Method and apparatus for determining recovery deployment scheme of power distribution network, and computer device

Abstract

The present application relates to a method and apparatus for determining a recovery deployment scheme of a power distribution network, a computer device, a storage medium and a computer program product. The method comprises: generating a plurality of typical flooding and waterlogging disaster scenarios of a power distribution network; determining a load recovery item and a maintenance time item corresponding to the plurality of typical flooding and waterlogging disaster scenarios, and on the basis of the load recovery item and the maintenance time item, generating an objective function corresponding to the typical flooding and waterlogging disaster scenarios; determining at least one element recovery constraint condition of the objective function, wherein the element recovery constraint condition is used for constraining the recovery process of the power distribution network; determining a target drainage scheme and a target maintenance scheme that meet the at least one element recovery constraint condition and maximize the objective function; and on the basis of the target drainage scheme and the target maintenance scheme, obtaining a recovery deployment scheme of the power distribution network. Use of the method can improve the rationality of the recovery deployment scheme of the power distribution network.

Description

Method, device and computer equipment for determining distribution network restoration deployment plan

[0001] This application claims priority to Chinese patent application number 202311572797.8, filed on November 21, 2023, entitled “Method, device and computer equipment for determining distribution network restoration deployment plan”, the entire text of which is hereby incorporated by reference. Technical Field

[0002] The present application relates to the technical field of distribution network technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for determining a distribution network restoration deployment plan. Background Art

[0003] As the risk of extreme weather disasters continues to increase, urban flooding is becoming more frequent. Due to the high uncertainty of urban flooding, the severe damage caused by accumulated water to circuit components, and the difficulty in repairing components caused by accumulated water, this has a negative impact on the distribution network.

[0004] In traditional methods, after a disaster occurs, relevant agencies usually arrange personnel to drain and repair the distribution network.

[0005] However, the arrangement of personnel after a disaster is temporary, which leads to unreasonable arrangement plans and reduces the rationality of the distribution network restoration deployment plan.

[0006] Summary of the Invention

[0007] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining a distribution network restoration deployment plan that can improve the rationality of the distribution network restoration deployment plan in response to the above technical problems.

[0008] In the first aspect, the present application provides a method for determining a distribution network restoration deployment plan. The method includes: generating multiple typical flooding disaster scenarios of the distribution network; the typical flooding disaster scenario is characterized by the damage status of multiple components in the distribution network; determining the load recovery item and maintenance time item corresponding to the typical flooding disaster scenario, and generating an objective function corresponding to the typical flooding disaster scenario based on the load recovery item and maintenance time item; the objective function is positively correlated with the load recovery item, and negatively correlated with the maintenance time item; the load recovery item represents the degree of recovery of the load carried at the node, and the maintenance time item represents the time taken to restore the damaged components in the distribution network; the node represents the structure used to convert voltage in the distribution network; determining at least one component recovery constraint of the objective function; the component recovery constraint is used to constrain the distribution network restoration process; determining a target drainage plan and a target maintenance plan that satisfy at least one component recovery constraint and maximizes the objective function; and obtaining a distribution network restoration deployment plan based on the target drainage plan and the target maintenance plan.

[0009] In the second aspect, the present application also provides a distribution network restoration deployment plan determination device. It includes: a scenario generation module, which is used to generate multiple typical waterlogging disaster scenarios of the distribution network; the typical waterlogging disaster scenarios are characterized by the damage status of multiple components in the distribution network; a function generation module, which is used to determine the load recovery item and maintenance time item corresponding to the typical waterlogging disaster scenario, and generate an objective function corresponding to the typical waterlogging disaster scenario based on the load recovery item and maintenance time item; the objective function is positively correlated with the load recovery item, and negatively correlated with the maintenance time item; the load recovery item represents the degree of recovery of the load carried at the node, and the maintenance time item represents the time taken to restore the damaged component in the distribution network; the node represents the structure for converting voltage in the distribution network; a constraint condition determination module, which is used to determine at least one component recovery constraint condition of the objective function; the component recovery constraint condition is used to constrain the distribution network restoration process; a first solution determination module, which is used to determine a target drainage solution and a target maintenance solution that satisfy at least one component recovery constraint condition and maximizes the objective function; a second solution determination module, which is used to obtain a distribution network restoration deployment plan based on the target drainage solution and the target maintenance solution.

[0010] In some embodiments, the function generation module includes an objective function, which is:

[0011] in, is the load recovery term, is the maintenance time term, s represents any typical flooding disaster scenario in S, S is a set of multiple typical flooding disaster scenarios, π sis the probability of a typical flood disaster scenario s occurring, α1 is the weight of the load recovery term, and α2 is the weight of the maintenance time term; t is the moment in the distribution network recovery process, t∈{1,2,…,T}, Δt is the time interval between two adjacent moments in {1,2,…,T}, and T represents the Tth moment in the distribution network recovery process; V represents the node set of the distribution network; j is any node in the node set of the distribution network; w j is the weight of the load carried by node j; Indicates whether the load carried by node j is restored at time t in any typical flooding disaster scenario s; represents the active power of the load carried by node j at time t in any typical flood disaster scenario s; n represents an element in the distribution network, N s is the set of damaged components of the distribution network under any typical flooding disaster scenario s; Indicates whether component n is repaired at time t in any typical flooding disaster scenario s.

