optimization requirement. Then, the first configuration parameter is determined from the configuration parameter set related to the target parameter. Exemplarily, taking the network optimization requirement of determining the physical network as obtaining the maximum amount of data without changing the physical state of the physical network as an example, the target parameter can be determined as a parameter determined based on the uplink and downlink throughput. The configuration parameters related to the uplink and downlink throughput may include power control algorithm parameters and AMC parameters, that is, the first configuration parameter may include the above-mentioned power control algorithm parameters and / or AMC parameters.

[0084] In some embodiments, the first configuration parameter can also be determined based on the degree of influence of each configuration parameter on the network optimization requirement, that is, the first configuration parameter is determined based on the degree of influence of each configuration parameter on the target parameter. Thus, based on the network optimization requirement of the physical network, one or more configuration parameters that can influence the target parameter related to the network optimization requirement can be determined as the first configuration parameter.

[0085] In some embodiments, multiple network optimization requirements may be received. Further, the multiple network optimization requirements may be sorted based on the optimization priorities of the respective network optimization requirements, and network optimization may be performed based on the first network optimization requirement with the highest optimization priority first. After the network optimization process is completed, network optimization may be performed based on the second network optimization requirement with the optimization priority second only to the first network optimization requirement, and so on, until network optimization of the network optimization requirement with the lowest optimization priority is completed.

[0086] In some embodiments, the construction parameters of the digital twin network can also be determined according to the construction parameters of the physical network, and then the digital twin network corresponding to the physical network can be constructed according to the determined construction parameters of the digital twin network. Furthermore, the first configuration parameter can be optimized based on the digital twin network corresponding to the physical network.

[0087] In some embodiments, the construction parameters of the above-mentioned digital twin network include one or more of network status configuration parameters, relevant algorithm parameters, and environmental parameters.

[0088] Among them, the network status configuration parameters include one or more of the network basic performance indicators KPI, cell load parameters, cell interference parameters, and user statistical characteristic parameters; the related algorithm parameters include one or more of the physical layer parameters, scheduling algorithm parameters, power control algorithm parameters, and adaptive coding modulation parameters; the environmental parameters include one or more of the geographical parameters, system parameters, frequency parameters, and access configuration parameters.

[0089] In some embodiments, the digital twin network may be constructed before executing the network optimization requirements based on the physical network and determining the first configuration parameter to be optimized. Alternatively, the digital twin network may be constructed before executing the following step S102 and optimizing the first configuration parameter.

[0090] In some embodiments, the physical state of the physical network can be periodically detected, and in response to detecting a change in the physical state of the physical network, the construction parameters of the digital twin network are updated to obtain updated construction parameters, and the digital twin network is reconstructed based on the updated construction parameters.

[0091] In some embodiments, in response to detecting a change in the physical state of the physical network, a first configuration parameter to be optimized may be determined based on a network optimization requirement of the physical network.

[0092] It should be noted that in the method provided in the embodiment of the present application, after the physical state of the physical network changes, the construction parameters of the digital twin network can be updated, thereby improving the authenticity of the digital twin network construction and avoiding the problem of simulation data errors caused by unstable physical network state.

[0093] S102. Optimize the first configuration parameter based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the first configuration parameter.

[0094] In some embodiments, the optimal parameter value refers to the parameter value of the first configuration parameter that best meets the network optimization requirements determined based on the digital twin network corresponding to the physical network.

[0095] In some embodiments, Figure 4 As shown, step S102 can be specifically implemented as the following steps S1021-S1024:

[0096] S1021. Iterate and update the parameter value of the first configuration parameter a preset number of times.

[0097] In some embodiments, the parameter value of the first configuration parameter after the i-th iteration update is determined based on the parameter value of the first configuration parameter after the i-1-th iteration update and the digital twin result corresponding to the parameter value after the i-1-th iteration update, where i is a positive integer.

[0098] In some embodiments, the parameter value of the first configuration parameter may be iteratively updated a preset number of times based on an artificial intelligence algorithm.

