Electric power communication network route planning method, electronic equipment and storage medium

Abstract

The invention discloses a power communication network route planning method, electronic equipment and a storage medium, and relates to the technical field of communication, and the method comprises the steps: obtaining source node equipment and destination node equipment of a to-be-planned route scheme in a power communication network, and in a route scheme set corresponding to the source node equipment and the destination node equipment, carrying out route planning on the to-be-planned route scheme; determining an initial routing scheme corresponding to the target moment, controlling the source node equipment to send the service data to the destination node equipment according to the initial routing scheme at the target moment, and obtaining at least one piece of routing environment information corresponding to the initial routing scheme at the target moment, and iteratively determining a target routing scheme between the source node equipment and the destination node equipment in a routing scheme set based on the deep Q network by taking the initial routing scheme corresponding to the target moment and the at least one piece of routing state information as a starting point. According to the embodiment of the invention, the problem of poor routing planning effect in the electric power communication network with a large number of nodes is solved, and the routing planning efficiency and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method for planning routing of a power communication network, electronic equipment and a storage medium. Background Art

[0002] As the scale of the power grid continues to expand, the speed and scale of data generated by new power systems have increased significantly, which requires the power communication network to not only have efficient data processing capabilities, but also ensure the stability and security of data transmission.

[0003] In the existing technology, in the face of complex and ever-changing power grid business, traditional planning methods rely on expert experience and manual selection, which is difficult to efficiently handle and adapt to these changes. In the face of the high-dimensional state space caused by the increase in the number of network nodes, traditional reinforcement learning algorithms are difficult to converge to the optimal strategy, which limits the effectiveness and reliability of planning methods. Summary of the invention

[0004] The present invention provides a method for planning routing in a power communication network, an electronic device and a storage medium, so as to solve the problem of poor routing planning effect in a power communication network with a huge number of nodes.

[0005] According to one aspect of an embodiment of the present invention, a method for routing planning of a power communication network is provided, comprising:

[0006] The source node device and the sink node device of the routing scheme to be planned in the power communication network are obtained, and an initial routing scheme corresponding to the target time is determined in the routing scheme set corresponding to the source node device and the sink node device, the source node device is controlled to send service data to the sink node device according to the initial routing scheme at the target time, and at least one routing environment information corresponding to the initial routing scheme at the target time is obtained, and the target routing scheme between the source node device and the sink node device is iteratively determined in the scheme set based on the deep Q network, taking the initial routing scheme corresponding to the target time and at least one routing state information as the starting point.

[0007] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0008] At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the routing planning method for the power communication network of any embodiment of the present invention.

[0009] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the routing planning method for the power communication network described in any embodiment of the present invention when executed.

[0010] The technical solution of the embodiment of the present invention obtains the source node device and the sink node device of the routing scheme to be planned in the power communication network, and determines the initial routing scheme corresponding to the target time in the routing scheme set corresponding to the source node device and the sink node device, provides a comparison benchmark for the subsequent routing scheme planning, controls the source node device to send the service data to the sink node device according to the initial routing scheme at the target time, and obtains at least one routing environment information corresponding to the initial routing scheme at the target time, provides a data basis for the iterative optimization of the subsequent routing scheme, takes the initial routing scheme corresponding to the target time and at least one routing state information as the starting point, and iteratively determines the target routing scheme between the source node device and the sink node device in the routing scheme set based on the deep Q network as the optimal routing planning scheme. The problem of poor routing planning effect in the power communication network with a large number of nodes is solved, and the efficiency and reliability of data transmission are improved.

[0011] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 is a flow chart of a method for planning a route for a power communication network provided according to a first embodiment of the present invention;

[0014] Figure 2 is a flow chart of a method for planning routing of a power communication network provided according to a second embodiment of the present invention;

[0015] Figure 3 is a flow chart of a method for planning routing of a power communication network provided according to a third embodiment of the present invention;

[0016] Figure 4 This is a structural diagram of a power communication network routing planning device provided according to a fourth embodiment of the present invention;

[0017] Figure 5It is a structural schematic diagram of an electronic device for implementing the power communication network routing planning method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment 1

[0021] Figure 1 This is a flow chart of a method for routing planning of a power communication network provided in the first embodiment of the present invention. This embodiment can be applied to the case where optimal routing planning between node devices is implemented in a power communication network with a large number of nodes. The method of this embodiment can be implemented by a routing planning device of a power communication network, which can be implemented in software and / or hardware, and can generally be configured in an electronic device with data processing function. Figure 1 As shown, the method includes:

[0022] S110, obtaining source node devices and sink node devices of a routing scheme to be planned in the power communication network, and determining an initial routing scheme corresponding to a target time in a set of routing schemes corresponding to the source node devices and the sink node devices.

[0023] In the embodiment of the present invention, the power communication network can be specifically understood as: a communication network of the power system, which allows data exchange and communication between different parts of the power system, and is used to monitor and control the generation, transmission and distribution of electricity.

[0024] In the embodiment of the present invention, the source node device can be specifically understood as: the starting point in the power communication network, that is, the sending end of data or signals, for example, a power station or substation responsible for generating or transmitting power data.

[0025] In the embodiment of the present invention, the sink node device can be specifically understood as: corresponding to the source node device, the end point for receiving information or data in the power communication network, for example, a controller for performing specific operations, a terminal for displaying data, or a server for processing data.

[0026] In the embodiment of the present invention, the routing scheme to be planned can be specifically understood as: in the power communication network, a transmission path from a source node to a destination node that has not yet been determined or needs to be optimized to ensure the efficiency, reliability and security of data transmission.

