Method and device for determining disaster resistance and reduction multi-scene resource scheduling strategy of power distribution network

Abstract

The invention belongs to the technical field of power systems, and particularly discloses a method and a device for determining a disaster resistance and reduction multi-scene resource scheduling strategy of a power distribution network. According to the method and the device, the line fault state of the power distribution network, the operation state of the power distribution network and each executable scheduling strategy corresponding to the flexible resources in the power distribution network at the current moment under each random scene in a random scene set consisting of fault scenes of the power distribution network caused by natural disasters (such as extreme weather events); and obtaining an optimal scheduling strategy of the flexible resources at the current moment in each random scene. According to the method, the optimal scheduling strategy of the flexible resources in various random scenes is comprehensively considered to cope with random and dynamic fault scenes caused by natural disasters, so that the disaster resistance and reduction capability of the power distribution network is improved.

Description

Technical Field

[0001] This application belongs to the field of power system technology, and more specifically, relates to a method and apparatus for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios. Background Technology

[0002] In recent years, natural disasters caused by climate change (such as extreme weather events with high-impact and low-probability (HILP) characteristics) have posed severe challenges to the operation of power systems (such as distribution networks). Severe power outages caused by extreme weather events highlight the urgency of enhancing the disaster resilience and mitigation capabilities of power systems.

[0003] In related technologies, after a natural disaster causes a power distribution network failure, the scheduling strategy is mostly solved by establishing an optimization planning model to cope with the failure scenario caused by the natural disaster. However, due to the uncertainty of the failure scenario caused by natural disasters, the algorithm for solving the optimization planning model in related technologies uses dynamic programming technology, which only considers certain specific operating modes in the power distribution network. The resulting scheduling strategy is difficult to adapt to the random and dynamic failure scenarios caused by natural disasters, resulting in poor disaster resistance and mitigation capabilities of the power distribution network. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the purpose of this application is to provide a method and device for determining resource scheduling strategies for disaster prevention and mitigation in multiple scenarios of power distribution networks, which aims to solve the problem of poor disaster prevention and mitigation capabilities of power distribution networks in related technologies.

[0005] To achieve the above objectives, firstly, this application provides a method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks across multiple scenarios, including:

[0006] Obtain the line fault status and operating status of the distribution network at the current time under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters.

[0007] Based on the executable scheduling strategies, line fault status, and operating status corresponding to the flexibility resources in the distribution network, determine the optimal scheduling strategy for the flexibility resources at the current moment under each random scenario.

[0008] In some embodiments, the optimal scheduling strategy for the current flexible resource under each random scenario is determined based on the executable scheduling strategies, line fault states, and operating states corresponding to the flexible resources in the distribution network, including:

[0009] For any random scenario in the set of random scenarios:

[0010] Based on the current line fault status and operating status under any random scenario, determine the expected benefits of each executable scheduling strategy at the current and future times.

[0011] The executable scheduling strategy with the highest expected benefits at the current and future times is taken as the optimal scheduling strategy for the current time's flexibility resources in any random scenario.

[0012] In some embodiments, based on the line fault state and operating state at the current moment in any random scenario, the expected benefits of each executable scheduling strategy at the current and future moments are determined, including:

[0013] Input the current line fault status and operating status under any random scenario into the target network model to determine the expected benefits of each executable scheduling strategy at the current and future times.

[0014] The target network model is trained in the following way:

[0015] Each executable scheduling strategy, the line fault status and operation status at historical moments under each random scenario are input into the preset network model for training. The parameters of the state value network and the action advantage network in the preset network model are updated until the preset network model converges.

[0016] The converged preset network model is used as the target network model.

[0017] In some embodiments, whether the preset network model has converged is determined in the following way:

[0018] If the difference between the predicted values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy output by the preset network model and the actual values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy is less than or equal to the preset value, the preset network model is determined to be converged.

[0019] In some embodiments, the flexibility resource includes:

[0020] Distributed power sources, interruptible loads, and interconnection switches.