[0012] In some embodiments, the constraint determination module further includes:

[0013] Where i is any node in the node set of the distribution network; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; represents the power-on status of node i at time t in any typical flood disaster scenario s; represents the available state of node i at time t in any typical flood disaster scenario s; Equivalent to the objective function

[0014] In some embodiments, the constraint determination module further includes:

[0015] Where L is the line set of the distribution network, (j, i) is a line segment in the distribution network line set that starts at node j and ends at node i; represents the active power transmitted by line (j, i) at time t under any typical flood disaster scenario s; represents the active power injected into node i at time t under any typical flooding disaster scenario s; represents the active power of the power source at node i at time t under any typical flood disaster scenario s; the power source is a distributed power source; (i, j) is a line in the distribution network that starts at node i and ends at node j; represents the active power transmitted by line (i, j) at time t under any typical flood disaster scenario s; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; In any typical flood disaster scenario s, the active power of the load carried by node i at time t; Equivalent to the objective function

[0016] In some embodiments, the constraint determination module further includes

[0017] in, represents the time when maintenance team r starts to repair component n in any typical flood disaster scenario s. Maintenance team r is a team that repairs component n in the distribution network; represents the time consumed by maintenance team r to repair component n in any typical flood disaster scenario s; Indicates whether the accumulated water at component n is drained at time t in any typical flood disaster scenario s; represents the moment when drainage team p starts draining water at component n in any typical flooding disaster scenario s. Drainage team p is a team that drains water at component n in the distribution network. represents the time that drainage team p consumes in draining components under any typical flood disaster scenario s; Repair is the set of repair teams that repair damaged components in the distribution network; Pump is the set of drainage teams that remove water from each node in the distribution network; With the objective function Same meaning.

[0018] In some embodiments, the scenario generation module is also used to obtain precipitation information and disaster intensity information of the distribution network within a target time period; obtain component quality characterization values ​​of multiple components in the distribution network, and determine the damage probability of each component based on the disaster intensity information and the component quality characterization value of each component; generate multiple urban flooding disaster scenarios based on the damage probability of each component; each urban flooding disaster scenario is characterized by the damage status of multiple components, and for two different urban flooding disaster scenarios, there is at least one component with a different damage status; and determine multiple typical urban flooding disaster scenarios from multiple urban flooding disaster scenarios.

[0019] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the method for determining a distribution network restoration deployment plan are implemented.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for determining a distribution network restoration deployment plan.

[0021] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the steps in the method for determining a distribution network restoration deployment plan.

[0022] The above-mentioned distribution network restoration deployment plan determination method, device, computer equipment, storage medium and computer program product, based on the typical flooding disaster scenario of the generated distribution network, constructs an objective function regarding the load recovery and maintenance time of the distribution network, and determines multiple constraints for the objective function, so that the restoration deployment method for the distribution network can be determined. Since the objective function is positively correlated with the load recovery term and negatively correlated with the maintenance time term, the purpose of the objective function is to maximize the load recovery term and minimize the maintenance time term, so that the target drainage plan and target maintenance plan when the objective function is maximized can make the load recovery term as large as possible and the maintenance time term as small as possible. The distribution network restoration deployment plan obtained according to the target drainage plan and target maintenance plan when the objective function is maximized can make the distribution network recovery time as short as possible and the recovery degree as large as possible, thereby improving the rationality of the distribution network restoration deployment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] FIG1 is a diagram illustrating an application environment of a method for determining a distribution network restoration deployment plan according to an embodiment;

[0025] FIG2 is a flow chart of a method for determining a distribution network restoration deployment plan in one embodiment;

[0026] FIG3 is a schematic diagram of a topological structure of a power distribution network in one embodiment;

[0027] FIG4 is a structural block diagram of a device for determining a distribution network restoration deployment plan in one embodiment;

[0028] FIG5 is a diagram showing the internal structure of a computer device according to one embodiment;

[0029] FIG6 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0031] The method for determining a distribution network restoration deployment plan provided in an embodiment of the present application can be applied in the application environment shown in FIG1 . The data storage system can store data that the computer device 102 needs to process. The data storage system can be integrated with the computer device 102 or placed on a cloud or other network server.

[0032] Specifically, computer device 102 generates a typical flooding disaster scenario for the distribution network, then determines a load recovery term and a maintenance time term corresponding to the typical flooding disaster scenario. Based on the load recovery term and the maintenance time term, an objective function corresponding to the typical flooding disaster scenario is generated. Computer device 102 determines at least one component restoration constraint in the objective function and, if the at least one component restoration constraint is satisfied, determines a target drainage plan and a target maintenance plan that maximize the objective function. Thus, a distribution network restoration deployment plan is derived based on the target drainage plan and the target maintenance plan that maximize the objective function.