[0027] In the embodiment of the present invention, the target time can be specifically understood as: a predetermined time point at which a specific task is expected to be completed or a certain state is expected to be reached in the power communication network, such as the time point at which service transmission needs to be completed, the time point at which the network state needs to reach a certain condition, or the specific time for data synchronization.

[0028] In the embodiment of the present invention, the initial routing solution may be specifically understood as: a preliminary communication path or strategy proposed based on current network conditions and requirements during the planning stage.

[0029] In the embodiment of the present invention, the routing solution set can be specifically understood as: a set of all possible routing path solutions. Each routing solution defines a potential path for data from a source node to a destination node. The routing solution set provides a selection range for selecting the best routing path, wherein a routing solution can be randomly selected from the routing solution set as an initial routing solution, and the initial routing solution can be selected from the routing solution set according to prior experience, which is not limited in this embodiment.

[0030] Specifically, after determining the source node device and the sink node device of the routing scheme to be planned in the power communication network, all routing paths between the source node device and the sink node device can be clarified, and all routing paths are combined into a routing scheme set. In the routing scheme set corresponding to the source node device and the sink node device, the initial routing scheme corresponding to the target time is determined, and this initial routing scheme is used as the basis for the subsequent routing scheme selection. Among them, when there are multiple device nodes between the source node device and the sink node device, it can continue to be refined into a combination of multiple source node devices and sink node devices, and the routing path planning of multiple nodes in a large network is divided into multiple small sub-network routing path planning. In each sub-network, the optimal transmission path is calculated independently for the source node device and the sink node device, wherein the source node device and the sink node device do not contain or contain a small number of intermediate node devices. This method not only simplifies the routing calculation process, but also improves the accuracy and efficiency of path selection.

[0031] S120: Control the source node device to send the service data to the sink node device according to the initial routing scheme at the target time, and obtain at least one item of routing environment information corresponding to the initial routing scheme at the target time.

[0032] In the embodiment of the present invention, the routing environment information may be specifically understood as: in the electric power communication network, all data and conditions related to routing decisions, which directly affect the effectiveness of routing planning and the overall performance of the network.

[0033] Specifically, the source node device is controlled to send service data to the destination node device at the target time according to the initial routing plan, and at least one data and condition related to the routing decision corresponding to the plan at the target time is obtained, providing a data basis for subsequent iterative optimization of the routing plan.

[0034] S130. Taking the initial routing scheme corresponding to the target time and at least one item of routing state information as the starting point, iteratively determine the target routing scheme between the source node device and the sink node device in the routing scheme set based on the deep Q network.

[0035] In the embodiment of the present invention, the deep Q network can be specifically understood as: a neural network that combines deep learning and Q learning for optimizing routing decisions to select the best path, wherein the Q function is used to evaluate the expected utility of taking a specific action under a given state.

[0036] In the embodiment of the present invention, the target routing solution may be specifically understood as: an optimal routing solution selected for a specific requirement or optimization target.

[0037] Specifically, according to the initial routing scheme corresponding to the target time and at least one routing state information, the routing scheme with the highest evaluation value is selected from the routing scheme set through iterative optimization of the constructed deep Q network.

[0038] Exemplarily, in the routing planning of the power communication network, a single routing scheme with low cost and simple design can be selected to transmit information for non-critical services. First, the routing schemes between the source node device and the sink node device in the power communication network and between them are clarified, a set of routing schemes is constructed, and an initial routing scheme is selected. According to the initial routing scheme, the service data is sent from the source node device to the sink node device at the target time, and at least one routing environment information is obtained. The initial routing scheme and routing state information are iteratively determined in the routing scheme set based on the deep Q network to determine the routing scheme with the highest evaluation value as the target routing scheme.

[0039] The technical solution of the embodiment of the present invention first obtains the source node device and the sink node device of the routing scheme to be planned in the power communication network, and determines the initial routing scheme corresponding to the target time in the routing scheme set corresponding to the source node device and the sink node device, thereby refining the routing planning problem of multiple nodes in a large network into a routing planning sub-problem of a simple network, simplifying the routing calculation process, improving the accuracy and efficiency of path selection, and providing a comparison basis and a solution selection range for subsequent iterative optimization of routing planning solutions; then, the source node device is controlled to send the service data to the sink node device according to the initial routing scheme at the target time, and at least one routing environment information corresponding to the initial routing scheme at the target time is obtained, so as to optimize the subsequent iterative optimization of routing solutions. Providing a data basis; starting from an initial routing scheme corresponding to a target time and at least one item of routing state information, the target routing scheme between a source node device and a destination node device is iteratively determined in a routing scheme set based on a deep Q network. Through a deep Q network, in a large-scale or multi-node power communication network with a complex network environment of a high-dimensional state space, the routing scheme is automatically explored and utilized and decisions are made. Moreover, according to the routing environment information, the routing strategy can be dynamically adjusted in real time in response to changes in network conditions, thereby realizing the optimal selection of routing schemes for source node devices and destination node devices in a known set of routing schemes, solving the problem of poor routing planning effects in power communication networks with a large number of nodes, and improving the efficiency and reliability of routing planning.

