Electric power communication network roundabout route reconstruction method and device based on digital twinning

Abstract

The invention provides an electric power communication network roundabout route reconstruction method and device based on digital twinning, and mainly relates to the technical field of communication. Specifically, the circuitous route reconstruction method for the electric power communication network comprises the following steps: carrying out twinborn mapping on the electric power communication network to construct a digital twinborn model of the electric power communication network; carrying out simulation tests of multiple fault states by using a digital twin model to obtain a fault state service loss degree and a fault state bandwidth occupancy rate; under the condition that the fault-state service loss degree is greater than a first threshold value or the fault-state bandwidth occupancy rate is greater than a second threshold value, performing routing strategy optimization based on a digital twin model by using a Markov decision method to obtain a routing optimization result; and performing routing reconstruction on the electric power communication network based on a routing optimization result to obtain a reconstructed electric power communication network.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and more specifically, to a method and device for reconstructing a circuitous route of an electric power communication network based on digital twins. Background Art

[0002] As one of the key tasks in the development of smart grids, digital twin technology aims to improve the intelligence level of the power grid through digital means, and enhance the grid's adaptive capabilities and fault recovery efficiency. Digital twin technology effectively simulates, optimizes and predicts the behavior and performance of actual equipment and systems by building a virtual twin of the physical system in digital space. In the field of power communications, the application of digital twin technology not only provides strong support for system design and optimization, but also plays an important role in testing, verification and operation and maintenance management.

[0003] Traditional routing methods often rely on static network models. In complex power communication networks, there are a large number of routing options, and traditional routing algorithms can only find local optimal routing solutions when applying digital twin technology. This may lead to insufficient utilization of network resources, and in some cases, may even cause network congestion and resource waste. Although digital twin technology can build a virtual twin of a physical system, in actual applications, it cannot ensure that the digital twin model is updated synchronously with the actual network status. Summary of the invention

[0004] In view of this, the present disclosure provides a method and device for reconstructing detour routes of a power communication network based on digital twins.

[0005] One aspect of the present disclosure provides a method for reconstructing a detour route of an electric power communication network based on a digital twin, comprising: performing twin mapping on the electric power communication network to construct a digital twin model of the electric power communication network; using the digital twin model to perform simulation tests of various fault states to obtain a fault state service loss degree and a fault state bandwidth occupancy rate; when the fault state service loss degree is greater than a first threshold, or the fault state bandwidth occupancy rate is greater than a second threshold, using a Markov decision method to optimize a routing strategy based on the digital twin model to obtain a routing optimization result; and performing routing reconstruction on the electric power communication network based on the routing optimization result to obtain a reconstructed electric power communication network.

[0006] Another aspect of the present disclosure provides a digital twin-based power communication network detour route reconstruction device, including: a construction module, used to perform twin mapping on the power communication network to construct a digital twin model of the above-mentioned power communication network; a testing module, used to use the above-mentioned digital twin model to perform simulation tests on multiple fault states to obtain the fault state service loss degree and the fault state bandwidth occupancy rate; an optimization module, used to use the Markov decision method to optimize the routing strategy based on the digital twin model when the above-mentioned fault state service loss degree is greater than a first threshold, or the above-mentioned fault state bandwidth occupancy rate is greater than a second threshold, to obtain a routing optimization result; and a reconstruction module, used to perform routing reconstruction on the above-mentioned power communication network based on the above-mentioned routing optimization result to obtain a reconstructed power communication network.

[0007] Another aspect of the present disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0008] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0009] Another aspect of the present disclosure provides a computer program product, which includes computer executable instructions, and when the instructions are executed, are used to implement the method as described above.

[0010] According to the embodiments of the present disclosure, a digital twin model is constructed to reflect the physical state and logical relationship of the network in real time, and the network data is mapped to the digital twin space. On this basis, the Markov decision method is used to optimize the routing strategy based on the digital twin model. By performing routing reconstruction operations, the network can quickly recover to the optimal state, thereby avoiding network congestion and resource waste, and significantly improving the transmission efficiency and reliability of the power communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0012] Figure 1 An exemplary system architecture to which a method for reconstructing a detour route of a power communication network based on digital twins can be applied according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 2 A flowchart of a method for reconstructing a circuitous route of a power communication network based on digital twins according to an embodiment of the present disclosure is schematically shown;

[0014] Figure 3 A schematic diagram of a power communication network architecture based on digital twins according to a specific embodiment of the present disclosure is schematically shown;

[0015] Figure 4 A schematic diagram of power communication network service flow transmission according to a specific embodiment of the present disclosure is schematically shown;

[0016] Figure 5 A schematic diagram of a power communication network topology according to a specific embodiment of the present disclosure is shown schematically;

[0017] Figure 6 The end-to-end delay distribution diagram of different algorithms according to a specific embodiment of the present disclosure is schematically shown;

[0018] Figure 7 A schematic diagram of network throughput of different algorithms according to a specific embodiment of the present disclosure is schematically shown;

[0019] Figure 8 A block diagram schematically shows a device for reconstructing a detour route of a power communication network based on digital twins according to an embodiment of the present disclosure; and

[0020] Fig. 9 A block diagram of an electronic device suitable for implementing a method for reconstructing a detour route of a power communication network based on digital twins according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0022] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0023] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0024] In the context of promoting high-quality development of new power systems, the power industry is actively responding to the complex and changing operating environment, implementing special actions to improve quality and efficiency, and driving intelligent upgrades with innovation. Among them, digital twin technology, as one of the key tasks in the development of smart grids, aims to improve the intelligence level of the grid through digital means, and enhance the grid's adaptive capabilities and fault recovery efficiency.

[0025] Digital twin technology effectively simulates, optimizes and predicts the behavior and performance of actual equipment and systems by building a virtual twin of the physical system in digital space. In the field of power communications, the application of digital twin technology not only provides strong support for system design and optimization, but also plays an important role in testing, verification and operation and maintenance management. Especially in the digital transformation of power systems, digital twin technology has become a key means to improve the level of intelligence and automation of power grids.

[0026] Traditional routing methods often rely on static network models. However, due to the dynamically changing network environment and complex topology in the power communication network, traditional routing methods are difficult to reflect changes in network status in real time. Although digital twin technology can build a virtual twin of the physical system, in practical applications, it cannot ensure that the digital twin model is updated synchronously with the actual network status. Secondly, in complex power communication networks, there are a large number of routing options, and traditional routing algorithms can often only find locally optimal routing solutions when applying digital twin technology. This may lead to the inability to fully utilize network resources, and in some cases, it may even cause network congestion and resource waste.