[0033] The computer device 102 may be a server or a terminal. Terminals may include, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. The server may be implemented as a standalone server or a server cluster consisting of multiple servers.

[0034] In an exemplary embodiment, as shown in FIG2 , a method for determining a distribution network restoration deployment plan is provided, which is described by taking the method applied to the computer device 102 in FIG1 as an example, and includes the following steps 202 to 210 . Among them:

[0035] Step 202 : Generate a typical flood disaster scenario of the distribution network; the typical flood disaster scenario is represented by the damage status of multiple components in the distribution network.

[0036] The distribution network is a power grid that distributes electricity to various users through distribution facilities. A flood disaster refers to a disaster caused by surface water accumulation or flooding. A flood disaster scenario is characterized by the damage status of multiple components in the distribution network. For example, if the distribution network has 200 components, of which 10 are damaged and 190 are undamaged, then these 200 components and their corresponding damage status can represent a flood disaster scenario. Components are devices or components used to transmit, distribute, and control the flow of electricity on the distribution network. For example, components include but are not limited to transformers, switchgear, distribution boards, busbar systems, lightning arresters, electricity meters, and cables. A typical flood disaster scenario is selected from multiple flood disaster scenarios. For example, a typical flood disaster scenario can be a cluster center obtained by clustering multiple flood disaster scenarios.

[0037] Specifically, the computer device can use Monte Carlo simulation to generate multiple flooding disaster scenarios corresponding to the distribution network, where "multiple" means at least one. For example, the computer device can obtain precipitation forecasts and flooding disaster intensity estimates for each region in the distribution network from official meteorological agencies. Based on the component quality indicators of each component in the distribution network and the flooding disaster intensity estimates, the computer device can generate the damage probability of each component in the distribution network. For example, there are three components in the distribution network, denoted as component d, component e, and component f. The damage probability of component d is 0.3, the damage probability of component e is 0.4, and the damage probability of component f is 0.8. The computer device compares the damage probability of component d with a uniformly distributed random number in the interval (0, 1). If the random number is 0.6, and the damage probability 0.3 is less than the random number 0.6, the damage state of component d is defined as undamaged. Similarly, the damage states of components e and f can be determined. The computer then compares each component's damage probability with a uniformly distributed random number in the interval (0, 1). This means that each component's damage probability can correspond to the same random number or a different random number. The computer then uses the comparison results of each component's damage probability with the random number to determine the damage status of each component in the distribution network. Once the computer has determined the damage status of each component in the distribution network, it can simulate a flooding disaster scenario. The computer can repeat this process until multiple flooding disaster scenarios are generated.

[0038] In some embodiments, the computer device may use a k-center clustering algorithm to cluster the generated multiple flooding disaster scenarios to obtain multiple typical flooding disaster scenarios. Assume that the computer device generates a total of a flooding disaster scenarios, which are numbered X1, X2, ..., Xa. Given m components in the distribution network, each flooding disaster scenario has m attributes. First, the computer device presets the number of typical flooding disaster scenarios to k. Thus, from the a flooding disaster scenarios, the computer device randomly selects k flooding disaster scenarios as initial cluster centers, with each initial cluster center belonging to a different cluster. Then, the computer device calculates the distance from each flooding disaster scenario to each initial cluster center and sequentially compares the distance from each flooding disaster scenario to each initial cluster center to obtain a comparison result. The smaller the comparison result, the closer the flooding disaster scenario is to the initial cluster center corresponding to the comparison result. Based on the comparison results, the computer device divides each flood disaster scene into the cluster where the initial cluster center corresponding to the minimum comparison result is located. The distance from each flood disaster scene to each initial cluster center can be calculated by the formula Calculation is performed, where Xi represents the i-th flooding disaster scenario, Cj represents the j-th initial cluster center, Xiv represents the v-th attribute of the i-th flooding disaster scenario, and Cjv represents the v-th attribute of the j-th initial cluster center. Subsequently, the computer device sequentially selects each flooding disaster scenario within each cluster and calculates the sum of the distances between each flooding disaster scenario and all scenarios in the current cluster, obtaining a calculation result. Based on the calculation result, the computer device determines the flooding disaster scenario with the smallest sum of distances to all flooding disaster scenarios in the current cluster and selects the flooding disaster scenario with the smallest sum of distances as the new cluster center in the current cluster. The above steps are then repeated until no new cluster centers are generated in each cluster, or when the distance between the latest cluster center in each cluster and the surrounding flooding disaster scenarios is extremely small. The computer device then outputs a clustering result, which is a collection of multiple typical flooding disaster scenarios. The clustering result is the final cluster center generated in each cluster, totaling k. The computer device will generate k typical flooding disaster scenes as s0, s1, ..., sk, and the set of all typical flooding disaster scenes is S. Then the probability of each typical flooding disaster scene is Among them, π s is the probability of occurrence of any typical flood disaster scenario s, num s is the number of scenes in the cluster where any typical flooding disaster scene s is located, and num is the total number of scenes.