[0099] Based on the network optimization requirements, the artificial intelligence algorithm parameters can be determined, and then based on the artificial intelligence algorithm corresponding to the artificial intelligence algorithm parameters, the parameter value of the first configuration parameter can be iteratively updated a preset number of times. Among them, the artificial intelligence algorithm parameters include artificial intelligence algorithm functions, artificial intelligence algorithm structures, etc. In some embodiments, based on the network optimization requirements, the sub-service type corresponding to the network optimization requirements can be determined, and then based on the sub-service type, artificial intelligence algorithm parameters such as artificial intelligence algorithm functions and artificial intelligence algorithm structures can be determined.

[0100] For example, when the network optimization requirement of the physical network is to obtain the maximum amount of data without changing the physical state of the physical network, the sub-service type can be determined as a traffic optimization sub-service type, and its corresponding artificial intelligence algorithm function can be the following formula (1), and the artificial intelligence algorithm structure can be a hyperparameter optimization algorithm (Tree-structured Parzen Estimator, TPE) model.

[0101] In response to the network optimization requirements, it is necessary to determine the digital twin network configuration parameters with the maximum throughput. The target parameters can be determined based on the uplink and downlink throughputs. For example, the target parameters are determined as the sum of the downlink throughput with a weight of 1 / 2 and the uplink throughput with a weight of 1. The artificial intelligence algorithm function can be:

[0102]

[0103] Among them, Object is the target parameter determined based on the network optimization requirements, ul_throughput is the uplink throughput, and dl_throughput is the downlink throughput.

[0104] Furthermore, the configuration parameter with the highest degree of influence on the target parameter in the digital twin network can be selected as the first configuration parameter. For example, the downlink bit error rate parameter and the downlink AMC adjustment step size related to the AMC algorithm can be selected.

[0105] Thus, the initial parameter value and value range of the first configuration parameter can be determined first. For example, the initial parameter value is 0.0 for the downlink bit error rate, 0.75 for the downlink AMC adjustment step, and the value ranges of the downlink bit error rate and the downlink AMC adjustment step can be as shown in Table 1.

[0106] Table 1

[0107] Serial number First configuration parameter Value range 1 Downlink bit error rate 0,0.05,0.1,0.15,0.2,0.25,0.3 2 Downlink AMC adjustment step 0,0.1875,0.375,0.5625,0.75

[0108] Furthermore, the TPE model can fit a random model that conforms to historical data based on historical learning parameters, and perform a preset number of iterations to update the parameter value of the first configuration parameter. Exemplarily, based on the network optimization requirement of the physical network that obtains the maximum amount of data, the preset number of times can be 50 times, and the learning direction is "maximum value". Thus, the parameter value of the first configuration parameter can be iteratively updated 50 times, and the parameter values ​​of the first configuration parameter after iterative updates can be obtained 50 times.

[0109] S1022. Input the parameter value of the first configuration parameter after each iterative update into the digital twin network to obtain the digital twin result corresponding to the parameter value of the first configuration parameter after each iterative update.

[0110] In some embodiments, the digital twin result is used to indicate the network performance of the digital twin network related to the network optimization requirements. Exemplarily, the digital twin result can be characterized by the parameter value of the above-mentioned target parameter.

[0111] For example, the configuration parameters of the digital twin network can be updated and adjusted based on the parameter value configuration after the iterative update of the first configuration parameter. After the update of the digital twin network is completed, the parameter value of the target parameter obtained after this iteration is determined.

[0112] Taking the network optimization requirements of the physical network with the maximum data volume as an example, the system runs for 200 seconds at a time, each base station contains 3 cells, the number of users is 10, and the straight-line distance between each user and the base station is 9 meters. Based on the initial value of the first parameter, the downlink bit error rate is 0.0, the downlink AMC adjustment step is 0.75, and the downlink throughput is 123.15Mbps and the uplink throughput is 38.71Mbps. Based on the above formula (1), the parameter value of the target parameter is 100.28Mbps. Exemplarily, the parameter values ​​of the target parameters obtained by multiple iterative updates are shown in Table 2.

[0113] Table 2

[0114]

[0115]

[0116] In some embodiments, when the physical state of the physical network changes, the parameter value of the first configuration parameter after each iterative update can be used to reconstruct the digital twin network. The parameter values ​​of the target parameters obtained by multiple iterative updates are shown in Table 3.