[0027] In view of this, an embodiment of the present disclosure provides a method for reconstructing a detour route of an electric power communication network based on digital twins, including: performing twin mapping on the electric power communication network to construct a digital twin model of the electric power communication network; using the digital twin model to perform simulation tests on various fault states to obtain the fault state service loss degree and the fault state bandwidth occupancy rate; when the fault state service loss degree is greater than a first threshold, or the fault state bandwidth occupancy rate is greater than a second threshold, using a Markov decision method to optimize the routing strategy based on the digital twin model to obtain a routing optimization result; based on the routing optimization result, performing routing reconstruction on the electric power communication network to obtain a reconstructed electric power communication network.

[0028] Figure 1 The exemplary system architecture to which the method for reconstructing the detour routing of a power communication network based on digital twins can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0029] like Figure 1 As shown, the system architecture according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0030] The user may use the first terminal device 101 , the second terminal device 102 , and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send requests, etc.

[0031] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0032] The server 105 may be a server that provides various services, such as executing tasks such as building a digital twin model, simulation testing, routing strategy optimization, and routing reconstruction (only as an example), and feeding back the processing results to the terminal device.

[0033] It should be noted that the method for reconstructing the detour route of the electric power communication network based on digital twin provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the apparatus for reconstructing the detour route of the electric power communication network based on digital twin provided in the embodiment of the present disclosure can generally be set in the server 105.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0035] Figure 2 A flowchart of a method for reconstructing a detour route of a power communication network based on digital twin according to an embodiment of the present disclosure is schematically shown.

[0036] like Figure 2 As shown, the method includes operations S201 to S204.

[0037] In operation S201, twin mapping is performed on the power communication network to construct a digital twin model of the power communication network.

[0038] In operation S202, a digital twin model is used to perform simulation tests of various fault states to obtain the fault state service loss degree and the fault state bandwidth occupancy rate.

[0039] In operation S203, when the fault state service loss degree is greater than the first threshold, or the fault state bandwidth occupancy rate is greater than the second threshold, a Markov decision method is used to optimize the routing strategy based on the digital twin model to obtain a routing optimization result.

[0040] In operation S204, the power communication network is routed reconstructed based on the route optimization result to obtain a reconstructed power communication network.

[0041] According to an embodiment of the present disclosure, based on the key data of the power communication network, the power communication network is twin mapped, the physical entity of the power communication network and its logical rules such as operation logic and production process are mapped to the virtual space, and a virtual twin corresponding to the physical network entity is created. Based on the virtual twin corresponding to the physical network entity, a digital twin model of the power communication network is constructed.

[0042] According to an embodiment of the present disclosure, a digital twin model can be used to reflect the operating status and performance characteristics of an actual power communication network.

[0043] According to an embodiment of the present disclosure, through twin mapping, the physical network can be simulated, analyzed and optimized in the virtual space without directly intervening in the physical network.

[0044] According to the embodiments of the present disclosure, a digital twin model is used to simulate multiple possible network failure scenarios, such as equipment failure, link interruption, etc. For each failure scenario, in order to quantitatively evaluate the impact of the failure on the power communication network, the failure state service loss degree and failure state bandwidth occupancy rate can be calculated to identify service security risks.

[0045] According to an embodiment of the present disclosure, the fault state service loss degree is used to characterize the sum of the importance of services that cannot be rerouted in the fault state of the power communication network. The fault state service loss degree can be used to reflect the direct impact of the fault on the reliability of service operation.

[0046] According to the embodiments of the present disclosure, the fault state bandwidth occupancy rate can be used to characterize the bandwidth occupancy of each communication link after service rerouting. The fault state bandwidth occupancy rate can be used to reflect the resource utilization efficiency and congestion degree of the network in a fault state.

[0047] According to an embodiment of the present disclosure, when the failure state service loss degree is greater than a set first threshold, or the failure state bandwidth occupancy rate is greater than a set second threshold, the routing policy optimization process is triggered.

[0048] According to an embodiment of the present disclosure, the Markov decision method is a decision method based on state transition probability, which can handle complex problems with uncertainty and dynamics.

[0049] Specifically, the Markov decision method can be used to optimize the routing strategy on the digital twin model. By synchronously updating the state space and link status, it can be ensured that the Markov decision process can make decisions based on the latest and most accurate network information. By solving the Markov decision process, the service loss and bandwidth occupancy can be minimized, thereby obtaining the optimal routing optimization result.

[0050] According to an embodiment of the present disclosure, the actual power communication network is reconfigured according to the routing optimization results. The routing reconstruction process includes operations such as adjusting the network topology and redistributing communication traffic. After the routing reconstruction, the digital twin model is used again for verification and testing to ensure that the new routing solution can meet the network performance and reliability requirements.

[0051] Based on this, the embodiments of the present disclosure construct a digital twin model to reflect the physical state and logical relationship of the network in real time, and map the network data to the digital twin space. On this basis, the Markov decision method is used to optimize the routing strategy based on the digital twin model. By performing routing reconstruction operations, the network can quickly recover to the optimal state, thereby avoiding network congestion and resource waste, and significantly improving the transmission efficiency and reliability of the power communication network.

[0052] According to an embodiment of the present disclosure, a power communication network is twin mapped to construct a digital twin model of the power communication network, including: for each of the multiple communication devices included in the power communication network, based on the operation information of the communication device, extracting the operation characteristics of the communication device; based on the topological structure of the power communication network, obtaining the communication link between the multiple communication devices; based on the respective operation characteristics of the multiple communication devices and the communication links between the multiple communication devices, constructing an entity model of the power communication network; twin mapping the entity model to obtain an initial digital twin model; for the multiple power services included in the business space, based on the communication equipment required for each power service, determining the mapping relationship between the entity model and the business space; twin mapping is performed based on the mapping relationship between the entity model and the business space to add the business mapping to the initial digital twin model to obtain a digital twin model.

[0053] According to an embodiment of the present disclosure, the operation information of the communication device may include bandwidth usage, latency, packet loss rate, etc.

[0054] According to an embodiment of the present disclosure, based on the operating information of each communication device among the multiple communication devices included in the power communication network, processing methods such as data processing and feature extraction are used to extract the operating characteristics of each communication device. The operating characteristics of each communication device may include, for example, the current bandwidth, average delay, maximum packet loss rate, etc.

[0055] According to an embodiment of the present disclosure, the topological structure of the power communication network may be identified by using methods such as graph theory and network analysis technology, and the topological structure may include connection relationships between nodes (communication devices) and edges (communication links).

[0056] According to an embodiment of the present disclosure, based on the topological structure of the power communication network, communication links between multiple communication devices are constructed, and parameters such as the connection type and transmission rate of each communication link are determined.

[0057] According to the embodiments of the present disclosure, a physical model of the power communication network can be constructed by combining the operation characteristics of the communication device and the communication link information. The physical model can fully reflect the physical state and logical relationship of the network.