[0039] Step 204, determine the load recovery item and maintenance time item corresponding to the typical urban flooding disaster scenario, and generate the objective function corresponding to the typical urban flooding disaster scenario based on the load recovery item and the maintenance time item; the objective function is positively correlated with the load recovery item, and negatively correlated with the maintenance time item; the load recovery item represents the degree of recovery of the load carried at the node, and the maintenance time item represents the time used to restore damaged components in the distribution network; the node represents the structure used to convert voltage in the distribution network.

[0040] The load recovery term represents the degree of recovery of the load carried at each node in the distribution network. The greater the degree of recovery, the better the distribution network recovery, that is, the closer it is to a normal distribution network. The repair time term represents the total time required to restore all damaged components in the distribution network. Each solution to the objective function corresponds to a distribution network restoration deployment plan. When the optimal solution to the objective function is obtained, the most suitable distribution network restoration deployment plan can be obtained. A node is an abstract representation in topology, and a node can connect to different components. If the distribution network is abstracted as a network, then lines and nodes are important components of the network. Nodes can be considered as power supply points in the distribution network, receiving electrical energy from the upper-level power grid, converting the received electrical energy into a voltage, and then transmitting it to users. The upper-level power grid is usually the transmission network. Nodes are connected by cables, which are components of the lines. The structures used for voltage conversion include transformers or load switches. Transformers are also a component.

[0041] Specifically, the objective function may be, for example:

[0042] The objective function maximization can be achieved by maximizing the objective function, which can be expressed as:

[0043] in, is the load recovery term, is the maintenance time term, s represents any typical flooding disaster scenario in S, S is a set of multiple typical flooding disaster scenarios, π s is the probability of a typical flood disaster scenario s occurring, α1 is the weight of the load recovery term, and α2 is the weight of the maintenance time term; t is the moment in the distribution network recovery process, t∈{1,2,…,T}, Δt is the time interval between two adjacent moments in {1,2,…,T}, and T represents the Tth moment in the distribution network recovery process; V represents the node set of the distribution network; j is any node in the node set of the distribution network; w j is the weight of the load carried by node j; Indicates whether the load carried by node j is restored at time t in any typical flooding disaster scenario s; represents the active power of the load carried by node j at time t in any typical flood disaster scenario s; n represents an element in the distribution network, N s is the set of damaged components of the distribution network under any typical flooding disaster scenario s; Indicates whether component n is repaired at time t in any typical flooding disaster scenario s.

[0044] In some embodiments, the computer device determines a load recovery item and a maintenance time item corresponding to any one of the multiple generated typical flooding disaster scenarios. Based on the load recovery item and the maintenance time item corresponding to the typical flooding disaster scenario, an objective function corresponding to the typical flooding disaster scenario can be generated. During the objective function optimization process, the objective function is positively correlated with the load recovery item, i.e., the greater the value of the load recovery item, the higher the degree of optimization of the objective function; and the objective function is negatively correlated with the maintenance time item, i.e., the smaller the value of the maintenance time item, the higher the degree of optimization of the objective function.

[0045] In some embodiments, the topological structure of the distribution network is shown in Figure 3. The solid circles in Figure 3 represent nodes in the distribution network. Figure 3 shows 32 nodes, namely node 1 to node 32. The solid lines connecting the nodes represent the transmission lines of electric energy in the normal operating state of the distribution network, and the dotted lines connecting the nodes represent the transmission lines of electric energy in the distribution network when the lines are damaged or in other abnormal operating states.

[0046] In some embodiments, each typical urban flooding disaster scene corresponds to a scene set, and the scene set corresponding to the typical urban flooding disaster scene includes the typical urban flooding disaster scene and at least one urban flooding disaster scene similar to the typical urban flooding disaster scene.

[0047] Step 206: Determine at least one component recovery constraint of the objective function; the component recovery constraint is used to constrain the distribution network recovery process.

[0048] Component recovery constraints are formulas that constrain the range of variables in the objective function and are used to constrain the distribution network recovery process. For example, component recovery constraints can constrain the variables in the maintenance time term. By constraining the variables in the maintenance time term, the numerical range of the maintenance time term can be refined, thereby improving the optimization level of the objective function. Component recovery constraints can include team dispatch constraints, recovery time constraints, recovery status constraints, and operating status constraints.

[0049] Specifically, computer equipment can constrain the variables in the objective function based on historical waterlogging disasters and typical waterlogging disaster scenarios; it can also constrain the variables in the objective function based on the efficiency of the drainage team and the maintenance team; it can also constrain the variables in the objective function based on the number of components installed at each node of the distribution network.

[0050] Step 208 : determining a target drainage solution and a target maintenance solution that satisfy at least one component restoration constraint and maximize the objective function.