[0021] In some embodiments, when the flexibility resources include distributed power sources, interruptible loads, and tie switches, the optimal scheduling strategy for the flexibility resources at the current moment in any random scenario from the set of random scenarios includes:

[0022] In any random scenario, the active power output of the distributed power source located at the first node in the distribution network at the current moment, the on / off state of the tie switch between the first lines, and the interruption power of the interruptible load located at the second node;

[0023] The first node is a node in the distribution network that has a distributed power source installed; the first line is the line between the third node and the fourth node; the third node and the fourth node are two nodes connected by tie switches in the distribution network; and the second node is a node in the distribution network that has an interruptible load installed.

[0024] Secondly, this application provides a device for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios, comprising:

[0025] The data acquisition module is used to acquire the line fault status and operating status of the distribution network at the current moment under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters.

[0026] The strategy generation module is used to determine the optimal scheduling strategy for the current time of the flexible resources under each random scenario, based on the executable scheduling strategies, line fault status, and operating status corresponding to the flexible resources in the distribution network.

[0027] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the method described in the first aspect or any possible implementation thereof.

[0028] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.

[0029] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.

[0030] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art:

[0031] This application provides a method and apparatus for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios. By considering the line fault status, operating status, and executable scheduling strategies corresponding to the flexible resources in the distribution network at the current moment within a random scenario set composed of fault scenarios caused by natural disasters (e.g., extreme weather events), the optimal scheduling strategy for the flexible resources at the current moment under each random scenario is obtained. This application comprehensively considers the optimal scheduling strategies for flexible resources under various random scenarios to address random and dynamic fault scenarios caused by natural disasters, thereby improving the disaster prevention and mitigation capabilities of the distribution network. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating the method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks across multiple scenarios, as provided in this application embodiment.

[0033] Figure 2 This is a schematic diagram of the structure of the power distribution network disaster mitigation and disaster relief multi-scenario resource scheduling strategy determination device provided in the embodiments of this application;

[0034] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0037] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0038] After an extreme weather event, the power outage load can be restored by distributed generators (DG) and renewable energy sources (RES), or it can be connected to another feeder powered by controlled DG or RES through network reconfiguration.

[0039] Related technologies can reduce load loss after natural disasters by using different hardening strategies such as updating poles and vegetation management, allocation strategies based on information gap decision theory, and establishing mixed integer programming models.

[0040] In the current technology for solving mixed-integer programming models, most optimization programming models are solved using commercial solvers such as CPLEX and GUROBI. Given the stochastic scenarios consisting of line faults under extreme weather events and distribution network operation scenarios, stochastic programming of resilient infrastructure in distribution networks needs to be solved under multi-variable constraints, including external environment and historical operating data with high-dimensional characteristics. During the solution process, the variable scale increases dramatically, leading to a failure to converge.

[0041] Based on this, embodiments of this application provide a method and apparatus for determining resource scheduling strategies for disaster prevention and mitigation in multiple scenarios of power distribution networks. The embodiments of this application are described below with reference to the accompanying drawings.

[0042] See Figure 1 The present application provides a method for determining resource scheduling strategies for disaster prevention and mitigation in multiple scenarios of power distribution networks, which may include steps 110 and 120.

[0043] Step 110: Obtain the line fault status and operating status of the distribution network at the current time under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters.

[0044] Step 120: Based on the executable scheduling strategies, line fault status, and operating status corresponding to the flexibility resources in the distribution network, determine the optimal scheduling strategy corresponding to the flexibility resources at the current moment under each random scenario.

[0045] In specific implementation, the set of random scenarios is a collection of random scenarios, which can be fault scenarios in the distribution network caused by natural disasters (such as extreme weather events). The line fault state of the distribution network can be various fault states that may occur in the distribution network due to natural disasters. The operating state of the distribution network can be the operating state of each device in the distribution network that may occur due to natural disasters. The current time can be any time; in this embodiment, t represents the current time.

[0046] For example, line fault conditions can include line interruption, distribution network voltage fluctuation, partial short circuit, unstable power supply, etc.

[0047] Based on the aforementioned line fault states, operating states, and executable scheduling strategies corresponding to the flexibility resources in the distribution network, a Q-function is constructed to represent the relationship between the resilience enhancement effect and each executable scheduling strategy. This Q-function can be used to characterize the resilience enhancement (or expected benefits) at the current and future times brought about by the execution of the corresponding executable scheduling strategies for flexibility resources. Furthermore, based on the expected benefits at the current and future times brought about by each executable scheduling strategy, the optimal scheduling strategy for flexibility resources is found among the various executable scheduling strategies.