[0058] According to an embodiment of the present disclosure, the entity model of the power communication network may include a physical entity model. In the power communication network, the physical entity model may be used to represent a collection of all communication components and the lines between them. These components include but are not limited to key devices such as power communication routers and switches.

[0059] According to an embodiment of the present disclosure, the initial digital twin model can be used to characterize the virtual twin model, and the virtual twin model can be used to perform a one-to-one mapping of the physical entity model in the digital space. The virtual twin model can be controlled and driven by a software control platform.

[0060] According to an embodiment of the present disclosure, a service space may include multiple power services, each of which requires a specific communication device to support its operation.

[0061] According to an embodiment of the present disclosure, based on the communication equipment required for each power service, a mapping relationship between a physical entity model and a service space can be determined. The mapping relationship can be used to characterize the corresponding relationship between the power service and the communication equipment.

[0062] According to an embodiment of the present disclosure, business information can be added to the initial digital twin model based on the mapping relationship between the physical entity model and the business space. For example, a corresponding representation can be created for each power business in the digital twin model, and these representations can be connected to the relevant communication equipment. By adding the business mapping to the initial digital twin model, a complete digital twin model can be constructed. The digital twin model can include not only the physical information of the physical entity model, but also the business information in the business space, so as to be able to reflect the physical structure and operating status of the power communication network in real time.

[0063] Figure 3 A schematic diagram of a power communication network architecture based on digital twins according to a specific embodiment of the present disclosure is schematically shown.

[0064] like Figure 3 As shown in the figure, the twin network layer is a virtual mapping of the physical network layer, that is, each physical network element in the physical network layer has a unique corresponding twin network element in the twin network layer. The network element status, traffic data, and network element connection relationship of the physical network layer will be virtually mapped to the twin network layer. The physical network and the twin network are interconnected and data is exchanged in real time. Among them, the physical network layer and the twin network layer have the same topology and the same number of network elements.

[0065] According to an embodiment of the present disclosure, based on the operation information of the communication device, the operation characteristics of the communication device are extracted, including: based on the switch state of the communication device, the accumulated operation time, the fault state and the maximum number of connectable devices of the communication device in the power communication network, the device performance sub-characteristics of the communication device are obtained; based on the current bandwidth, maximum bandwidth, communication delay data, accumulated operation time, packet loss rate data, bandwidth weight coefficient, delay weight coefficient and packet loss rate weight coefficient of the communication device, the network performance sub-characteristics of the communication device are obtained; based on the load rate data, traffic data, packet loss rate data, communication delay data and control delay influence coefficient of the communication device, the behavior sub-characteristics of the communication device are obtained; based on the device performance sub-characteristics, network performance sub-characteristics and behavior sub-characteristics of the communication device, the operation characteristics of the communication device are obtained.

[0066] According to an embodiment of the present disclosure, the operating characteristics of each communication device can be calculated based on the device performance sub-characteristics, network performance sub-characteristics and behavior sub-characteristics of the communication device. Specifically, the expression of the operating characteristics of each communication device is as follows:

[0067] (1);

[0068] (2);

[0069] In formula (1), represents the operating characteristics of the ith power communication device, Represents the equipment performance sub-characteristics of the power communication equipment, Represents the network performance sub-characteristics of power communication equipment, represents the behavioral sub-characteristics of the power communication equipment, Represents a network component definition function.

[0070] In formula (2), , , They represent weight parameters respectively, Indicates the coefficient of the control delay on the packet loss rate.

[0071] According to an embodiment of the present disclosure, the device performance sub-characteristic of the power communication device can be used to represent the physical state and connection capability of the device. The device performance sub-characteristic can be obtained based on, for example, the switch state of the communication device, the accumulated operation time such as the total operation time of the device, the fault state, and the maximum number of connectable devices of the device in the power communication network. Specifically, the device performance sub-characteristic is expressed as follows:

[0072] (3);

[0073] In the formula, It represents the equipment performance sub-characteristic of the power communication equipment. S represents the switch state of the power communication equipment, and the value is 0 or 1. R represents the accumulated operation time of the power communication equipment. F represents the fault state of the power communication equipment. Indicates the maximum number of devices that can be connected in the power communication network; Represents the distance between the physical quantity F and 1 in Euclidean space.

[0074] According to an embodiment of the present disclosure, the network performance sub-characteristics of the power communication device can be used to represent the transmission performance and stability of the device in the network. The network performance sub-characteristics can be obtained based on the current bandwidth, maximum bandwidth, communication delay data, accumulated operation time, packet loss rate data, bandwidth weight coefficient, delay weight coefficient and packet loss rate weight coefficient of the communication device. Specifically, the network performance sub-characteristics are expressed as follows:

[0075] (4);

[0076] In the formula, represents the network performance sub-characteristic of the power communication equipment, B represents the current bandwidth of the power communication equipment, represents the maximum bandwidth of the power communication equipment, D represents the network delay of the power communication equipment, T represents the delay attenuation parameter, P represents the packet loss rate, , , They represent the weight coefficients of bandwidth, delay and packet loss rate respectively.

[0077] According to an embodiment of the present disclosure, the behavior sub-features of the power communication device can be used to represent the dynamic behavior of the device under different load and flow conditions. The behavior sub-features can be obtained based on the load rate data, flow data, packet loss rate data, communication delay data and control delay influence coefficient of the communication device. Specifically, the behavior sub-features are expressed as follows:

[0078] (5);

[0079] In the formula, represents the behavior sub-characteristic of the power communication equipment, L(t) represents the load rate of the power communication equipment at time t, represents the flow of power communication equipment at time t, represents the packet loss rate of the power communication equipment at time t, represents the time delay of the power communication equipment at time t, The coefficient representing the influence of the control delay on the packet loss rate. In a specific embodiment of the present disclosure, the devices to be modeled (routers, switches, links, etc.) can be twinned one by one based on formulas (1) to (5).

[0080] According to an embodiment of the present disclosure, a physical model of a power communication network is constructed based on the operating characteristics of each of a plurality of communication devices and the communication links between the plurality of communication devices, including: obtaining a node set of the power communication network based on the operating characteristics of each of the plurality of communication devices; obtaining an edge set of the power communication network based on the communication links between the plurality of communication devices; and constructing a physical model of the power communication network based on the node set and edge set of the power communication network.

[0081] Specifically, the physical entity model can be composed of two parts: a node set and an edge set. Among them, the node set can be used to represent the various communication components in the power communication network, such as power communication routers, switches, etc. Each node has its own unique characteristics, such as bandwidth, latency, packet loss rate, etc. Among them, the edge set can be used to represent the connection relationship between various communication components, that is, communication links. These links have different connection types and transmission rates, and they together constitute the topological structure of the network. For example, the expression of the physical entity model is as follows:

[0082] (6);

[0083] Where PE represents the physical entity model; represents a collection of nodes in a physical power communication network; represents the operating characteristics of the ith physical power communication device; k represents the number of power communication devices in the network; represents the set of edges in the physical power communication network; Represents the operating characteristics of the ith physical power communication device in the physical power communication device Operational characteristics of the jth physical power communication device The connection relationship between them.