[0051] Among them, the target drainage plan is the pre-disaster deployment plan for the drainage team. The target maintenance plan is the pre-disaster deployment plan for the maintenance team.

[0052] Specifically, after determining the objective function and at least one component restoration constraint, the computer device can solve the objective function to obtain a maximized objective function. Based on the maximized objective function, the computer device can determine a target drainage plan and a target maintenance plan. For example, the drainage plan and the maintenance plan will affect the objective function. and Therefore, in order to maximize the objective function, it is necessary to determine the optimal drainage plan and maintenance plan, that is, to determine the target drainage plan and target maintenance plan. Therefore, the purpose of maximizing the objective function is to find the optimal drainage plan and maintenance plan.

[0053] Step 210: Obtain a distribution network restoration deployment plan based on the target drainage plan and the target maintenance plan.

[0054] The distribution network restoration deployment plan addresses the uncertainties of actual flooding disaster scenarios and pre-deploys teams based on typical flooding disaster scenarios and optimal post-disaster recovery methods. When implemented after a disaster, this plan maximizes post-disaster load recovery and minimizes the total maintenance time for the distribution network. The plan includes a targeted drainage plan and a targeted maintenance plan.

[0055] For example, if there is only one drainage team p and one maintenance team r, two deployment locations l1 and l2, a destination dp after the task is completed, and a damaged component n, and the maintenance team and drainage team move at the same speed, then the deployment plan is given: drainage team p docks at deployment location l1, and maintenance team r docks at deployment location l2. The distribution network restoration plan, for example, is as follows: immediately after the disaster, drainage team p departs from deployment location l1 at 00:00. After 10 minutes, it arrives at the damaged component n at 00:10 and begins drainage. Drainage takes 5 minutes and ends at 00:15. After drainage, drainage team p moves toward the destination dp and arrives at dp at 00:20, after 5 minutes. Maintenance team r departs from deployment location l2 at 00:00 and arrives at damaged component n at 00:18, 18 minutes later. At this point, drainage is complete, allowing maintenance team r to immediately begin repair work. The repair process lasts 12 minutes and concludes at 00:30, with component n repaired. After the repairs are complete, maintenance team r moves toward the destination dp, arriving at dp after 5 minutes at 00:35, completing the entire process. This process demonstrates that the deployment locations of the drainage and maintenance teams directly affect the time it takes them to reach the damaged component. If maintenance team r had docked at deployment location l1 before the disaster, rather than l2, and the drainage team's deployment location remained unchanged, the optimal recovery process would become: drainage team p's drainage process remains unchanged, completing drainage at 00:15 and arriving at destination dp at 00:20. Maintenance team r departs from deployment location l1 at 00:00 and arrives at damaged component n at 00:10, 10 minutes later. After waiting for drainage to complete, maintenance work begins at 00:15. The repair process lasts 12 minutes and ends at 00:27, with component n repaired. The total repair time is 27 minutes. After the repairs are complete, maintenance team r moves toward the destination dp, arriving at dp at 00:32, 5 minutes later. Therefore, under the optimal post-disaster recovery plan, the latter deployment option is superior to the former.

[0056] Specifically, each typical flooding disaster scenario can correspond to multiple sets of objective function solutions, each corresponding to a distribution network restoration deployment plan. Based on the set of objective function solutions, the computer device deploys the factors that affect the variables in the objective function, resulting in a drainage plan and a maintenance plan, and thus a corresponding distribution network restoration deployment plan. For example, if one of the variables in the objective function is recovery time, factors affecting recovery time include, but are not limited to, the time it takes the drainage team to drain the water, the time it takes the maintenance team to repair the water, and the time it takes for all teams to move on the road.

[0057] In the above-mentioned method for determining the distribution network restoration deployment plan, based on the typical flooding disaster scenario of the generated distribution network, an objective function regarding the load recovery and maintenance time of the distribution network is constructed, and multiple constraints for the objective function are determined, so that the restoration deployment method for the distribution network can be determined. Since the objective function is positively correlated with the load recovery term and negatively correlated with the maintenance time term, the purpose of the objective function is to maximize the load recovery term and minimize the maintenance time term. Therefore, the target drainage plan and target maintenance plan when the objective function is maximized can make the load recovery term as large as possible and the maintenance time term as small as possible. The distribution network restoration deployment plan obtained according to the target drainage plan and target maintenance plan when the objective function is maximized can make the distribution network recovery time as short as possible and the recovery degree as large as possible, thereby improving the rationality of the distribution network restoration deployment plan.