[0117] Table 3

[0118]

[0119] S1023. Take the optimal digital twin result among the digital twin results corresponding to the parameter values ​​of the first configuration parameter after each iterative update as the first digital twin result.

[0120] Exemplarily, taking the network optimization requirement of the physical network with the maximum data volume as an example, when the parameter value after the seventh iteration is the best digital twin result among the digital twin results corresponding to the parameter value after the seventh iteration, the digital twin result corresponding to the parameter value after the seventh iteration can be the first digital twin result. Among them, the first configuration parameter is that the downlink bit error rate parameter is 0.25, the AMC adjustment step is 0.5625, and the maximum throughput result is 100.28Mbps.

[0121] Alternatively, based on the embodiment shown in Table 3 above, when the parameter value after the 45th iteration update is the best digital twin result among the digital twin results corresponding to the iteratively updated parameter value, the digital twin result corresponding to the parameter value after the 45th iteration update can be the first digital twin result. Among them, the first configuration parameter is that the downlink bit error rate parameter is 0.1, the AMC adjustment step is 0.1875, and the maximum throughput result is 23.07Mbps.

[0122] In some embodiments, Figure 2 In the network optimization system shown, after determining the first digital twin result, the artificial intelligence module 220 can report the first digital twin result and the parameter value of the first configuration parameter corresponding to the digital twin result to the network optimization module 210.

[0123] S1024. Use the parameter value of the first configuration parameter corresponding to the first digital twin result as the optimal parameter value of the first configuration parameter.

[0124] S103: Send the optimal parameter value of the first configuration parameter to the physical network.

[0125] In some embodiments, a first digital twin result is obtained, where the first digital twin result is a digital twin result obtained by the digital twin network based on an optimal parameter value of a first configuration parameter. When the first digital twin result meets the network optimization requirements, the optimal parameter value of the first configuration parameter is sent to the physical network.

[0126] It should be noted that the method provided in this application can also judge the first digital twin network based on network optimization requirements, and send configuration parameter values ​​when the requirements are met, which can further improve the accuracy of network optimization.

[0127] In one example, combining Figure 2 In the network optimization system shown in FIG. 1 , the process of determining the optimal parameter value of the first configuration parameter may be an inner loop process in the network optimization process. Figure 5 or Figure 6 As shown, the inner loop process includes the network optimization module 210 sending the configuration parameters of the digital twin network to the digital twin module 230, and sending the artificial intelligence algorithm parameters to the artificial intelligence module 220 based on the network optimization requirements. The artificial intelligence module 220 optimizes the first configuration parameter based on the artificial intelligence algorithm parameters, sends the parameter value of the first configuration parameter updated n times to the digital twin module 230, receives the digital twin result corresponding to the parameter value after each iterative update, and reports the best first digital twin result to the network optimization module 210. Then, when the first digital twin result meets the network optimization requirements, the optimal parameter value of the first configuration parameter is sent to the physical network, that is, the outer loop process is started.

[0128] In some embodiments, when the physical state of the physical network does not change, the optimal parameter value of the first configuration parameter is sent to the physical network.

[0129] In some embodiments, the optimal parameter value of the first configuration parameter may also be transmitted to the user.

[0130] In another example, combining Figure 2 The network optimization system shown in the figure, based on the inner loop, combines the network optimization module 210 and the data transmission process of the physical network 240 to form the outer loop process of the network optimization system. Figure 5 or Figure 7 As shown, the outer loop process includes the network optimization module 210 receiving the network optimization requirements input by the user, and transmitting the network optimization results to the user, that is, transmitting the optimal parameter value of the first configuration parameter. The network optimization module 210 can also send the optimal parameter value of the first configuration parameter to the physical network. And the physical network 240 reports the physical state of the physical network to the network optimization module 210, and the physical state of the physical network remains unchanged. In some embodiments, the physical network 240 can also report the operation results based on the optimal parameter value of the first configuration parameter to the network optimization module 210.

[0131] In some embodiments, when the physical state of the physical network changes, the digital twin network is reconstructed. At this time, the configuration parameters of the physical network can also be optimized again based on the reconstructed digital twin network to obtain the optimal parameter value of the first configuration parameter.