[0084] In this specific embodiment, the expression of the virtual twin model is as follows:

[0085] (7);

[0086] Where VE represents the virtual twin model, Represents a set of nodes in a virtual communication network, that is, a set of network components. represents the operating characteristics of the i-th virtual network component, represents the edge set in the virtual communication network, that is, the connection set between components, Represents the operating characteristics of the i-th virtual network component and the operating characteristics of the jth virtual network component connection relationship.

[0087] In this specific embodiment, the operation characteristics of the virtual network component can be calculated based on the device performance sub-characteristics, network performance sub-characteristics and behavior sub-characteristics of the virtual network component. Specifically, the expression of the operation characteristics of each virtual network component is as follows:

[0088] (8);

[0089] In the formula, represents the operating characteristics of the i-th virtual network component, Represents the device performance sub-characteristics of the virtual network components, Represents the network performance sub-characteristics of the virtual network components, represents the behavioral sub-characteristics of virtual network components, Represents the definition function of a virtual network component.

[0090] According to an embodiment of the present disclosure, for multiple power services included in the business space, the business space model can be used to determine the mapping relationship between the physical entity model and the business space, and realize the control function of the physical entity model and the virtual twin model. The business space model can also receive feedback data from the physical entity model and the virtual twin model for analysis and evaluation. Specifically, the expression of the business space model is as follows:

[0091] (9);

[0092] In the formula, SS represents the business space model, S L Indicates a network service or application.

[0093] According to the embodiments of the present disclosure, in the physical entity model, the implementation of different services is achieved through the combination of different network components, and thus the mapping relationship expression between the physical entity model and the service space is as follows:

[0094] (10);

[0095] In the formula, Indicates business S i The set of operational characteristics of the physical power communications equipment required, Indicates business S i Operational characteristics of the jth physical power communication device The mapping relationship between .

[0096] According to an embodiment of the present disclosure, the mapping relationship between the virtual twin model and the business space is expressed as follows:

[0097] (11);

[0098] In the formula, Indicates business S i The set of operational characteristics of the virtual network components required, Indicates business S i and the operating characteristics of the jth virtual network component The mapping relationship between In a specific embodiment, a service mapping of a physical entity can be established based on formula (9) to formula (11), thereby obtaining a complete twin model.

[0099] According to an embodiment of the present disclosure, a digital twin model is used to perform simulation tests of multiple fault states to obtain fault state service loss degrees and fault state bandwidth occupancy rates, including: in each fault state, performing random failure processing on the digital twin model to obtain a digital twin model corresponding to the fault state; performing a business operation simulation test on the digital twin model corresponding to the fault state to determine at least one remaining power business that can be operated from multiple power businesses included in the business space; obtaining the service loss degree of the fault state based on the importance weights of each of the multiple power businesses and the importance weights of each of the at least one remaining power business, and obtaining the service loss degree of the fault state based on the average of the service loss degrees of the multiple fault states; performing a communication simulation test on the digital twin model corresponding to the fault state to obtain the bandwidth occupancy rates of the multiple communication links included in the digital twin model corresponding to the fault state; obtaining the bandwidth occupancy rate of the fault state based on the bandwidth occupancy rates of the multiple communication links included in the digital twin model corresponding to the fault state and the total number of communication links of the digital twin model corresponding to the fault state, and obtaining the bandwidth occupancy rate of the fault state based on the average of the bandwidth occupancy rates of the multiple fault states.

[0100] According to an embodiment of the present disclosure, a digital twin model can be used to simulate a variety of possible network failure scenarios. By dynamically identifying failure risks in the power communication network and triggering a routing reconstruction algorithm based on these risks, the algorithm can dynamically adjust the transmission path of the service according to the size and type of risk to ensure the continuity and reliability of the service.

[0101] According to an embodiment of the present disclosure, the risk identification standard may include two dimensions, the static security standard of the business and the dynamic security standard of the business. Among them, the static security standard of the business mainly focuses on the reliability of the operation path of the business under normal operation. Specifically, the digital twin model can be used to simulate the normal operation status of the business and evaluate the reliability of its path, so as to identify potential static security risks. Among them, the dynamic security standard of the business mainly focuses on the ability of the business to restore normal operation through detours in the event of a network failure. Specifically, the N-1 failure can be simulated (that is, assuming that a component in the network fails) to evaluate the detour capability of the business in the event of a failure, as well as the carrying capacity of the network bandwidth after the level-by-level detour. The dynamic security standard of the business can reflect the network's ability to support business operations and the reliability of business operations in the event of a failure.

[0102] According to an embodiment of the present disclosure, in order to quantitatively evaluate the impact of a fault on a power communication network, the service security risk may be identified by calculating the fault state service loss degree and the fault state bandwidth occupancy rate.

[0103] According to an embodiment of the present disclosure, for each preset fault state, a random failure process may be performed on the digital twin model, which may include, for example, simulated component failure, communication link interruption, etc.

[0104] According to a specific embodiment of the present disclosure, a business operation simulation test can be performed on the digital twin model corresponding to the fault state. In this process, it is observed which power services can still be operated, that is, at least one remaining power service that can be operated is determined.

[0105] In this specific embodiment, the fault state service loss degree can be based on the importance weights of multiple power services. First, the total weight of all services in the normal state is calculated, and then the sum of the importance weights of at least one remaining power service is calculated. The above calculations are performed for multiple fault states respectively, and then the average is taken to obtain the fault state service loss degree. Specifically, the fault state service loss degree is calculated as follows:

[0106] (12);

[0107] In the formula, Q represents the failure state service loss degree, represents the importance of the i-th business, represents the importance of the jth business, U c Indicates the set of power services included in the business space, U h Represents the remaining power business set, N f Indicates the number of simulated expected accidents.

[0108] In this specific embodiment, the method for calculating the importance of the power business is shown in Tables 1 to 3.

[0109] Table 1 Weights of power business indicators

[0110]

[0111] Table 2 Evaluation values ​​of typical power business under evaluation indicators

[0112]

[0113] Table 3 Importance results of typical power business

[0114]

[0115] According to a specific embodiment of the present disclosure, a communication simulation test can be performed on the digital twin model corresponding to the fault state. In this process, the bandwidth occupancy of each communication link is recorded.