[0048] Based on this optimal scheduling strategy, we can address random and dynamic fault scenarios caused by natural disasters and improve the disaster resistance and mitigation capabilities of the distribution network (i.e., the distribution network's ability to prepare for, absorb, and recover from HILP events).

[0049] This application provides a method for determining resource scheduling strategies for distribution networks under various disaster mitigation scenarios. By considering the line fault status, operating status, and executable scheduling strategies corresponding to the flexibility resources in the distribution network at the current moment within a random scenario set composed of fault scenarios caused by natural disasters (e.g., extreme weather events), the optimal scheduling strategy for the flexibility resources at the current moment under each random scenario is obtained. This application comprehensively considers the optimal scheduling strategies for flexibility resources under various random scenarios to address random and dynamic fault scenarios caused by natural disasters, thereby improving the disaster mitigation capabilities of the distribution network.

[0050] Furthermore, in some embodiments, the flexibility resources in step 120 may specifically include:

[0051] Distributed generation (DG), interruptible load (IL), and tie switches.

[0052] In practice, the various flexibility resources in this distribution network may include DG, IL and tie switches.

[0053] Furthermore, in some embodiments, when the flexibility resources include distributed power sources, interruptible loads, and tie switches, the optimal scheduling strategy for the flexibility resources at the current moment in any random scenario from the set of random scenarios may include:

[0054] In any random scenario, the active power output of the distributed power source located at the first node in the distribution network at the current moment, the on / off state of the tie switch between the first lines, and the interruption power of the interruptible load located at the second node;

[0055] The first node is a node in the distribution network that has a distributed power source installed; the first line is the line between the third node and the fourth node; the third node and the fourth node are two nodes connected by tie switches in the distribution network; and the second node is a node in the distribution network that has an interruptible load installed.

[0056] In specific implementation, this application embodiment establishes various subsets of flexible resources to find random scenarios for flexible planning. These subsets of flexible resources consist of executable scheduling strategies corresponding to the flexible resources in the random scenarios. In this application embodiment, the subsets of flexible resources may include a DG subset, a handshake switch subset, and an IL subset.

[0057] For example, for any random scene s: a subset of DG elements in Let represent the active power output by the DG at the first node i in any random scenario s at the current time t. (Connecting switch subset) medium elements Let represent the on / off state of the first line between the two nodes (the third node j and the fourth node k) connected by the liaison switch l in any random scenario s, where Different values ​​represent different on / off states of the tie switch l. IL subset elements in This represents the interrupt power of the IL at the second node m in any random scenario s, where the interrupt power refers to the active power.

[0058] Assume that the DG subset Contact switch subset and IL subset If the elements in the array are n1, n2, and n3, then:

[0059]

[0060] Where i = 1,...,n1, Ω DG Let Ω be the set of all first nodes in the distribution network. l = 1, ..., n², Ω tie Let m = 1, ..., n^3, Ω. IL It is the set of all second nodes in the distribution network.

[0061] The executable scheduling policy a corresponding to the flexibility resources at the current time t in any random scenario s. t It can be represented as: Among them, a t ∈a t ′, at ′ represents all executable scheduling policies corresponding to flexible resources.

[0062] The optimal scheduling strategy for flexibility resources in the distribution network at time t under any random scenario s in the set of random scenarios can be determined by considering all executable scheduling strategies a corresponding to the flexibility resources. t The optimal scheduling strategy is obtained by finding the active power output of the DG located at the first node i in the distribution network at the current time t, the on / off state of the tie switch l between the first lines, and the interruption power of the IL located at the second node m in the distribution network under any random scenario s.

[0063] Furthermore, in some embodiments, step 120, determining the optimal scheduling strategy for the current flexible resource under each random scenario based on the executable scheduling strategies, line fault states, and operating states corresponding to the flexible resources in the distribution network, may include:

[0064] For any random scenario in the set of random scenarios:

[0065] Based on the current line fault status and operating status under any random scenario, determine the expected benefits of each executable scheduling strategy at the current and future times.