[0132] In another example, combining Figure 2 The network optimization system shown in Figure 8 As shown, when the physical state of the physical network changes, Figure 7 On the basis of the embodiment shown, multiple inner circulation processes can be started.

[0133] The present application provides a network optimization method, which can optimize the configuration parameters of the physical network in combination with the digital twin network to determine the configuration parameters that meet the current network optimization requirements. In this way, the digital twin network can be used to perform multiple high-level simulations of the physical network to be optimized during the optimization process, and the status of the digital twin network and the physical network can be obtained in real time to correct the digital twin network, so as to improve the efficiency and accuracy of network optimization.

[0134] In some embodiments, Fig. 9 As shown, the network optimization method provided in the embodiment of the present application also includes the following steps:

[0135] S201. When the first digital twin result does not meet the network optimization requirements, determine the second configuration parameters to be optimized based on the network optimization requirements.

[0136] In some embodiments, the first configuration parameter and the second configuration parameter differ in at least one of the following: parameter type, parameter value range, and parameter number.

[0137] In one example, taking the network optimization requirement of the physical network for obtaining the maximum data volume as an example, since the optimization requirement is to determine the maximum data volume, in order to determine whether the data volume can be further increased, the parameter selection range can be expanded to determine the second configuration parameter to be optimized. For example, the target receiving power and the partial path loss compensation related parameters can be added to the first configuration parameter to obtain the second configuration parameter. That is, the second configuration parameter is the downlink bit error rate, the downlink AMC adjustment step size, the target receiving power, and the partial path loss compensation related parameters.

[0138] S202. Based on the digital twin network corresponding to the physical network, optimize the second configuration parameters to obtain the optimal parameter value of the second configuration parameter and the second digital twin result.

[0139] Among them, the second digital twin result is a digital twin result obtained by the digital twin network based on the optimal parameter value of the second configuration parameter.

[0140] Exemplarily, taking the network optimization requirement of the physical network for obtaining the maximum data volume as an example, the second configuration parameters are the downlink bit error rate, the downlink AMC adjustment step size, the target receiving power, and the parameters related to partial path loss compensation.

[0141] The value ranges of the downlink bit error rate, downlink AMC adjustment step size, target receiving power, and partial path loss compensation related parameters can be shown in Table 4.

[0142] Table 4

[0143] Serial number Configuration parameters Value range 1 Downlink bit error rate 0,0.05,0.1,0.15,0.2,0.25,0.3 2 Downlink AMC adjustment step 0,0.1875,0.375,0.5625,0.75 3 Target received power -220,-210,-100,-90,-80,-70,-60 4 Partial path loss compensation related parameters 0,1,2,3,4,5,6,7,8

[0144] In one example, the initial value of the second configuration parameter may be a downlink bit error rate of 0, a downlink AMC adjustment step of 0.75, a target received power of -70 dBm, and a partial path loss compensation related parameter of 0.

[0145] Thus, based on the relevant description of step S1021 above, the artificial intelligence algorithm structure is a TPE model, which can fit a random model that conforms to historical data based on historical learning parameters, and iterate and update the parameter value of the second configuration parameter a preset number of times. Exemplarily, the preset number of times can be 50 times, and the learning direction is "maximum value". Thus, the parameter value of the second configuration parameter can be iteratively updated 50 times, and the parameter values ​​of the first configuration parameter after iterative update can be obtained 50 times respectively.

[0146] Furthermore, the parameter value of the second configuration parameter after each iteration update can also be input into the digital twin network to obtain the digital twin result corresponding to the parameter value of the second configuration parameter after each iteration update. The best digital twin result among the digital twin results corresponding to the parameter value of the second configuration parameter after each iteration update is used as the second digital twin result.

[0147] Exemplarily, the parameter values ​​of the target parameters obtained by multiple iterations are shown in Table 5, where the downlink throughput determined based on the initial value of the second configuration parameter is 123.12 Mbps, and the uplink throughput is 1.72 Mbps. Based on formula (1), the parameter value of the target parameter can be determined to be 63.29 Mbps.