[0058] In an exemplary embodiment, the objective function is:

[0059] in, is the load recovery term, is the maintenance time term, s represents any typical flooding disaster scenario in S, S is a set of multiple typical flooding disaster scenarios, π s is the probability of a typical flood disaster scenario s occurring, α1 is the weight of the load recovery term, and α2 is the weight of the maintenance time term; t is the moment in the distribution network recovery process, t∈{1,2,…,T}, Δt is the time interval between two adjacent moments in {1,2,…,T}, and T represents the Tth moment in the distribution network recovery process; V represents the node set of the distribution network; j is any node in the node set of the distribution network; w j is the weight of the load carried by node j; Indicates whether the load carried by node j is restored at time t in any typical flooding disaster scenario s; represents the active power of the load carried by node j at time t in any typical flood disaster scenario s; n represents an element in the distribution network, N s is the set of damaged components of the distribution network under any typical flooding disaster scenario s; Indicates whether component n is repaired at time t in any typical flooding disaster scenario s.

[0060] The distribution network recovery process includes load recovery and maintenance. t∈{1,2,…,T} represents the time of the load recovery and maintenance process. T represents the Tth time. The time interval between two adjacent time points in {1,2,…,T} is Δt. When the value of is 1, it means that in any typical flooding disaster scenario s, the load carried by node j has been restored at time t. When the value of is 0, it means that in any typical flooding disaster scenario s, the load borne by node j has not been restored at time t.

[0061] In this embodiment, by setting the objective function of the distribution network restoration deployment plan, the maximum degree of load recovery carried by the distribution network and the shortest time used for maintenance can be obtained during the distribution network restoration process, thereby improving the restoration efficiency of the distribution network.

[0062] In an exemplary embodiment, the at least one component recovery constraint comprises:

[0063] Where i is any node in the node set of the distribution network; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; represents the power-on status of node i at time t in any typical flood disaster scenario s; represents the available state of node i at time t in any typical flood disaster scenario s; Equivalent to the objective function

[0064] Specifically, the computer device displays all damaged components in a typical flood disaster scene in the form of a set, and obtains the damaged component set N s The damaged components can be divided into damaged node components and damaged line components according to their installation locations, and are displayed in the form of sets to obtain the damaged node component set DB. s and damaged line element set DL s ,and Assume that the repair status of node i and line (i, j) are expressed as and Then we have:

[0065] in, Indicates whether the damaged component at node i is repaired at time t in any typical flood disaster scenario s. Indicates whether the damaged components on line (i, j) are repaired at time t in any typical flood disaster scenario s. or When the value of is 1, it means that the damaged element at node i or the damaged element on line (i, j) has been repaired at time t. or When the value of is 0, it may indicate that the damaged component at node i or the damaged component on line (i, j) has not been repaired at time t, or it may indicate that the component at node i or the component on line (i, j) is not damaged.

[0066] In some embodiments, the computer device represents the damage status of node i and line (i, j) of the distribution network under any typical flood disaster scenario s as and when or When the value of is 1, it means that the component at node i or the component on line (i, j) in the typical flood disaster scenario has been damaged; when or When the value of is 0, it means that the component at node i or the component on line (i, j) is not damaged. For each typical flood disaster scenario, and is a known quantity, which can be directly obtained by computer equipment from typical flood disaster scenarios. Assume that the availability status of node i and line (i, j) are expressed as and Then we have:

[0067] Where V represents the set of nodes in the distribution network, and L represents the set of lines in the distribution network. The power supply status of node i at time t in any typical flood disaster scenario s can be expressed as Indicates that the node can be powered on only when the node status is available. The value of is 1. If the node is powered on when it is unavailable, it will cause damage to the components at the node or cause safety hazards. The formula can be expressed as There are main substations, distributed power sources and loads in the distribution network. In any typical flood disaster scenario s, the recovery state of the main substation at time t can be expressed as The recovery state of the distributed generation at time t can be expressed as The load recovery state at time t can be expressed as For the main substation, distributed power source and load in the distribution network, the main substation, distributed power source and load can only be restored when the power supply status of their corresponding nodes is energized, which can be expressed as:

[0068] Computer equipment In any typical flooding disaster scenario s, the connectivity status of line (i, j) at time t. Since the two end nodes of line (i, j) are nodes i and j respectively, line (i, j) can only be connected when the line is available and the power supply status of nodes i and j are both energized. It can be expressed as:

[0069] In some embodiments, in order to ensure the recovery effect of the distribution network, the computer device sets the restored load to not be damaged again during the distribution network recovery process, which can be expressed as

[0070] In this embodiment, the restoration accuracy of the distribution network is improved by constraining the restoration status of various components.