[0040] Embodiment 2

[0041] Figure 2 A flowchart of a routing planning method for an electric power communication network provided in Embodiment 2 of the present invention. This embodiment is technically refined based on the above embodiments. In this embodiment, specifically, the routing scheme is divided into a primary routing scheme and a protection routing scheme, and the routing status information includes at least one of the risk balance level, load balance level, transmission delay between devices, optical power, and common mode risk of the routing scheme, and when the source node device is controlled to send service data to the destination node device based on a dual-transmission selective reception method and based on the primary routing scheme and the protection routing scheme, the operation of "obtaining at least one routing environment information corresponding to the initial routing scheme" is concretized.

[0042] Correspondingly, such as Figure 2 As shown, the method includes:

[0043] S210. Obtain source node devices and sink node devices of the main routing scheme and protection routing scheme to be planned in the power communication network, and determine the initial main routing scheme and initial protection routing scheme corresponding to the target time in the set of main routing schemes and protection routing schemes corresponding to the source node devices and the sink node devices.

[0044] In the embodiment of the present invention, the primary routing scheme can be specifically understood as: a scheme designed based on the current network status and business requirements to meet the service quality requirements of the business, and is the preferred path for data transmission under normal operating conditions. According to the different planning stages of the primary routing scheme, it can be divided into: a primary routing scheme to be planned, an initial primary routing scheme, and a target primary routing scheme. Among them, all possible primary routing path schemes constitute a set of primary routing schemes.

[0045] In the embodiment of the present invention, the protection routing scheme can be specifically understood as: providing a backup path when the primary route fails, ensuring that when the primary route is unavailable, the service can quickly switch to the backup path to minimize service interruption. The protection routing scheme involves additional resources and costs, but is necessary in scenarios with critical services and high availability requirements. According to the different planning stages of the protection routing scheme, it can be divided into: a protection routing scheme to be planned, an initial protection routing scheme, and a target protection routing scheme. Among them, all possible protection routing path schemes constitute a protection routing scheme set.

[0046] S220, control the source node device to send the service data to the destination node device based on the dual-transmission and selective reception method, based on the main routing plan and the protection routing plan, and obtain information on at least one of the risk balance level, load balance level, transmission delay between devices, optical power and common mode risk corresponding to the initial main routing plan and the initial protection routing plan at the target time.

[0047] In the embodiment of the present invention, dual transmission and selective reception can be specifically understood as: data is sent from the same source node on two different paths and selectively received at the receiving end of the destination node. This method provides a redundancy mechanism to prevent one of the paths from failing or being congested. The destination node can choose to receive the best or most reliable of the two sent copies based on specific criteria or algorithms to ensure the continuity of critical services and efficient operation of the network.

[0048] In the embodiment of the present invention, the risk balance level can be specifically understood as: the state of balancing the risks of different parts or links in network design. The goal of risk balance is to achieve a uniform distribution of risks among all network components or areas, to avoid the increase of the vulnerability of the entire network due to excessively high risks in some parts, and to improve the effect of routing planning.

[0049] Specifically, according to the formula:

[0050] Calculate the risk balance level of source node i and sink node j under the initial routing scheme at target time k in, represents the primary routing scheme for source node i and sink node j at target time k, represents the primary routing solution corresponding to the target time k The transmission route between adjacent routing nodes i and j′ The transmission routing risk. A is the failure probability constant, is the transmission route between adjacent routing nodes i′ and j′ at target time k The risk probability value of failure, I n is the business importance of the nth business in the business data, N is the total number of businesses in the business data, and f m_avg Primary routing solution The average risk value of the transmission route. U is the number of adjacent node device routes in the power communication network. represents the protection routing scheme for source node i and sink node j at target time k, is the protection routing scheme corresponding to the target time k The transmission path between adjacent routing nodes i′ and j′ The transmission routing risk. is the transmission route between adjacent routing nodes i′ and j′ at target time k The risk probability value of failure. q_avg To protect the routing scheme The average risk value of the transmission route. in, It is determined according to the information fed back by the sink node j device after receiving the service data.

[0051] In the embodiments of the present invention, the load balancing level can be specifically understood as: a way of distributing data traffic or workload in a network to optimize resource usage, avoid congestion, and improve the overall performance of the network. Load balancing usually involves distributing tasks to multiple servers or nodes to ensure that no single point is overloaded and to improve the effectiveness of routing planning.

[0052] Specifically, according to the formula:

[0053] Calculate the load balancing level of source node i and sink node j under the initial routing scheme at target time k in, is the service acceptance value of the source node i device, It is obtained by summing the ratio of the remaining high-order cross-connect capacity to the high-order cross-connect capacity and the ratio of the remaining low-order cross-connect capacity to the low-order cross-connect capacity of the source node i device. is the service admission value of the source node j device. Primary routing solution The total bandwidth resources of the transmission route, Primary routing solution The remaining bandwidth resources of the transmission route, To protect the routing scheme The total bandwidth resources of the transmission route, To protect the routing scheme The remaining bandwidth resources of the transmission route. It is determined according to the information fed back by the sink node j device after receiving the service data.

[0054] In the embodiment of the present invention, the transmission delay between devices can be specifically understood as: the time required for data to be transmitted from one device to another in the network. Transmission delay is one of the key indicators for measuring network performance, and is particularly important for systems that require real-time or near real-time response.

[0055] Specifically, according to the formula:

[0056] Calculate the transmission delay between source node i and sink node j at target time k under the initial routing scheme in, Primary routing solution And protection routing solution The node delay of the transmission route between adjacent routing nodes i′ and j′ in . It is determined according to the information fed back by the sink node j device after receiving the service data.