[0066] The executable scheduling strategy with the highest expected benefits at the current and future times is taken as the optimal scheduling strategy for the current time's flexibility resources in any random scenario.

[0067] In its specific implementation, this application embodiment employs a deep reinforcement learning method to obtain the optimal scheduling strategy. The purpose of the deep reinforcement learning method is to achieve a nonlinear mapping from the line fault state, operating state, and various executable scheduling strategies corresponding to the flexibility resources of the distribution network to elastic enhancement.

[0068] Deep reinforcement learning is a model-free method that does not require prior knowledge. It uses historical state data to train neural networks to derive complex decisions. With sufficient historical data, the method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks provided in this application can adapt to larger-scale distribution networks.

[0069] Therefore, for any random scenario s, this application embodiment constructs a Q-function to describe the relationship between the elasticity enhancement effect and each executable scheduling strategy during the fault recovery process s. t Under (i.e., line fault state and operating state), the executable scheduling strategies corresponding to the flexibility resources are a t The expected benefits of ′ in the present and future moments.

[0070] For example, with an executable scheduling policy a t For example, the elastic enhancement effect constructed in the embodiments of this application and the executable scheduling strategy a t The Q-function of the relationship between them is Q(s) t ,a t The specific formula is as follows:

[0071] Q(s t ,a t )=E[r(s t ,a t )+μr(s t+1 ,a t+1 )+μ 2 r(s t+2 ,a t+2 ...]

[0072] =E[r(s) t ,a t )+μQ(s t+1 ,a t+1 )]

[0073] Where r(s) t ,a t () represents the executable scheduling strategy for the flexible resources in the distribution network at time t under any random scenario s. t The reward obtained is the flexibility to execute executable scheduling strategies. t The subsequent benefits to the distribution network; μ is the discount factor, with a value range of [0, 1]. A higher discount factor means that the reinforcement learning self-learning agent focuses more on long-term returns, while a lower discount factor focuses more on short-term returns. t+1 Let a be the line fault state and operating state of the distribution network at the next time step t+1 under any random scenario s. t+1 Let be an executable scheduling strategy for the flexible resources in the distribution network at the next time step t+1 under any random scenario s.

[0074] By substituting the line fault state, operational state, and executable scheduling strategies at the current time t under any random scenario s into the Q function above, we can calculate the executable scheduling strategies a corresponding to the flexibility resources at the current time t under any random scenario s. t The expected benefits brought about by ′ at the current time t and in the future time.

[0075] By comparing the executable scheduling strategies a under any random scenario s t By considering the expected benefits of each scheduling strategy at the current time t and in the future, we can find the executable scheduling strategy a. tThe executable scheduling strategy that yields the highest expected benefits at the current time t and future time is identified, and it is used as the optimal scheduling strategy for the flexibility resources at the current time t under any random scenario s.

[0076] By performing the same processing procedure as for any random scenario s on the remaining random scenarios in the set of random scenarios, the optimal scheduling strategy corresponding to the flexibility resources at the current moment in each random scenario can be obtained.

[0077] By analyzing the optimal scheduling strategy corresponding to the current time of flexible resources under various random scenarios, planning schemes for DG, tie switches and IL are obtained, such as the location and capacity of new DG, the location of tie switches and the interrupt capacity of IL.

[0078] This application embodiment analyzes the optimal scheduling resources corresponding to the flexibility resources under various random scenarios, and finally obtains the optimal planning scheme for flexibility resources after a natural disaster, which can provide rational suggestions for the planning of urban resilient infrastructure.

[0079] Furthermore, in some embodiments, the step of determining the expected benefits of each executable scheduling strategy at the current and future times based on the line fault state and operating state at the current time under any random scenario may include:

[0080] Input the current line fault status and operating status under any random scenario into the target network model to determine the expected benefits of each executable scheduling strategy at the current and future times.

[0081] The target network model is trained in the following way:

[0082] Each executable scheduling strategy, the line fault status and operation status at historical moments under each random scenario are input into the preset network model for training. The parameters of the state value network and the action advantage network in the preset network model are updated until the preset network model converges.

[0083] The converged preset network model is used as the target network model.