[0148] Table 5

[0149]

[0150]

[0151] Furthermore, when the parameter value after the 18th iteration update is the best digital twin result among the digital twin results corresponding to the second configuration parameter value after the iteration update, the digital twin result corresponding to the parameter value after the 18th iteration update can be determined as the second digital twin result. Among them, the second configuration parameter is that the downlink bit error rate parameter is 0.1, the AMC adjustment step is 0.5625, the target receiving power is -60dBm, the partial path loss compensation related parameter is 5, and the maximum throughput result that can be obtained is 100.28Mbps.

[0152] That is, the optimal parameter values ​​of the second configuration parameters are that the downlink bit error rate parameter is 0.1, the AMC adjustment step is 0.5625, the target receiving power is -60dBm, and the partial path loss compensation related parameter is 5.

[0153] In one example, based on the embodiment shown in Table 3 above, the second configuration parameter may be a downlink bit error rate, a downlink AMC adjustment step size, and a physical uplink control channel power control parameter. Further, the parameter values ​​of the target parameters obtained by multiple iterations are shown in Table 6.

[0154] Table 6

[0155]

[0156] Furthermore, when the parameter value after the 0th iteration update is the best digital twin result among the digital twin results corresponding to the second configuration parameter value after the iteration update, the digital twin result corresponding to the parameter value after the 0th iteration update can be the second digital twin result. Among them, the second configuration parameter is the downlink bit error rate parameter is 0.1, the downlink AMC adjustment step is 0.5625, the target receiving power is -60dBm, the partial path loss compensation related parameter is 5, and the maximum throughput result that can be obtained is 21.57Mbps.

[0157] That is, the optimal parameter values ​​of the second configuration parameters are that the downlink bit error rate parameter is 0.1, the AMC adjustment step is 0.5625, the target receiving power is -60dBm, and the partial path loss compensation related parameter is 5.

[0158] In addition, a more detailed description of the technical features in step S202 can refer to the relevant description in the above-mentioned step S102, which will not be repeated here.

[0159] S203. When the second digital twin result meets the network optimization requirements, the optimal parameter value of the second configuration parameter is sent to the physical network.

[0160] In some embodiments, when the second digital twin result does not meet the network optimization requirements, the parameter value of the third configuration parameter is sent to the physical network, and the parameter value of the third configuration parameter is the parameter value of the configuration parameter corresponding to the best digital twin result between the first digital twin result and the second digital twin result.

[0161] Exemplarily, based on the embodiment shown in Table 6 above, the maximum throughput result 21.57 Mbps that can be obtained in the second digital twin result of the digital twin result corresponding to the parameter value updated after the 0th iteration, and the maximum throughput result 21.90 Mbps that can be obtained in the first digital twin result, thus, the parameter values ​​​​corresponding to the first digital twin result, the downlink bit error rate parameter 0.1, and the downlink AMC adjustment step 0.1875, can be determined as the parameter values ​​​​of the third configuration parameter, and the parameter values ​​​​of the third configuration parameter are sent to the physical network.

[0162] In some embodiments, when the second digital twin result does not meet the network optimization requirements, the configuration parameters to be optimized can be updated again based on the network optimization requirements to execute the above optimization process again until the digital twin result meets the network optimization requirements.

[0163] In some embodiments, Figure 6 On the basis of Fig.10 As shown, if the first digital twin result does not meet the network optimization requirements, the inner loop process can be executed again. Furthermore, if the second digital twin result does not meet the network optimization requirements, the inner loop process can be executed for the third time... until the digital twin result meets the network optimization requirements, and the outer loop process is started.

[0164] Based on the above embodiment, when the digital twin result does not meet the requirements, the "inner loop" process can be re-executed multiple times, so that the accuracy of network optimization can be further improved.

[0165] In some embodiments, Fig.11 As shown, the network optimization method provided in the embodiment of the present application may also include the following steps:

[0166] S301. Obtain an operation result of a physical network based on an optimal parameter value of a first configuration parameter.

[0167] In some embodiments, the operation result is used to indicate the network performance of the physical network related to the network optimization requirements. Exemplarily, the operation result can be represented by the parameter value of the above target parameter.

[0168] Exemplarily, taking the above-mentioned network optimization requirement of obtaining the maximum data volume of the physical network as an example, the target parameter can be determined based on the uplink and downlink throughput.