[0057] In the embodiment of the present invention, optical power can be specifically understood as: the intensity of an optical signal transmitted in an optical fiber. The level of optical power will affect the quality and transmission distance of the signal, and needs to be properly managed and adjusted in route planning to ensure effective data transmission.

[0058] Specifically, according to the formula:

[0059] Calculate the optical power of source node i and sink node j under the initial routing scheme at target time k Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution The optical power of this hop between adjacent routing nodes i′ and j′ meets the transmission requirements, otherwise it is 0. in，max，i′j′ is the maximum input optical power of this hop between adjacent routing nodes i′ and j′, P in，min，i′j′ is the minimum input optical power of this hop between adjacent routing nodes i′ and j′. It is obtained by detecting the transmission channel between the source node i device and the sink node j device under the initial routing scheme at the target time k.

[0060] In the embodiments of the present invention, common mode risk can be specifically understood as: a common risk factor that affects multiple devices or multiple network parts in the network. Common mode risk may cause multiple systems or services to fail simultaneously when an accident occurs, thereby increasing the overall vulnerability of the system. In routing planning, identifying and managing common mode risks is crucial to improving network reliability.

[0061] Specifically, according to the formula:

[0062] Calculate the common mode risk of source node i and sink node j under the initial routing scheme at target time k Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution There is a common mode risk in this hop between adjacent routing nodes i′ and j′, otherwise it is 0. It is obtained by detecting the transmission channel between the source node i device and the sink node j device under the initial routing scheme at the target time k.

[0063] S230. Based on the deep Q network, the target main routing scheme and the target protection routing scheme between the source node device and the host node device are iteratively determined in the set of main routing schemes and protection routing schemes using the initial main routing scheme and the initial protection routing scheme corresponding to the target time and the risk balance level, the load balance level, the transmission delay between devices, the optical power, and at least one of the common mode risks.

[0064] The technical solution of the embodiment of the present invention first obtains the source node device and the sink node device of the main routing scheme and the protection routing scheme to be planned in the power communication network, and determines the initial main routing scheme and the initial protection routing scheme corresponding to the target time in the main routing scheme and the protection routing scheme set corresponding to the source node device and the sink node device. By refining the routing planning problem of a large network with multiple nodes into the routing planning sub-problems of a simple network, the routing calculation process is simplified, the accuracy and efficiency of the path selection are improved, and a comparison basis and a solution selection range are provided for the iterative optimization of subsequent routing planning solutions. The routing scheme and the protection routing scheme are used to plan the routing of the power communication network, which ensures the risk dispersion and rapid fault recovery of the power communication network, and improves the effect and reliability of the routing planning of the power communication network; then the source node device is controlled to send the service data to the sink node device based on the dual-transmission and selective reception method, based on the main routing scheme and the protection routing scheme, and obtain the risk balance level, load balance level, transmission delay between devices, optical power and at least one of the common mode risk corresponding to the initial main routing scheme and the initial protection routing scheme at the target time. Through the redundant mechanism of dual-transmission and selective reception, the risks caused by failures and congestion are reduced. The invention reduces the potential loss of information, improves the reliability of information transmission, and provides a data basis for the iterative optimization of subsequent routing schemes by collecting at least one routing environment information, so as to ensure that the risk distribution in the network is uniform, reduce the risk of interruption of the entire network service due to local failures, ensure reasonable distribution of traffic, prevent overload of certain links or devices, ensure that the delay requirements of services that require rapid response can be met, ensure the reliability of signals in the optical fiber-based communication network during transmission, avoid multiple key services relying on the same physical or logical resources, reduce common mode risks, and improve the reliability of routing planning; with the initial main routing scheme and the initial protection routing scheme corresponding to the target time and the information of the risk balance level, load balance level, transmission delay between devices, optical power and at least one of the common mode risks, iteratively determines the target main routing scheme and the target protection routing scheme between the source node device and the sink node device in the main routing scheme and the protection routing scheme set based on the deep Q network, and automatically explores and utilizes the routing scheme and makes decisions based on the routing environment information of the risk balance level, load balance level, transmission delay between devices, optical power and at least one of the common mode risks updated in real time through the deep Q network, responds to each change in network conditions, and dynamically adjusts the routing strategy. This process not only optimizes the path selection between the source node and the destination node, but also improves the effect of routing planning in a large node network, and improves the efficiency and reliability of routing planning.

[0065] Embodiment 3

[0066] Figure 3 This is a flow chart of a method for planning a route for a power communication network provided in Embodiment 3 of the present invention. Figure 3 As shown, the method includes:

[0067] S310, obtaining a source node device and a sink node device of a routing scheme to be planned in the power communication network, and determining an initial routing scheme corresponding to a target time in a set of routing schemes corresponding to the source node device and the sink node device.

[0068] S320: Control the source node device to send the service data to the sink node device according to the initial routing scheme at the target time, and obtain at least one item of routing environment information corresponding to the initial routing scheme at the target time.

[0069] S330, obtaining the experience of routing planning of the power communication network in a scenario similar to the power communication network, and initializing the parameters of the deep convolutional neural network based on the principle of the hot start process according to the experience of routing planning of the power communication network.

[0070] In the embodiment of the present invention, the power communication network routing planning experience can be specifically understood as: historical situations similar to the current network status or demand, which can be used to refer to or learn from previous routing planning solutions and the settings of network parameters therein.

[0071] In the embodiment of the present invention, hot start can be specifically understood as: using existing information, routing planning experience in similar scenarios or preset configurations to quickly start network services, rather than configuring from scratch.