[0084] In the specific implementation, an executable scheduling policy a is used. t For example, since Q(s) t ,a t Analytical expressions for Q(s) are difficult to obtain; therefore, embodiments of this application employ a target network model to implement the expression for Q(s). t ,a t The parameterized approximation of the target network is obtained by training a pre-defined network model, which can be specifically derived from the state-value network V(s). t;θ v ) and Action Advantage Network A ( s t,a t ;θ a )constitute.

[0085] Where, θ v Let θ be the parameter to be optimized in the state-value network. a These are the parameters to be optimized in the action advantage network.

[0086] Using a state-value network V(s) t ;θ v ) and Action Advantage Network A(s t ,a t ;θ a Construct the action value function Q(s) t ,a t ;θ v ,θ a ):

[0087]

[0088] Among them, Ω A Let |Ω be the set of all executable scheduling policies corresponding to flexible resources. A | represents the number of actions for all executable scheduling policies.

[0089] By continuously training a pre-set network model, the accuracy of the approximate Q-function can be continuously improved.

[0090] The training process of the preset network model is as follows:

[0091] The executable scheduling strategies corresponding to the flexibility resources, the historical line fault states and operating states under each random scenario in the random scenario set are input into the preset network model for training, and the state-value network V(s) is trained. t ;θ v The parameter θ v and Action Advantage Network A(s) t ,a t ;θ a The parameter θ a Update the network until the preset network model converges. Use the converged preset network model as the target network model.

[0092] Furthermore, in some embodiments, whether the preset network model has converged is determined in the following way:

[0093] If the difference between the predicted values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy output by the preset network model and the actual values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy is less than or equal to the preset value, the preset network model is determined to be converged.

[0094] Specifically, the loss function of the state-value network V(s) can be minimized. t ;θ v The parameter θ in ) v and Action Advantage Network A(s) t ,a t ;θ a The parameter θ a Update. In this embodiment, the loss function can be specifically determined based on the difference between the predicted values ​​of the expected benefits of each executable scheduling strategy at the current and future times, output by the preset network model, and the actual values ​​of the expected benefits of each executable scheduling strategy at the current and future times.

[0095] By comparing the differences between the predicted values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy output by the preset network model and the actual values ​​of the expected benefits at the current and future times brought by each executable scheduling strategy, and the preset value, it is determined whether the preset network model has converged. If the differences obtained are all less than the preset value, then the preset network model is determined to have converged. In this embodiment, the preset value is a constant close to 0.

[0096] This application provides a method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks across multiple scenarios. By constructing a Q-function relating the elasticity enhancement effect to various executable scheduling strategies corresponding to flexible resources, and using a reinforcement learning algorithm based on a competitive network architecture, the nonlinear mapping from each executable scheduling strategy to elasticity enhancement is obtained. This method traverses all random scenarios to obtain the optimal scheduling strategy for each scenario. This overcomes the limitations of traditional planning methods that use commercial solvers and solves the convergence problem in solving stochastic programming models. Furthermore, this application significantly improves the distribution network's ability to withstand natural disasters and reduces load losses by rationally optimizing various flexible resources.

[0097] The following describes the distribution network disaster mitigation and mitigation multi-scenario resource scheduling strategy determination device provided in this application. The distribution network disaster mitigation and mitigation multi-scenario resource scheduling strategy determination device described below can be referred to in correspondence with the distribution network disaster mitigation and mitigation multi-scenario resource scheduling strategy determination device method described above.

[0098] See Figure 2This application provides a device for determining resource scheduling strategies for disaster prevention and mitigation in multiple scenarios of power distribution networks, which may include: a data acquisition module 210 and a strategy generation module 220.

[0099] The data acquisition module 210 is used to acquire the line fault status and operating status of the distribution network at the current time under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters.

[0100] The strategy generation module 220 is used to determine the optimal scheduling strategy for the current time of the flexible resources under each random scenario based on the executable scheduling strategies, line fault status and operating status corresponding to the flexible resources in the distribution network.