[0071] In an exemplary embodiment, the at least one component recovery constraint further includes:

[0072] Where L is the line set of the distribution network, (j, i) is a line segment in the distribution network line set that starts at node j and ends at node i; represents the active power transmitted by line (j, i) at time t under any typical flood disaster scenario s; represents the active power injected into node i at time t under any typical flooding disaster scenario s; represents the active power of the power source at node i at time t under any typical flood disaster scenario s; the power source is a distributed power source; (i, j) is a line in the distribution network that starts at node i and ends at node j; represents the active power transmitted by line (i, j) at time t under any typical flood disaster scenario s; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; In any typical flood disaster scenario s, the active power of the load carried by node i at time t; Equivalent to the objective function

[0073] Specifically, the component recovery constraint condition also includes the operating state constraint condition. To represent the active power injected by the upper power grid to node i at time t in any typical flood disaster scenario s, use To represent the reactive power injected by the upper power grid to node i at time t in any typical flood disaster scenario s; It represents the upper limit of active power injected by the upper grid to node i, and is expressed as Represents the upper limit of reactive power injected by the upper power grid to node i; In any typical flood disaster scenario s, the active power output of the distributed generation at node i at time t is expressed as represents the reactive power output of the distributed generation at node i at time t under any typical flood disaster scenario s; It represents the upper limit of the active output of the distributed generation at node i, and is expressed as represents the upper limit of the reactive power output of the distributed generation at node i. This can be used to obtain the constraints on the capacity of the main substation in the distribution network, and also the constraints on the output of distributed energy in the distribution network, which can be expressed as follows:

[0074] Based on the above constraints, we can get the constraints on the capacity of each line in the distribution network:

[0075] in, represents the active power transmitted by line (i, j) at time t under any typical flood disaster scenario s (assuming that the power flow is positive from i to j), represents the reactive power transmitted by line (i, j) at time t under any typical flood disaster scenario s, is the active capacity of line (i, j), is the reactive capacity of line (i, j).

[0076] In some embodiments, the computer device may use a linear power flow model to constrain the power balance of each node, where the constraints are:

[0077] The above two formulas represent that the active power and reactive power flowing into node i are equal to the active power and reactive power flowing out of or consumed by node i.

[0078] In some embodiments, for line (i, j), there are also constraints on the voltages at both ends of the line, namely in is the voltage of line (i, j) at node i at time t under any typical flood disaster scenario s, is the voltage of line (i, j) at node j at time t in any typical flood disaster scenario s, V ij0 is the rated voltage of line (i, j), and M is a sufficiently large number. ij represents the resistance of line (i, j), x ijRepresents the reactance of line (i, j). When the connectivity status of line (i, j) is disconnected, this constraint is invalid.

[0079] In some embodiments, for node i, there is a constraint on the voltage at node i, which is expressed as in is the voltage upper limit of node i, is the lower limit of the voltage at node i.

[0080] In this embodiment, the restoration accuracy of the distribution network is improved by constraining the operating status of each node and line in the distribution network.

[0081] In an exemplary embodiment, the at least one component recovery constraint further includes:

[0082] in, represents the time when maintenance team r starts to repair component n in any typical flood disaster scenario s. Maintenance team r is a team that repairs component n in the distribution network; represents the time consumed by maintenance team r to repair component n in any typical flood disaster scenario s; Indicates whether the accumulated water at component n is drained at time t in any typical flood disaster scenario s; represents the moment when drainage team p starts draining water at component n in any typical flooding disaster scenario s. Drainage team p is a team that drains water at component n in the distribution network. represents the time that drainage team p consumes in draining components under any typical flood disaster scenario s; Repair is the set of repair teams that repair damaged components in the distribution network; Pump is the set of drainage teams that remove water from each node in the distribution network; With the objective function Same meaning.

[0083] Specifically, the component recovery constraints also include team dispatch constraints and recovery time constraints. Drainage personnel and maintenance personnel are based on teams. c represents a team involved in maintenance, and Crew represents the set of all teams involved in maintenance; p represents a drainage team involved in maintenance, and Pump represents the set of all drainage teams involved in maintenance; r represents a maintenance team involved in maintenance, and Repair represents the set of all maintenance teams involved in maintenance. Then c∈Crew, p∈Pump, r∈Repair, and Pump∈Crew, Repair∈Crew. l represents the deployment location of the team, CL represents the set of all deployment locations, and dp represents the final return point of the team, that is, the end point. Computer equipment is represented by Dep c,l Indicates whether the team has reached the deployment position. When the deployment position of team c is l, Dep c,l The value of is 1. Since each team can only be deployed to one location, there is a constraint ∑ l∈CL Dep c,l ≤1, Indicates whether team c moves from deployment location l to component n in any typical flood disaster scenario s. When team c moves from deployment location l to component n, The value of is 1. Indicates whether team c moves from component m to component n in any typical flood disaster scenario s. When team c moves from component m to component n, The value of is 1. Component m and component n are nodes or components in the line of the distribution network.

[0084] In some embodiments, if team c is deployed to location l, team c can depart from location l, i.e. If team c has been to component n, then team c will definitely leave from component n, that is:

[0085] The same team can only go to the same component once, that is:

[0086] After each team completes the task at the deployment location, they need to return to the destination dp. Computer equipment Indicates whether team c has been to component n in any typical flood disaster scenario s. If team c has been to component n, then The value of is 1.