[0072] Specifically, according to the principle of the hot start process, the weight parameter θ of the Q network is initialized using the experience of power communication network routing planning in similar scenarios, and the Q function is used To evaluate the status of source node transmission device i and sink node device j at time k The power communication network routing scheme selected The long-term accumulated discounted reward is used to initialize the experience pool, initialize the sampling parameters according to the number of extracted routing planning experiences, and initialize the trade-off parameters and unit parameters in the benefits. Construct the loss function according to the formula:

[0073] Calculate the loss function L ij (θ), where y represents the yth experience extracted, and x′ ij Indicates the next routing plan selected by the source node transmission device i and the sink node device j, represents the benefit of the routing plan selected by the source node transmission device i and the sink node device j under the yth experience, represents the expected value of selecting a batch of experiences from the experience base B, represents the target Q value, is the discount factor for the maximum Q value of all possible routing solutions, is in the next state The maximum Q value of all possible routing plans is: Is the current network status and routing planning solutions Q-value prediction.

[0074] A deep convolutional neural network is constructed in this way, which is used for iterative optimization and optimal selection of subsequent routing planning solutions.

[0075] S340, taking the initial routing scheme corresponding to the target time and at least one routing state information as the starting point, iterate in the routing scheme set according to the preset strategy to determine the new routing scheme to be executed at each new time, and obtain the new routing state information at each new time.

[0076] In an embodiment of the present invention, routing status information can be understood as: at the target time, receiving the risk balance level, load balance level and transmission delay information fed back by the destination node transmission device, and observing at least one routing environment information of the optical power level and common mode risk of the transmission channel.

[0077] Specifically, the initial routing scheme corresponding to the target time and at least one routing state information are used as the iteration starting point, and the source node transmission device is selected according to the ε greedy strategy to select the power communication network routing scheme. Choose to maximize the Q function with a high probability of 1-ε Power communication network routing scheme based on And retain a very small exploration probability ε to randomly select other possible power communication network routing schemes to balance the exploration and utilization of the source node transmission equipment learning process, avoid local optimality of the results, and improve the reliability of routing planning. Among them, 0<ε<1. After each iteration, the new routing state information at each new moment is obtained for subsequent continuous iterative operations in combination with the determined new moment routing planning scheme.

[0078] S350: Calculate the benefits of the power communication network routing planning that matches each new routing solution according to a preset benefit calculation formula.

[0079] In the embodiment of the present invention, planning benefit can be understood as: the advantage brought by effective routing planning. According to the formula:

[0080] Calculate the routing planning benefits of source node i and sink node j under the initial routing scheme at time k Where ψ is the optical power level coefficient, is the common mode risk coefficient, τ is the risk balance level coefficient, and κ is the unit transmission delay coefficient.

[0081] S360: Based on the new routing schemes, new routing status information and the routing planning benefits of the power communication network at each new moment, multiple experiences are constructed and added to the experience pool.

[0082] In the embodiment of the present invention, the experience pool can be understood as: used to store the experience of power communication network routing planning, and samples can be randomly extracted from it for training to improve learning efficiency and stability.

[0083] Specifically, the routing planning experience records the new routing scheme, the new routing state information, the routing planning benefits of the power communication network, and the next routing state information. The network needs to learn from past decisions and adapt to the changing network environment conditions. By updating the experience to the experience pool, the Q network can avoid overfitting and improve its generalization and reliability in complex routing planning tasks.

[0084] S370: After completing multiple iterations, a set amount of experience is sampled from the experience pool to update the parameters of the deep convolutional neural network.

[0085] Specifically, a set number of experiences are sampled from the experience pool and the loss function L is calculated. ij (θ) and use the stochastic gradient descent method to update the weight parameter θ of the Q network. The stochastic gradient descent method is used to minimize the loss function and improve the performance of the learning strategy. By combining with the experience pool and using historical data for training, the dependence on fresh data is reduced, the efficiency of data use in routing planning decisions is improved, the variance in the training process is reduced, the learning process is more stable, and the reliability of routing planning is improved.

[0086] S380, returning to execute the operation of iteratively determining a new routing scheme to be executed at each new time in the routing scheme set according to a preset strategy, and obtaining new routing state information at each new time, until the iteration termination condition is met.

[0087] The conditions for ending the iteration may include: the number of iterations reaches a preset threshold, or the learned new routing solution meets a convergence condition, etc.

[0088] S390: Determine the new routing solution that is most recently generated when the iteration ends as the target routing solution.