[0116] In this specific embodiment, for each fault state, the fault state bandwidth occupancy rate can be calculated based on the average value of the bandwidth occupancy rates of all communication links and the total number of communication links of the digital twin model corresponding to the fault state to obtain the bandwidth occupancy rate of the fault state, and based on the average value of the bandwidth occupancy rates of multiple fault states, the fault state bandwidth occupancy rate is obtained. Specifically, the calculation method of the fault state bandwidth occupancy rate is as follows:

[0117] (13);

[0118] Where B represents the fault state bandwidth occupancy rate, b i represents the bandwidth occupancy of the i-th link; N e Represents the total number of communication links; N f Indicates the number of simulated expected accidents.

[0119] Figure 4 A schematic diagram of power communication network service flow transmission according to a specific embodiment of the present disclosure is schematically shown.

[0120] like Figure 4 As shown in the figure, nodes 1 to 10 can all represent substation nodes, the dotted line path represents the business flow, and the solid line path represents the communication link. There are shared risk link groups at nodes 3 and 4, nodes 3 and 5, nodes 3 and 6, nodes 7 and 9, and nodes 7 and 10, and the shared risk link groups can share the same physical resources.

[0121] According to an embodiment of the present disclosure, when the fault state service loss degree is greater than a first threshold, or the fault state bandwidth occupancy rate is greater than a second threshold, a Markov decision method is used to optimize the routing strategy based on a digital twin model to obtain a routing optimization result.

[0122] According to an embodiment of the present disclosure, a Markov decision method is used to optimize the routing strategy based on a digital twin model to obtain a routing optimization result, including: based on the digital twin model, the power communication network is divided into multiple control domains; for each control domain, the state space of the control domain is obtained based on the state sets of the control domain and the neighboring control domains of the control domain; in the state space of the control domain, the weights of each of the multiple communication links related to the control domain are iteratively optimized based on a reward function to calculate the minimum cost path based on the updated weights of each of the multiple communication links related to the control domain, to obtain the optimal control path that satisfies network load balancing, to obtain a routing optimization result.

[0123] According to an embodiment of the present disclosure, based on a digital twin model, the power communication network is divided into multiple control domains. Among them, multiple control domains can be used to characterize the logical partitions of the power communication network. Each control domain has a neighboring control domain adjacent to it, which is connected through a communication link. There is a topological connection relationship between neighboring control domains and there is no overlap, ensuring that each communication device belongs to only one control domain. Specifically, the topological structure expression of the control domain is as follows:

[0124] (14);

[0125] In the formula, G C represents the topological structure of the control domain, E C Represents the link set of the control domain, , V C Represents the set of forwarding power communication devices in the control domain, which consists of gateway nodes Vg and ordinary forwarding nodes Vo.

[0126] According to an embodiment of the present disclosure, for each control domain, a state space is constructed according to the state sets of itself and its adjacent control domains, wherein the state set of the control domain can be obtained based on the operation characteristics of the communication devices contained therein.

[0127] Specifically, the routing reconstruction process can be modeled as a Markov decision process . Where N represents the number of control domains. In the power communication network, these control domains will work together to optimize the routing strategy of the entire network. S represents the state space of the control domain, which describes all the states that each control domain may be in. These states may include, for example, node attributes of the domain and neighboring domains, link status (delay, bandwidth, packet loss rate), traffic matrix, and network load. For each control domain G C , its state space Si can contain the state sets of this domain and all neighboring domains. A represents the action space, represents the joint action space set of all control domains, which can be used to define the actions that the control domain can take, that is, the link selection weights of all possible control topologies. By changing these weights, the control domain can use the weighted shortest path algorithm to calculate the minimum cost path, thereby optimizing network load balancing. represents the joint reward function of the control domain. The joint reward function can be used to define the reward that the control domain receives after taking a certain action. In this scenario, the reward function can be defined based on the link bandwidth utilization of the control domain to reflect the improvement in network load.

[0128] According to the embodiments of the present disclosure, a policy (Actor) network can be used to generate actions that can be taken by the control domain. In the cooperative Markov decision, the policy network can adopt a sequential advantage evaluation mechanism to update the policy according to the fixed order flow relationship when the power business is transmitted upstream and the instruction is issued in the routing. Specifically, a subset of control domains is selected according to the business flow, and it is arranged into a linear control domain sequence . Then for , the arrangement order satisfies the following expression:

[0129] (15);

[0130] In the formula, function f(x) represents the control domain x in the sequence The position index in i ,b j ,c k They are the control domain agents on the access side, aggregation side, and core side respectively.

[0131] According to an embodiment of the present disclosure, the advantage function can be used to evaluate the average performance of a certain action relative to the current strategy. In the power communication network, the sequence can be The joint advantage function Break down into a series of strengths assessments that follow the sequential flow of the business.

[0132] (16);

[0133] In the formula, represents the joint advantage function, Indicates the current policy.

[0134] According to the embodiments of the present disclosure, the state space S may be composed of node attributes, link status (delay, bandwidth, packet loss rate), traffic matrix, and network load of the local domain and neighboring domains. C have The state space S of control domain i is iContains the state set of this domain and all neighboring domains The state space of each control domain is composed of adjacency matrices of different dimensions. For example, the state space S containing only a single node i The state space S consists of multiple nodes and links, including the voltage level of the power communication equipment and the traffic load of the control domain. i It also includes link information such as link occupied bandwidth, latency, and packet loss rate.

[0135] According to an embodiment of the present disclosure, the action space A is defined as the link selection weights of the control topology. By changing these weights, the agent can use a weighted shortest path algorithm to calculate the minimum cost path as the optimal control path that satisfies network load balancing. Specifically, the expression of the action space set is as follows:

[0136] (17);

[0137] In the formula, A i represents the action space set, Indicates the link weight.

[0138] According to an embodiment of the present disclosure, the reward function R can use the link bandwidth occupancy rate of the control domain to define the network load, and calculate the reward accordingly, so as to help guide the agent to take actions that can improve the network load. Specifically, based on the digital twin model, the occupied bandwidth and total bandwidth capacity of each of the multiple communication links related to the control domain can be determined; based on the occupied bandwidth and total bandwidth capacity of each of the multiple communication links related to the control domain, the network load of the control domain can be obtained. Among them, the control domain G C The expression of network load is as follows:

[0139] (18);

[0140] In the formula, Indicates the control domain G C The network load, B ij , C ij They represent the occupied bandwidth and total bandwidth capacity on link (i, j) in the control domain respectively, and 𝑛𝑒𝑡 represents the control domain type.

[0141] According to an embodiment of the present disclosure, in the state space of the control domain, the agent will iteratively optimize the weights of multiple communication links based on the current state and reward function. This process can use reinforcement learning algorithms such as HADDPG. Through continuous trial and error, the agent will gradually learn how to select the optimal link weights based on the current state to maximize long-term rewards. After the link weights are updated, the agent will use these weights to calculate the minimum cost path among multiple communication links related to the control domain.