[0101] This application provides a device for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks across multiple scenarios. This device determines the optimal scheduling strategy for flexible resources in each random scenario by considering the line fault state, operating state, and executable scheduling strategies corresponding to flexible resources in the distribution network at the current moment within a random scenario set composed of fault scenarios caused by natural disasters (e.g., extreme weather events). By comprehensively considering the optimal scheduling strategies for flexible resources under various random scenarios, this application aims to address random and dynamic fault scenarios caused by natural disasters, thereby improving the disaster prevention and mitigation capabilities of the distribution network.

[0102] It is understood that the detailed functional implementation of each of the above units / modules can be found in the description in the aforementioned method embodiments, and will not be repeated here.

[0103] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0104] Based on the methods in the above embodiments, this application provides an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communications interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute the methods in the above embodiments.

[0105] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0106] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0107] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the methods in the above embodiments.

[0108] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0109] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0110] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0111] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0112] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios, characterized in that, include: Obtain the line fault status and operating status of the distribution network at the current time under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters. Based on the executable scheduling strategies corresponding to the flexibility resources in the distribution network, the line fault status, and the operating status, the optimal scheduling strategy corresponding to the flexibility resources at the current time under each random scenario is determined.

2. The method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios as described in claim 1, characterized in that, The step of determining the optimal scheduling strategy for the current time of each of the random scenarios based on the executable scheduling strategies corresponding to the flexibility resources in the distribution network, the line fault status, and the operating status includes: For any random scenario in the set of random scenarios: Based on the line fault state and the operating state at the current moment in any random scenario, determine the expected benefits of each executable scheduling strategy at the current moment and in the future moment. The executable scheduling strategy with the highest expected benefits at the current and future times is taken as the optimal scheduling strategy for the flexibility resource at the current time in any random scenario.

3. The method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios as described in claim 2, characterized in that, The step of determining the expected benefits of each executable scheduling strategy at the current and future times based on the line fault state and the operating state at the current time under the arbitrary random scenario includes: The line fault state and the operating state at the current moment under any random scenario are input into the target network model to determine the expected benefits of each executable scheduling strategy at the current moment and in the future moment. The target network model is trained in the following manner: Each executable scheduling strategy, the line fault status and the running status at historical moments under each random scenario are input into a preset network model for training. The parameters of the state value network and the action advantage network in the preset network model are updated until the preset network model converges. The converged preset network model is used as the target network model.

4. The method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios as described in claim 3, characterized in that, Whether the preset network model has converged is determined by the following method: If the difference between the predicted values ​​of the expected benefits at the current and future times brought about by each of the executable scheduling strategies output by the preset network model and the actual values ​​of the expected benefits at the current and future times brought about by each of the executable scheduling strategies is less than or equal to a preset value, the preset network model is determined to have converged.

5. The method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios as described in any one of claims 1-4, characterized in that, The flexibility resources include: Distributed power sources, interruptible loads, and interconnection switches.

6. The method for determining resource scheduling strategies for disaster prevention and mitigation in distribution networks under multiple scenarios as described in claim 5, characterized in that, When the flexible resources include distributed power sources, interruptible loads, and tie switches, the optimal scheduling strategy for the flexible resources at the current time in any random scenario within the set of random scenarios includes: In any random scenario, the active power output of the distributed power source located at the first node in the distribution network at the current moment, the on / off state of the tie switch between the first lines, and the interruption power of the interruptible load located at the second node; Wherein, the first node is a node in the distribution network that is equipped with the distributed power source, the first line is the line between the third node and the fourth node, the third node and the fourth node are two nodes connected by the tie switch in the distribution network, and the second node is a node in the distribution network that is equipped with the interruptible load.

7. A device for determining resource scheduling strategies for disaster prevention and mitigation in power distribution networks under multiple scenarios, characterized in that, include: The data acquisition module is used to acquire the line fault status and operating status of the distribution network at the current time under each random scenario in the random scenario set. The random scenario set is a set composed of random scenarios, and the random scenario is a fault scenario of the distribution network caused by natural disasters. The strategy generation module is used to determine the optimal scheduling strategy corresponding to the flexibility resource at the current time under each random scenario based on the executable scheduling strategies corresponding to the flexibility resources in the distribution network, the line fault status, and the operating status.

8. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on the processor, it causes the processor to perform the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the computer program product is run on a processor, the processor causes the processor to perform the method as described in any one of claims 1-6.

Images