[0089] The technical solution of the embodiment of the present invention first obtains the source node device and the sink node device of the routing scheme to be planned in the power communication network, and determines the initial routing scheme corresponding to the target time in the routing scheme set corresponding to the source node device and the sink node device, and simplifies the routing calculation process by subdividing the multi-node routing planning problem of a large network into multiple simple network sub-problems, thereby improving the accuracy and efficiency of path selection, and providing a comparison basis and optional solutions for the subsequent iterative optimization of routing planning solutions, laying a foundation for formulating the optimal strategy; then the source node device is controlled to send service data to the sink node device according to the initial routing scheme at the target time, and at least one routing environment information corresponding to the initial routing scheme at the target time is obtained, providing a data basis for the environment information for the subsequent iterative optimization of the routing scheme; the routing planning experience of the power communication network in a scenario similar to the power communication network is obtained, and based on the routing planning experience of the power communication network, the parameters of the deep convolutional neural network are initialized based on the principle of the hot start process. By means of hot start, the initialization based on the experience in similar scenarios can improve the performance of the network in the new scenario, and the initial state of the network is close to the possible solution space area, which helps the network converge to the optimal solution faster and reduces the time and computing resources required for training. , enhance generalization ability, deep convolutional neural network can more effectively utilize existing knowledge, improve the efficiency and reliability of routing planning problems; take the initial routing plan corresponding to the target time and at least one routing state information as the starting point, iterate in the routing plan set according to the preset strategy to determine the new routing plan executed at each new time, and obtain the new routing state information at each new time, calculate the routing planning benefits of the power communication network matching each new routing plan according to the preset benefit calculation formula, and construct multiple experience-added routes based on the new routing plan, new routing state information and routing planning benefits of the power communication network at each new time. To the experience pool, after completing multiple iterations, a set number of experiences are sampled from the experience pool to update the parameters of the deep convolutional neural network, and the current routing planning scheme and the current routing environment information are combined to iterate the routing schemes in the routing scheme set one by one. After the iteration, the network parameters are updated, and the obtained post-execution routing status information and the calculated benefits of the routing planning scheme are updated as experience to the experience pool for continuous iteration. By combining historical planning experience with network status information, the utilization rate of data is increased, the dependence on fresh data is reduced to a certain extent, the learning process is more stable, and the reliability of routing planning is improved;Return to execute the operation of iterating in the routing scheme set according to the preset strategy to determine the new routing scheme executed at each new moment, and obtain the new routing status information at each new moment, until the end of the iteration condition is met, and the new routing scheme generated most recently at the end of the iteration is determined as the target routing scheme. By making full use of historical experience and current environmental information, reducing training time, continuously iterating and selecting the best, dynamically adjusting the routing strategy, improving the generalization ability, the routing planning scheme decided can better adapt to the new or changing environment, solve the problem of poor routing planning effect in the power communication network, and improve the efficiency and reliability of routing planning. ;

[0090] It needs to be emphasized again that the embodiments of the present invention propose an innovative power communication network routing planning scheme based on hot-start reinforcement learning. This scheme enables node devices to improve the routing planning efficiency of power communication services through continuous trial and error and dynamic optimization based on the load balancing, risk balancing, optical power level, transmission delay and common mode status information fed back by the network, using a hot-start reinforcement learning algorithm, combined with routing planning experience in similar scenarios, in the case of an unknown power communication network model. This not only improves the load balancing and optical power level of the power communication network, but also reduces the transmission delay and risk of service routing, thereby significantly improving the economic benefits of node devices and the overall operational stability of the power grid. Through this innovative method, it is expected to achieve more efficient, safer and more reliable data transmission in the routing planning of the power communication network, providing solid technical support for the stable operation of the new power system.

[0091] Embodiment 4

[0092] Figure 4 This is a structural diagram of a power communication network routing planning device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device specifically includes: an initial routing solution determination module 410, a routing environment information acquisition module 420, and a target routing solution determination module 430.

[0093] The initial routing scheme determination module 410 is used to obtain the source node device and the sink node device of the routing scheme to be planned in the power communication network, and determine the initial routing scheme corresponding to the target time in the routing scheme set corresponding to the source node device and the sink node device.

[0094] The routing environment information acquisition module 420 is used to control the source node device to send the service data to the sink node device according to the initial routing scheme at the target time, and to acquire at least one item of routing environment information corresponding to the initial routing scheme at the target time.

[0095] The target routing scheme determination module 430 is used to iteratively determine the target routing scheme between the source node device and the destination node device in the routing scheme set based on the deep Q network, taking the initial routing scheme corresponding to the target time and at least one routing state information as the starting point.

[0096] The technical solution of the embodiment of the present invention obtains the source node device and the sink node device of the routing solution to be planned in the power communication network, and determines the initial routing solution corresponding to the target time in the routing solution set corresponding to the source node device and the sink node device, thereby decomposing the complex large network multi-node routing problem into simple sub-network problems, which not only simplifies the routing calculation process, but also improves the accuracy and efficiency of path selection, and provides an important reference basis and selection solution for subsequent iterative optimization; controls the source node device to send the service data to the sink node device according to the initial routing solution at the target time, and obtains at least one routing environment information corresponding to the initial routing solution at the target time, so as to provide an important reference basis and selection solution for subsequent iterative optimization. It lays a data foundation; starting from the initial routing plan corresponding to the target time and at least one routing state information, the target routing plan between the source node device and the destination node device is iteratively determined in the routing plan set based on the deep Q network. The deep Q network automatically explores and utilizes routing plans in a complex network environment with a high-dimensional state space to make intelligent decisions. It can also flexibly respond to changes in network conditions and dynamically adjust routing strategies based on real-time routing environment information, thereby realizing the optimal selection of routing plans for source node devices and destination node devices in a known set of routing plans, solving the routing planning problem caused by a large number of nodes in large-scale power communication networks and improving the efficiency and reliability of routing planning.

[0097] On the basis of the above embodiments, the routing scheme includes a primary routing scheme and a protection routing scheme;

[0098] The routing status information includes at least one of the risk balance level, load balance level, transmission delay between devices, optical power and common mode risk of the routing solution;

[0099] The routing environment information acquisition module 420 is specifically used for:

[0100] The control source node device sends the service data to the sink node device based on the dual-send selective reception method, the main routing solution and the protection routing solution.