[0142] According to an embodiment of the present disclosure, the minimum cost path can be used to characterize the path with the minimum cost (such as delay, bandwidth consumption, etc.) under the premise of meeting network performance requirements. The minimum cost path can be implemented by a weighted shortest path algorithm (such as Dijkstra algorithm, Bellman-Ford algorithm, etc.).

[0143] According to the embodiments of the present disclosure, by selecting these minimum cost paths, the agent can obtain the optimal control path that meets the network load balancing requirements. These paths not only take into account the performance of a single link, but also take into account the load balancing of the entire network. Therefore, the method can more effectively utilize network resources and improve the overall performance of the network. Finally, the agent will output the routing optimization results, that is, a series of optimal control paths. These paths can be used as the basis for network routing strategies to guide data transmission and instruction issuance in actual networks.

[0144] Based on this, after defining the elements of the Markov decision process MDP, the embodiment of the present disclosure can fully consider the decision-making influence of the forward agent by adopting the above method, thereby updating its own strategy, and using a reinforcement learning algorithm (such as HADDPG) to train the control domain agent so that it learns how to select the optimal action (i.e., link weight) according to the current state, thereby optimizing the network routing strategy. Through iterative training, the agent will gradually learn how to make the best decision under different states to achieve network load balancing and performance improvement.

[0145] According to an embodiment of the present disclosure, the routing optimization objective includes minimizing the load variance between access side and same side control domains while satisfying path constraints, and the load variance between access side and same side control domains is determined based on the network load of the control domain.

[0146] According to an embodiment of the present disclosure, the routing optimization target is used to minimize the load variance between the control domains on the access side and the same side by adjusting the routing strategy in the network. The routing optimization target can be used to achieve network load balancing, improve the utilization of network resources, and reduce network bottlenecks and performance degradation caused by load imbalance. Specifically, in order to improve the differentiated service quality, the service importance indexes in Tables 1 to 3 can be referred to, and it can be stipulated that the control domain through which the service with high service importance passes should have a lower end-to-end delay.

[0147] According to the embodiments of the present disclosure, the path constraint conditions include: the occupied bandwidth of the communication link in the control domain is less than or equal to the total bandwidth capacity; the average end-to-end delay of the control domain is less than or equal to the maximum tolerable delay of the service; the average packet loss rate of the control domain is less than or equal to the maximum tolerable packet loss rate of the service. Specifically, the expression of the path constraint condition is as follows:

[0148] (19);

[0149] In the formula, represents the load variance, I m represents the business importance index, and n represents the control domain G C The number of links, B ij , C ij denote the occupied bandwidth and total bandwidth capacity of the link (i, j) in the control domain, 𝑛𝑒𝑡 denotes the control domain type, and constraint (i) is used to ensure that the occupied bandwidth of the link in the control domain does not exceed the total bandwidth capacity to avoid network congestion and link failure. Constraint (ii) is used to ensure the average end-to-end delay of the control domain Not greater than the maximum tolerable delay of the mth service , to ensure the real-time and reliability of the service. Constraint (iii) is used to ensure the average packet loss rate of the control domain Not greater than the maximum packet loss rate that the service can tolerate , to improve the integrity and accuracy of data transmission.

[0150] According to the embodiments of the present disclosure, based on the above-mentioned route optimization objectives and path constraints, the reward function R of the control domain can be designed: i . Reward function R i It can be used to reflect the routing optimization goal (i.e., minimizing load variance) and the satisfaction of path constraints. Specifically, the reward function is expressed as follows:

[0151] (20);

[0152] In the formula, R i represents the reward function.

[0153] Figure 5 A schematic diagram of a power communication network topology according to a specific embodiment of the present disclosure is schematically shown.

[0154] In a specific embodiment of the present disclosure, the following can be used: Figure 5 The power communication network topology shown is used as the detection object, where Figure 5 There are 35 nodes in total, each node represents a switch that supports the OpenFlow protocol, and each switch is connected to multiple hosts.

[0155] In this specific embodiment, initial parameters such as network state, Actor network, and Critic network are set. The current network state is used as the input of the Actor network. The Actor network generates an action based on the input current network state as the link selection weight for controlling the topology. Based on the weighted shortest path algorithm, the control path is calculated based on the link selection weight. Based on the control path, the intra-domain routing algorithm is executed to generate a complete routing strategy that meets the service QoS constraints. The generated routing strategy is executed in the power communication network to obtain a new network state and reward value. The new network state, action, reward value, and old state are stored in the experience replay pool. The Critic online network can update the target value and network parameters at time step t using formulas (21) and (22) based on the samples in the experience replay pool. The Actor online network sequentially updates the strategy parameters according to formula (23).

[0156] (twenty one);

[0157] (twenty two);

[0158] (twenty three);

[0159] In the formula, represents the target value at time step t, represents the network parameters, Indicates action, Indicates the network status. Indicates the new network status. Represents the reward value.

[0160] Reference below Figure 6~Figure 7 , the method for reconstructing the detour routing of the power communication network based on digital twin is further explained in combination with specific embodiments.

[0161] Figure 6 A schematic diagram of end-to-end delay distribution of different algorithms according to a specific embodiment of the present disclosure is schematically shown.

[0162] Figure 7 The diagram schematically shows the network throughput of different algorithms according to a specific embodiment of the present disclosure.

[0163] like Figure 6 and Figure 7 As shown, DT-H represents the digital twin-based power communication network detour routing reconstruction method proposed in the present invention, HADDPG represents the traditional heterogeneous advantage decomposition deep deterministic policy gradient algorithm, MADDPG represents the traditional multi-agent deep deterministic policy gradient algorithm, and DDPG-SGR represents the deep deterministic policy gradient algorithm combined with state-target representation.

[0164] like Figure 6 and Figure 7 As shown, the end-to-end delay of the power communication network detour route reconstruction method based on digital twin proposed in the present disclosure is the lowest among the four methods, and the throughput is high. Based on this, the power communication network detour route reconstruction method based on digital twin proposed in the present disclosure realizes automatic path reconstruction when the channel fails or is congested by real-time monitoring of the network power communication equipment and communication channel status. Compared with the traditional routing switching method that relies on manual intervention, the present invention can quickly generate the optimal detour path and automatically switch when a problem is detected, which greatly improves the response speed and reliability of the network and reduces the time of communication interruption. In addition, through the real-time synchronization of the digital twin model and the physical network, the present invention can continuously adapt to network changes, dynamically optimize resource allocation, and improve bandwidth utilization and overall network stability. In the path selection process, the algorithm is combined to automatically analyze the performance indicators of multiple paths (such as bandwidth, delay, packet loss rate, etc.), effectively avoiding the subjective errors that may exist in traditional manual path selection.