[0169] In some embodiments, when the first digital twin result does not meet the network optimization requirements, the operation result of the physical network based on the optimal parameter value of the second configuration parameter can also be obtained. Of course, the operation result of the physical network based on the optimal parameter value of the third configuration parameter can also be obtained. Then, based on the relationship between the operation result and the corresponding digital twin result, the adjustment strategy for the digital twin network is determined.

[0170] S302: Determine an adjustment strategy for the digital twin network based on the relationship between the operation result and the first digital twin result.

[0171] Among them, the first digital twin result is a digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter.

[0172] In some embodiments, when the operation result is inferior to the first digital twin result, the adjustment strategy includes performing performance correction processing on the digital twin network. Furthermore, the above network optimization process can be performed again based on the digital twin network that has undergone performance correction processing to re-optimize the configuration parameters of the physical network to obtain the optimal parameter value of the first configuration parameter.

[0173] Alternatively, if the operation result is better than the first digital twin result, the network optimization process can be ended. In addition, the optimal parameter value of the first configuration parameter can be fed back to the user.

[0174] In some embodiments, the network optimization result may also be determined based on the relationship between the operation result and the operation result of the physical network in the previous network optimization cycle, wherein the operation result of the physical network in the previous network optimization cycle is the operation result of the physical network obtained by the last network optimization process based on the network optimization requirements.

[0175] In one example, the operation result is that the maximum throughput that can be obtained is 95.72Mbps, and the physical network obtained by the previous network optimization process is that the maximum throughput that can be obtained is 75Mbps, so the network optimization process can be ended. In addition, the optimal parameter value of the configuration parameter can also be fed back to the user. For example, the optimal parameter value can include a downlink bit error rate parameter of 0.1, a downlink AMC adjustment step of 0.5625, a target receive power of -60dBm, and a partial path loss compensation related parameter of 5.

[0176] In another example, the operation result is that the maximum throughput that can be obtained is 21.90 Mbps, and the maximum throughput that can be obtained for the physical network obtained by the previous network optimization process is 20.03 Mbps, so the network optimization process can be ended. In addition, the optimal parameter value of the configuration parameter can also be fed back to the user. For example, the optimal parameter value can include a downlink bit error rate parameter of 0.1 and a downlink AMC adjustment step of 0.1875.

[0177] If the various modules of the above-mentioned network optimization system 200 are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The storage medium for storing computer software products includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0178] In the case of implementing the functions of each module of the above network optimization system 200 in the form of hardware, the embodiment of the present application further provides a communication device 300, which is used to implement the network optimization method provided by the present application. Fig.12 As shown, the communication device 300 includes: a communication interface 303, a processor 302, and a bus 304. Optionally, the communication device may further include a memory 301.

[0179] The processor 302 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present application. The processor 302 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present application. The processor 302 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0180] The communication interface 303 is used to connect with other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0181] The memory 301 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0182] As a possible implementation, the memory 301 may exist independently of the processor 302, and the memory 301 may be connected to the processor 302 via a bus 304, and is used to store instructions or program codes executable by the processor 302, such as computer program instructions, etc. When the processor 302 calls and executes the instructions or program codes stored in the memory 301, the communication method provided in the embodiment of the present application can be implemented.

[0183] In another possible implementation, the memory 301 may also be integrated with the processor 302 .

[0184] The bus 304 may be an extended industry standard architecture (EISA) bus, etc. The bus 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.12 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0185] Some embodiments of the present application provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium), in which computer program instructions are stored. When the computer program instructions are executed on a computer (e.g., the above-mentioned communication device, the processor of the communication device, or the above-mentioned environment reflection function module, etc.), the computer executes the method for transmitting environment reflection as described in any of the above-mentioned embodiments. It should be understood that the present application does not limit the specific form of the computer.

[0186] In some examples, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this application may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0187] An embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a computer, the computer is enabled to execute the method described in any one of the above embodiments.

[0188] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A network optimization method, characterized in that: The method comprises: Determine a first configuration parameter to be optimized based on a network optimization requirement of the physical network; Based on the digital twin network corresponding to the physical network, optimizing the first configuration parameter to obtain an optimal parameter value of the first configuration parameter; Sending the optimal parameter value of the first configuration parameter to the physical network.