[0101] Based on the above embodiments, the routing environment information acquisition module 420 is further used to:

[0102] According to the formula: Calculate the risk balance level of the source node i device and the sink node j device under the initial routing scheme at the target time k

[0103] is the primary routing solution corresponding to the target time k The transmission route between adjacent routing nodes i′ and j′ transmission routing risks;

[0104] in, A is the failure probability constant, Transmitting routes between adjacent routing nodes i′ and j′ The risk probability value of failure, I n is the business importance of the nth business in the business data, and N is the total number of businesses in the business data; f m_avg Primary routing solution The average risk value of the transmission route;

[0105] U is the number of adjacent node device routes in the power communication network; is the protection routing scheme corresponding to the target time k The transmission path between adjacent routing nodes i′ and j′ The transmission routing risk, f q_avg To protect the routing scheme The average risk value of the transmission route;

[0106] in, It is determined according to information fed back by the sink node j device after receiving the service data.

[0107] Based on the above embodiments, the routing environment information acquisition module 420 is further used to:

[0108] According to the formula: Calculate the load balancing level of the source node i device and the sink node j device under the initial routing scheme at the target time k

[0109] in, is the service acceptance value of the source node i device, It is obtained by summing the ratio of the remaining high-order cross-connect capacity to the high-order cross-connect capacity and the ratio of the remaining low-order cross-connect capacity to the low-order cross-connect capacity of the source node i device. is the service admission value of the source node j device;

[0110] Primary routing solution The total bandwidth resources of the transmission route, Primary routing solution The remaining bandwidth resources of the transmission route, To protect the routing scheme The total bandwidth resources of the transmission route, To protect the routing scheme The remaining bandwidth resources of the transmission route;

[0111] in, It is determined according to information fed back by the sink node j device after receiving the service data.

[0112] Based on the above embodiments, the routing environment information acquisition module 420 is further used to:

[0113] According to the formula: Calculate the transmission delay between source node i and sink node j at target time k under the initial routing scheme

[0114] in, Primary routing solution And protection routing solution The node delay of the transmission route between adjacent routing nodes i′ and j′;

[0115] in, It is determined according to information fed back by the sink node j device after receiving the service data.

[0116] Based on the above embodiments, the routing environment information acquisition module 420 is further used to:

[0117] According to the formula: Calculate the optical power of source node i and sink node j at target time k under the initial routing scheme

[0118] Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution The optical power of this hop between adjacent routing nodes i′ and j′ meets the transmission requirements, otherwise it is 0; P in，max，i′j′ is the maximum input optical power of this hop between adjacent routing nodes i′ and j′, P in，min，i′j′ is the minimum input optical power of this hop between adjacent routing nodes i′ and j′;

[0119] in, It is obtained by detecting the transmission channel of the source node i device and the sink node j device under the initial routing scheme at the target time k.

[0120] Based on the above embodiments, the routing environment information acquisition module 420 is further used to:

[0121] According to the formula: Calculate the common mode risk of source node i and sink node j under the initial routing scheme at target time k

[0122] Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution There is a common mode risk in this hop between adjacent routing nodes i′ and j′, otherwise it is 0;

[0123] in, It is obtained by detecting the transmission channel of the source node i device and the sink node j device under the initial routing scheme at the target time k.

[0124] Based on the above embodiments, the target routing solution determination module 430 is specifically used to:

[0125] Acquire power communication network routing planning experience in scenarios similar to the power communication network, and initialize parameters of a deep convolutional neural network based on the hot start process principle according to the power communication network routing planning experience;

[0126] Taking the initial routing scheme corresponding to the target time and the at least one routing state information as the starting point, iteratively determine the new routing scheme to be executed at each new time in the routing scheme set according to the preset strategy, and obtain the new routing state information at each new time;

[0127] According to a preset benefit calculation formula, the benefits of the power communication network routing planning that matches each of the new routing schemes are calculated;

[0128] Based on the new routing schemes, new routing status information and the benefits of power communication network routing planning at each new moment, multiple experiences are constructed and added to the experience pool;

[0129] After completing multiple iterations, sampling a set number of experiences from the experience pool to update the parameters of the deep convolutional neural network;

[0130] Return to execute the operation of iterating in the routing solution set according to the preset strategy to determine the new routing solution to be executed at each new time, and obtain the new routing state information at each new time, until the end of iteration condition is met;

[0131] The new routing plan generated most recently when the iteration ends is determined as the target routing plan.

[0132] The power communication network routing planning device provided in the embodiment of the present invention can execute the power communication network routing planning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0133] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0134] Embodiment 5

[0135] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0136] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0138] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a route planning method for a power communication network.

[0139] That is:

[0140] The method comprises the following steps: obtaining a source node device and a sink node device of a routing scheme to be planned in a power communication network, and determining an initial routing scheme corresponding to a target time in a set of routing schemes corresponding to the source node device and the sink node device; controlling the source node device to send service data to the sink node device according to the initial routing scheme at the target time, and obtaining at least one item of routing environment information corresponding to the initial routing scheme at the target time; taking the initial routing scheme corresponding to the target time and the at least one item of routing status information as a starting point, iteratively determining a target routing scheme between the source node device and the sink node device in the set of routing schemes based on a deep Q network.

[0141] In some embodiments, the route planning method of the power communication network may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the route planning method of the power communication network described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the route planning method of the power communication network in any other appropriate manner (e.g., by means of firmware).