[0165] Figure 8 A block diagram of a digital twin-based power communication network detour routing reconstruction device according to an embodiment of the present disclosure is schematically shown.

[0166] like Figure 8 As shown, the power communication network detour route reconstruction device 800 includes a construction module 810, a test module 820, an optimization module 830 and a reconstruction module 840.

[0167] Construction module 810 is used to perform twin mapping on the power communication network to construct a digital twin model of the power communication network.

[0168] The test module 820 is used to use the digital twin model to perform simulation tests on various fault states to obtain the fault state service loss degree and fault state bandwidth occupancy rate.

[0169] The optimization module 830 is used to use the Markov decision method to optimize the routing strategy based on the digital twin model to obtain the routing optimization result when the fault state service loss degree is greater than the first threshold, or the fault state bandwidth occupancy rate is greater than the second threshold.

[0170] The reconstruction module 840 is used to perform route reconstruction on the power communication network based on the route optimization result to obtain a reconstructed power communication network.

[0171] According to an embodiment of the present disclosure, the construction module 810 includes a first extraction submodule, a first determination submodule, a first construction submodule, a first mapping submodule, a second determination submodule, and a second mapping submodule.

[0172] The first extraction submodule is used to extract the operation characteristics of each communication device among the multiple communication devices included in the power communication network based on the operation information of the communication device.

[0173] The first determination submodule is used to obtain the communication links between the multiple communication devices based on the topological structure of the power communication network.

[0174] The first construction submodule is used to construct a physical model of the power communication network based on the operation characteristics of each of the multiple communication devices and the communication links between the multiple communication devices.

[0175] The first mapping submodule is used to perform twin mapping on the entity model to obtain an initial digital twin model.

[0176] The second determination submodule is used to determine the mapping relationship between the entity model and the business space for multiple power services included in the business space based on the communication equipment required for each power service.

[0177] The second mapping submodule is used to perform twin mapping based on the mapping relationship between the entity model and the business space, so as to add the business mapping to the initial digital twin model to obtain the digital twin model.

[0178] According to an embodiment of the present disclosure, the first extraction submodule includes a first determination unit, a second determination unit, a third determination unit, and a fourth determination unit.

[0179] The first determination unit is used to obtain the device performance sub-characteristic of the communication device based on the switch state, accumulated operation time, fault state and the maximum number of connectable devices of the communication device in the power communication network.

[0180] The second determination unit is used to obtain the network performance sub-characteristics of the communication device based on the current bandwidth, maximum bandwidth, communication delay data, cumulative running time, packet loss rate data, bandwidth weight coefficient, delay weight coefficient and packet loss rate weight coefficient of the communication device.

[0181] The third determining unit is used to obtain the behavior sub-features of the communication device based on the load rate data, flow data, packet loss rate data, communication delay data and control delay influence coefficient of the communication device.

[0182] The fourth determining unit is used to obtain the operation characteristics of the communication device based on the device performance sub-characteristics, network performance sub-characteristics and behavior sub-characteristics of the communication device.

[0183] According to an embodiment of the present disclosure, the first construction submodule includes a fifth determining unit, a sixth determining unit, and a first construction unit.

[0184] The fifth determining unit is used to obtain a node set of the power communication network based on the respective operating characteristics of the plurality of communication devices.

[0185] The sixth determining unit is used to obtain an edge set of the power communication network based on the communication links between the multiple communication devices.

[0186] The first construction unit is used to construct a physical model of the power communication network based on the node set and edge set of the power communication network.

[0187] According to an embodiment of the present disclosure, the test module 820 includes a failure processing submodule, a first test submodule, a third determination submodule, a second test submodule, and a fourth determination submodule.

[0188] The failure processing submodule is used to perform random failure processing on the digital twin model under each fault state to obtain a digital twin model corresponding to the fault state.

[0189] The first test submodule is used to perform a business operation simulation test on the digital twin model corresponding to the fault state to determine at least one remaining operable power business from a plurality of power businesses included in the business space.

[0190] The third determination submodule is used to obtain the service loss degree of the fault state based on the importance weights of each of the multiple power services and the importance weight of each of the at least one remaining power services, and to obtain the service loss degree of the fault state based on the average of the service loss degrees of the multiple fault states.

[0191] The second test submodule is used to perform a communication simulation test on the digital twin model corresponding to the fault state to obtain the bandwidth occupancy rate of each of the multiple communication links included in the digital twin model corresponding to the fault state.

[0192] The fourth determination submodule is used to obtain the bandwidth occupancy of the fault state based on the bandwidth occupancy of each of the multiple communication links included in the digital twin model corresponding to the fault state, and the total number of communication links of the digital twin model corresponding to the fault state, and to obtain the fault state bandwidth occupancy based on the average of the bandwidth occupancy of each of the multiple fault states.

[0193] According to an embodiment of the present disclosure, the optimization module 830 includes a partitioning submodule, a fifth determination submodule, and an iteration submodule.

[0194] The division submodule is used to divide the power communication network into multiple control domains based on the digital twin model.

[0195] The fifth determination submodule is used to obtain, for each control domain, a state space of the control domain based on the state sets of the control domain and its neighboring control domains.

[0196] The iterative submodule is used to iteratively optimize the weights of each of the multiple communication links related to the control domain based on the reward function in the state space of the control domain, so as to calculate the minimum cost path based on the updated weights of each of the multiple communication links related to the control domain, and obtain the optimal control path that satisfies the network load balancing, so as to obtain the routing optimization result.

[0197] According to an embodiment of the present disclosure, the power communication network detour routing reconstruction device also includes a first determination module and a second determination module.

[0198] The first determination module is used to determine the occupied bandwidth and total bandwidth capacity of each of multiple communication links related to the control domain based on the digital twin model.

[0199] The second determining module is used to obtain the network load of the control domain based on the occupied bandwidth and the total bandwidth capacity of each of the multiple communication links related to the control domain.

[0200] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0201] It should be noted that the part of the power communication network detour routing reconstruction device based on digital twin in the embodiments of the present disclosure corresponds to the part of the power communication network detour routing reconstruction method based on digital twin in the embodiments of the present disclosure. The description of the power communication network detour routing reconstruction device based on digital twin specifically refers to the part of the power communication network detour routing reconstruction method based on digital twin, which will not be repeated here.