2. The method according to claim 1, characterized in that The sending the optimal parameter value of the first configuration parameter to the physical network includes: Obtaining a first digital twin result, where the first digital twin result is a digital twin result obtained by the digital twin network based on an optimal parameter value of the first configuration parameter; When the first digital twin result meets the network optimization requirement, the optimal parameter value of the first configuration parameter is sent to the physical network.

3. The method according to claim 1, characterized in that: The network optimization requirement includes any one of the following: environment configuration requirement, resource utilization requirement, retransmission number requirement, capacity requirement, and service experience requirement.

4. The method according to claim 1, characterized in that: The first configuration parameter includes at least one of the following: geographic information configuration parameter, system information configuration parameter, frequency information configuration parameter, access configuration parameter, physical layer parameter, regulation algorithm parameter, power control algorithm parameter, and adaptive coding modulation parameter.

5. The method according to claim 1, characterized in that The optimizing the first configuration parameter based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the first configuration parameter includes: Iteratively updating the parameter value of the first configuration parameter a preset number of times; Inputting the parameter value of the first configuration parameter after each iterative update into the digital twin network to obtain the digital twin result corresponding to the parameter value of the first configuration parameter after each iterative update; The optimal digital twin result among the digital twin results corresponding to the parameter values ​​of the first configuration parameters after each iterative update is used as the first digital twin result; The parameter value of the first configuration parameter corresponding to the first digital twin result is used as the optimal parameter value of the first configuration parameter.

6. The method according to claim 5, characterized in that The parameter value of the first configuration parameter after the i-th iteration update is determined based on the parameter value of the first configuration parameter after the i-1-th iteration update and the digital twin result corresponding to the parameter value after the i-1-th iteration update, where i is a positive integer.

7. The method according to claim 5, characterized in that The iterative updating of the parameter value of the first configuration parameter for a preset number of times includes: Based on an artificial intelligence algorithm, the parameter value of the first configuration parameter is iteratively updated a preset number of times.

8. The method according to claim 1, characterized in that: The determining of the first configuration parameter to be optimized based on the network optimization requirement of the physical network includes: Based on the network optimization requirements, determining target parameters; The first configuration parameter is determined from a set of configuration parameters associated with the target parameter.

9. The method according to claim 1, characterized in that: The determining of the first configuration parameter to be optimized based on the network optimization requirement of the physical network includes: In response to detecting that a physical state of the physical network has changed, a first configuration parameter to be optimized is determined based on a network optimization requirement of the physical network.

10. The method according to claim 2, characterized in that The method further comprises: When the first digital twin result does not meet the network optimization requirement, determining a second configuration parameter to be optimized based on the network optimization requirement; Based on the digital twin network corresponding to the physical network, optimizing the second configuration parameter to obtain the optimal parameter value of the second configuration parameter and a second digital twin result, where the second digital twin result is the digital twin result obtained by the digital twin network based on the optimal parameter value of the second configuration parameter; When the second digital twin result meets the network optimization requirement, the optimal parameter value of the second configuration parameter is sent to the physical network.

11. The method according to claim 10, characterized in that The method further comprises: When the second digital twin result fails to meet the network optimization requirements, a parameter value of a third configuration parameter is sent to the physical network, and the parameter value of the third configuration parameter is the parameter value of the configuration parameter corresponding to the optimal digital twin result between the first digital twin result and the second digital twin result.

12. The method according to claim 10, characterized in that The first configuration parameter and the second configuration parameter differ in at least one of the following: parameter type, parameter value range, and parameter number.

13. The method according to claim 1, characterized in that The method further comprises: Obtaining an operation result of the physical network based on an optimal parameter value of the first configuration parameter; Based on the relationship between the running result and the first digital twin result, an adjustment strategy for the digital twin network is determined; wherein the first digital twin result is a digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter.

14. The method according to claim 13, characterized in that When the operating result is inferior to the first digital twin result, the adjustment strategy includes performing performance correction processing on the digital twin network.