[0142] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0144] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0145] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0146] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0147] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for routing planning of a power communication network, characterized in that: include: Acquire a source node device and a sink node device of a routing scheme to be planned in the power communication network, and determine an initial routing scheme corresponding to a target time in a set of routing schemes corresponding to the source node device and the sink node device; Controlling the source node device to send service data to the sink node device according to the initial routing scheme at the target time, and obtaining at least one item of routing environment information corresponding to the initial routing scheme at the target time; Taking the initial routing scheme corresponding to the target time and the at least one routing state information as a starting point, a target routing scheme between the source node device and the sink node device is iteratively determined in the routing scheme set based on a deep Q network.

2. The method according to claim 1, characterized in that The routing plan includes a primary routing plan and a protection routing plan; The routing status information includes at least one of the risk balance level, load balance level, transmission delay between devices, optical power and common mode risk of the routing solution; Controlling the source node device to send the service data to the sink node device according to the initial routing scheme includes: The control source node device sends the service data to the sink node device based on the dual-send selective reception method, the main routing solution and the protection routing solution.

3. The method according to claim 2, characterized in that Acquiring at least one item of routing environment information corresponding to the initial routing solution, including: According to the formula: Calculate the risk balance level of the source node i device and the sink node j device under the initial routing scheme at the target time k is the primary routing solution corresponding to the target time k The transmission route between adjacent routing nodes i′ and j′ transmission routing risks; in, A is the failure probability constant, Transmitting routes between adjacent routing nodes i′ and j′ The risk probability value of failure, I n is the business importance of the nth business in the business data, and N is the total number of businesses in the business data; f m_avg Primary routing solution The average risk value of the transmission route; U is the number of adjacent node device routes in the power communication network; is the protection routing scheme corresponding to the target time k The transmission path between adjacent routing nodes i′ and j′ The transmission routing risk, f q_avg To protect the routing scheme The average risk value of the transmission route; in, It is determined according to information fed back by the sink node j device after receiving the service data.

4. The method according to claim 2, characterized in that: Acquiring at least one item of routing environment information corresponding to the initial routing solution, including: According to the formula: Calculate the load balancing level of the source node i device and the sink node j device under the initial routing scheme at the target time k in, is the service acceptance value of the source node i device, It is obtained by summing the ratio of the remaining high-order cross-connect capacity to the high-order cross-connect capacity and the ratio of the remaining low-order cross-connect capacity to the low-order cross-connect capacity of the source node i device. is the service admission value of the source node j device; Primary routing solution The total bandwidth resources of the transmission route, Primary routing solution The remaining bandwidth resources of the transmission route, To protect the routing scheme The total bandwidth resources of the transmission route, To protect the routing scheme The remaining bandwidth resources of the transmission route; in, It is determined according to information fed back by the sink node j device after receiving the service data.

5. The method according to claim 2, characterized in that: Acquiring at least one item of routing environment information corresponding to the initial routing solution, including: According to the formula: Calculate the transmission delay between source node i and sink node j at target time k under the initial routing scheme in, Primary routing solution And protection routing solution The node delay of the transmission route between adjacent routing nodes i′ and j′; in, It is determined according to information fed back by the sink node j device after receiving the service data.

6. The method according to claim 2, characterized in that Acquiring at least one item of routing environment information corresponding to the initial routing solution, including: According to the formula: Calculate the optical power of source node i and sink node j at target time k under the initial routing scheme Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution The optical power of this hop between adjacent routing nodes i′ and j′ meets the transmission requirements, otherwise it is 0; P in，max，i′j′ is the maximum input optical power of this hop between adjacent routing nodes i′ and j′, P in，min，i′j′ is the minimum input optical power of this hop between adjacent routing nodes i′ and j°; in, It is obtained by detecting the transmission channel of the source node i device and the sink node j device under the initial routing scheme at the target time k.

7. The method according to claim 2, characterized in that Acquiring at least one item of routing environment information corresponding to the initial routing solution, including: According to the formula: Calculate the common mode risk of source node i and sink node j under the initial routing scheme at target time k Where I(·) is an indicator function, which takes the value 1 when the condition in the brackets is met, indicating the main routing solution. And protection routing solution There is a common mode risk in this hop between adjacent routing nodes i′ and j′, otherwise it is 0; in, It is obtained by detecting the transmission channel of the source node i device and the sink node j device under the initial routing scheme at the target time k.

8. The method according to any one of claims 1 to 7, characterized in that: Taking the initial routing scheme corresponding to the target time and the at least one routing state information as a starting point, iteratively determining a target routing scheme between the source node device and the sink node device in the routing scheme set based on a deep Q network, including: Acquire power communication network routing planning experience in scenarios similar to the power communication network, and initialize parameters of a deep convolutional neural network based on the hot start process principle according to the power communication network routing planning experience; Taking the initial routing scheme corresponding to the target time and the at least one routing state information as the starting point, iteratively determine the new routing scheme to be executed at each new time in the routing scheme set according to the preset strategy, and obtain the new routing state information at each new time; According to a preset benefit calculation formula, the benefits of the power communication network routing planning that matches each of the new routing schemes are calculated; Based on the new routing schemes, new routing status information and the benefits of power communication network routing planning at each new moment, multiple experiences are constructed and added to the experience pool; After completing multiple iterations, sampling a set number of experiences from the experience pool to update the parameters of the deep convolutional neural network; Return to execute the operation of iterating in the routing solution set according to the preset strategy to determine the new routing solution to be executed at each new time, and obtain the new routing state information at each new time, until the end of iteration condition is met; The new routing plan generated most recently when the iteration ends is determined as the target routing plan.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the route planning method for the power communication network according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the route planning method for the power communication network according to any one of claims 1 to 8 when executed.

Images