[0202] Fig. 9 A block diagram of an electronic device suitable for implementing a method for reconstructing a detour route of a power communication network based on digital twins according to an embodiment of the present disclosure is schematically shown. Fig. 9The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0203] like Fig. 9 As shown, the electronic device according to the embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to the program stored in the read-only memory ROM 902 or the program loaded from the storage part 908 to the random access memory RAM 903. The processor 901 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an on-board memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0204] In RAM 903, various programs and data required for the operation of the electronic device are stored. The processor 901, ROM 902, and RAM 903 are connected to each other via a bus 904. The processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program may also be stored in one or more memories other than ROM 902 and RAM 903. The processor 901 may also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0205] According to an embodiment of the present disclosure, the electronic device may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device may further include one or more of the following components connected to the input / output (I / O) interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0206] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0207] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0208] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0209] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the digital twin-based power communication network detour route reconstruction method provided by the embodiment of the present disclosure.

[0210] When the computer program is executed by the processor 901, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0211] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0212] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for reconstructing a circuitous route of a power communication network based on digital twin, comprising: Performing twin mapping on the power communication network to construct a digital twin model of the power communication network; The digital twin model is used to perform simulation tests of various fault states to obtain the fault state service loss degree and the fault state bandwidth occupancy rate; When the fault state service loss degree is greater than the first threshold, or the fault state bandwidth occupancy rate is greater than the second threshold, a Markov decision method is used to optimize the routing strategy based on the digital twin model to obtain a routing optimization result; as well as The power communication network is routed reconstructed based on the route optimization result to obtain a reconstructed power communication network.

2. The method according to claim 1, wherein: The performing twin mapping on the power communication network to construct a digital twin model of the power communication network includes: For each communication device among the plurality of communication devices included in the power communication network, extracting an operation feature of the communication device based on the operation information of the communication device; Based on the topological structure of the power communication network, obtaining communication links between the plurality of communication devices; constructing a physical model of the power communication network based on the operating characteristics of each of the plurality of communication devices and the communication links between the plurality of communication devices; Performing twin mapping on the entity model to obtain an initial digital twin model; For a plurality of electric power services included in the service space, based on the communication equipment required for each electric power service, determining a mapping relationship between the entity model and the service space; and Twin mapping is performed based on the mapping relationship between the entity model and the business space to add the business mapping to the initial digital twin model to obtain the digital twin model.

3. The method according to claim 2, wherein: The extracting the operation characteristics of the communication device based on the operation information of the communication device includes: Obtaining a device performance sub-characteristic of the communication device based on a switch state, a cumulative operating time, a fault state, and a maximum number of devices that can be connected to the communication device in the power communication network; Obtaining network performance sub-characteristics of the communication device based on the current bandwidth, maximum bandwidth, communication delay data, cumulative running time, packet loss rate data, bandwidth weight coefficient, delay weight coefficient and packet loss rate weight coefficient of the communication device; Obtaining a behavior sub-feature of the communication device based on the load rate data, flow data, packet loss rate data, communication delay data, and control delay impact coefficient of the communication device; and Based on the device performance sub-characteristics, network performance sub-characteristics and behavior sub-characteristics of the communication device, the operation characteristics of the communication device are obtained.

4. The method according to claim 2, wherein: The constructing the entity model of the power communication network based on the respective operating characteristics of the plurality of communication devices and the communication links between the plurality of communication devices comprises: Based on the operation characteristics of each of the plurality of communication devices, obtaining a node set of the power communication network; Based on the communication links between the plurality of communication devices, obtaining an edge set of the power communication network; and Based on the node set and edge set of the power communication network, a physical model of the power communication network is constructed.

5. The method according to claim 1, wherein: The digital twin model is used to perform simulation tests on various fault states to obtain the fault state service loss degree and fault state bandwidth occupancy rate, including: Under each fault state, performing random failure processing on the digital twin model to obtain a digital twin model corresponding to the fault state; Performing a business operation simulation test on the digital twin model corresponding to the fault state to determine at least one remaining electric power business that can be operated from a plurality of electric power businesses included in the business space; Based on the importance weights of the respective multiple power services and the importance weight of the respective at least one remaining power service, the service loss degree of the fault state is obtained, and based on the average of the service loss degrees of the respective multiple fault states, the service loss degree of the fault state is obtained; Performing a communication simulation test on the digital twin model corresponding to the fault state to obtain the bandwidth occupancy rate of each of the multiple communication links included in the digital twin model corresponding to the fault state; and Based on the bandwidth occupancy rates of each of the multiple communication links included in the digital twin model corresponding to the fault state, and the total number of communication links of the digital twin model corresponding to the fault state, the bandwidth occupancy rate of the fault state is obtained, and based on the average of the bandwidth occupancy rates of the multiple fault states, the bandwidth occupancy rate of the fault state is obtained.

6. The method according to claim 1, wherein: The Markov decision method is used to optimize the routing strategy based on the digital twin model to obtain the routing optimization result, including: Based on the digital twin model, the power communication network is divided into a plurality of control domains, wherein adjacent control domains have no overlap, each control domain has a neighbor control domain, and there is a communication link between the control domain and the neighbor control domain; For each control domain, based on the state sets of the control domain and its neighboring control domains, a state space of the control domain is obtained, wherein the state set of the control domain is obtained based on operating characteristics of communication devices included in the control domain; and In the state space of the control domain, the weights of each of the multiple communication links related to the control domain are iteratively optimized based on the reward function, so as to calculate the minimum cost path based on the updated weights of each of the multiple communication links related to the control domain, and obtain the optimal control path that satisfies the network load balancing, so as to obtain the routing optimization result, wherein the reward function is determined based on the routing optimization target.

7. The method according to claim 6, wherein: The routing optimization objective includes minimizing the load variance between access-side and same-side control domains while satisfying path constraints, wherein the load variance between access-side and same-side control domains is determined based on the network load of the control domain.

8. The method according to claim 7, further comprising: Based on the digital twin model, determine the occupied bandwidth and total bandwidth capacity of each of the plurality of communication links associated with the control domain; as well as Based on the occupied bandwidths and the total bandwidth capacity of each of the plurality of communication links related to the control domain, the network load of the control domain is obtained.

9. The method according to claim 7, wherein: The path constraints include: The occupied bandwidth of the communication link in the control domain is less than or equal to the total bandwidth capacity; The average end-to-end delay of the control domain is less than or equal to the maximum tolerable delay of the service; The average packet loss rate of the control domain is less than or equal to the maximum packet loss rate that the service can tolerate.

10. A power communication network detour routing reconstruction device based on digital twin, comprising: A construction module, used for performing twin mapping on the power communication network to construct a digital twin model of the power communication network; A testing module, used to use the digital twin model to perform simulation tests of various fault states to obtain the fault state service loss degree and fault state bandwidth occupancy rate; An optimization module, used to optimize the routing strategy based on the digital twin model using a Markov decision method to obtain a routing optimization result when the fault state service loss degree is greater than a first threshold or the fault state bandwidth occupancy rate is greater than a second threshold; as well as A reconstruction module is used to perform route reconstruction on the power communication network based on the route optimization result to obtain a reconstructed power communication network.

Images