15. The method according to claim 1, characterized in that The method further comprises: Determining construction parameters of the digital twin network according to construction parameters of the physical network; Construct the digital twin network according to the construction parameters of the digital twin network.

16. The method according to claim 15, characterized in that The construction parameters of the digital twin network include one or more of network state configuration parameters, relevant algorithm parameters, and environmental parameters; Among them, the network status configuration parameters include one or more of the network basic performance indicators KPI, cell load parameters, cell interference parameters, and user statistical characteristic parameters; the related algorithm parameters include one or more of the physical layer parameters, scheduling algorithm parameters, power control algorithm parameters, and adaptive coding modulation parameters; the environmental parameters include one or more of the geographical parameters, system parameters, frequency parameters, and access configuration parameters.

17. The method according to claim 15, characterized in that: The method further comprises: In response to detecting that a physical state of the physical network has changed, updating construction parameters of the digital twin network to obtain updated construction parameters; Based on the updated construction parameters, the digital twin network is reconstructed.

18. A network optimization system, characterized in that: The network optimization system includes a network optimization module and an artificial intelligence module: The artificial intelligence module is used to determine a first configuration parameter to be optimized based on a network optimization requirement of the physical network; The artificial intelligence module is further used to optimize the first configuration parameter based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the first configuration parameter; The network optimization module is used to send the optimal parameter value of the first configuration parameter to the physical network.

19. The network optimization system according to claim 18, characterized in that: The network optimization system further includes a digital twin module; the digital twin module is used to: Determining construction parameters of the digital twin network according to construction parameters of the physical network; Construct the digital twin network according to the construction parameters of the digital twin network.

20. The network optimization system according to claim 18, characterized in that: The artificial intelligence module is specifically used for: Iteratively updating the parameter value of the first configuration parameter a preset number of times; Inputting the parameter value of the first configuration parameter after each iterative update into the digital twin network to obtain the digital twin result corresponding to the parameter value of the first configuration parameter after each iterative update; The optimal digital twin result among the digital twin results corresponding to the parameter values ​​of the first configuration parameters after each iterative update is used as the first digital twin result; The parameter value of the first configuration parameter corresponding to the first digital twin result is used as the optimal parameter value of the first configuration parameter.

21. The network optimization system according to claim 18, characterized in that: The network optimization module is specifically used for: Obtaining a first digital twin result, where the first digital twin result is a digital twin result obtained by the digital twin network based on an optimal parameter value of the first configuration parameter; When the first digital twin result meets the network optimization requirement, the optimal parameter value of the first configuration parameter is sent to the physical network.

22. The network optimization system according to claim 21, characterized in that: The network optimization module is further configured to determine a second configuration parameter to be optimized based on the network optimization requirement when the first digital twin result does not meet the network optimization requirement; The artificial intelligence module is further used to optimize the second configuration parameters based on the digital twin network corresponding to the physical network to obtain the optimal parameter value of the second configuration parameter and the second digital twin result, where the second digital twin result is the digital twin result obtained by the digital twin network based on the optimal parameter value of the second configuration parameter; The network optimization module is also used to send the optimal parameter value of the second configuration parameter to the physical network when the second digital twin result meets the network optimization requirements.

23. The network optimization system according to claim 22, characterized in that: The network optimization module is also used to send the parameter value of a third configuration parameter to the physical network when the second digital twin result does not meet the network optimization requirements, and the parameter value of the third configuration parameter is the parameter value of the configuration parameter corresponding to the optimal digital twin result between the first digital twin result and the second digital twin result.

24. The network optimization system according to claim 19, characterized in that: The network optimization module is further used to: obtain an operation result of the physical network based on the optimal parameter value of the first configuration parameter; and determine an adjustment strategy for the digital twin network based on a superiority relationship between the operation result and the first digital twin result; Sending the adjustment strategy to the digital twin module; wherein the first digital twin result is a digital twin result obtained by the digital twin network based on the optimal parameter value of the first configuration parameter; The digital twin module is also used to adjust the digital twin network according to the adjustment strategy.

25. A communication device, characterized in that: include: Memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 17 is performed.

26. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a communication device, the communication device is caused to execute the method according to any one of claims 1 to 17.

Images