[0087] In some embodiments, the computer device is used Cap represents the maximum discharge capacity of the drainage team p. n,pThe actual drainage volume of the drainage team p at element n is expressed as represents the drainage required to repair component n. Then the total drainage volume of the drainage team p at each component is not greater than its maximum drainage volume:

[0088] If drainage team p has reached component n, then the drainage volume of drainage team p at component n is no greater than the drainage volume required to repair component n: If drainage team p has not reached component n, the actual drainage volume of drainage team p at component n is 0. The drainage volume required to repair component n is the sum of the drainage volumes of each drainage team at component n:

[0089] In some embodiments, the computer device is used Res represents the maximum number of maintenance resources that maintenance team r can carry. n,r It represents the maintenance resources consumed by maintenance team r at component n, and represents the resources required to repair component n, then the maintenance team has the following constraints:

[0090] Computer equipment will Defined as the maximum number of drainage teams participating in the drainage of element n, Defined as the maximum number of maintenance teams involved in the maintenance of component n, then

[0091] In some embodiments, after the computer device completes the constraints on the team dispatch, it can further constrain the restoration time of the distribution network based on the team dispatch constraints. First, the actual time it takes for the drainage team to drain the damaged component is related to the drainage speed and the drainage volume required by the component: in Q represents the actual time consumed by the drainage team p to drain water at component n in any typical flood disaster scenario s. p is the drainage speed of the drainage team p (unit: m 3 / s, cubic meters per second). Secondly, the computer equipment defines that in any typical flood disaster scenario s, the actual time taken by the maintenance team r to repair the component n is defined as If maintenance team r alone completely repairs component n, the time required is Considering that multiple maintenance teams can collaborate on repairs, for component n, in any typical flooding disaster scenario s, the repair progress of each maintenance team r can be expressed as the actual repair time Repair alone takes time When the sum of the repair progress of each maintenance team is greater than or equal to 1, the component n is repaired, that is,

[0092] In some embodiments, the computer device records the time when each team c arrives at element n in any typical flood disaster scenario s as If element n is the first element reached by team c, then:

[0093] in, is the travel time taken by team c to travel from deployment location l to component n, and M is a sufficiently large number. If component n is not the first component reached by team c, this constraint is invalid. Computer equipment defines that in any typical flood disaster scenario s, the time when team c starts to repair component n is Obviously, the time when team c starts to repair component n is no earlier than the arrival time of team c: When team c completes the drainage or maintenance task at component n and moves to the next location,

[0094] Here, M is a sufficiently large number. When component m is not the next component of team c after repairing component n, the constraint is invalid.

[0095] Similarly, computer equipment uses Indicates whether the accumulated water at component n is drained at time t in any typical flood disaster scenario s. If the accumulated water at component n is drained at time t, then The value of is 1. The water at component n can be drained only after all drainage teams have completed their tasks: For the maintenance team r, they can only start repairing component n after the accumulated water is drained, so For component n, the repair is completed only after all maintenance teams have completed their maintenance tasks, that is:

[0096] For any damaged element, drainage and repair will only occur once, so there is:

[0097] In this embodiment, by constraining the dispatch of drainage teams and maintenance teams, and constraining the time spent by drainage teams and maintenance teams, the recovery time of the distribution network is shortened and the recovery efficiency of the distribution network is improved.

[0098] In an exemplary embodiment, multiple typical waterlogging disaster scenarios for a distribution network are generated, including: obtaining precipitation information and disaster intensity information for the distribution network within a target time period; obtaining component quality characterization values ​​of multiple components in the distribution network, and determining the damage probability of each component based on the disaster intensity information and the component quality characterization value of each component; generating multiple waterlogging disaster scenarios based on the damage probability of each component; each waterlogging disaster scenario is characterized by the damage status of multiple components, and for two different waterlogging disaster scenarios, there is at least one component with a different damage status; and determining multiple typical waterlogging disaster scenarios from the multiple waterlogging disaster scenarios.

[0099] The target time period is a period of time in the future, such as a week or month. Precipitation information refers to precipitation data for each region within the distribution network during the target time period, such as a precipitation forecast for each region within the distribution network. Disaster intensity information is data related to the severity of waterlogging disasters. For example, the intensity of waterlogging disasters can be categorized into different levels, using specific data to characterize the intensity of waterlogging disasters.

[0100] Specifically, the computer device can obtain precipitation and disaster intensity information for the distribution network during a target time period from official meteorological agencies. It can then obtain component quality indicators for each component in the distribution network from the electricity management agency, which can be a power grid company. The computer device then combines the flood disaster intensity estimate to determine the damage probability of each component in the distribution network. The computer device then compares each component's damage probability with a uniformly distributed random number in the interval (0, 1). This means that each component's damage probability can correspond to the same random number or a different random number. The computer device uses the comparison results obtained between each component's damage probability and the random number to determine the damage status of each component in the distribution network. For example, there are three components in the distribution network, denoted as component d, component e, and component f. The damage probability of component d is 0.3, the damage probability of component e is 0.4, and the damage probability of component f is 0.8. The computer compares the damage probability of component d with a uniformly distributed random number in the interval (0,1). If the random number is 0.6, and the damage probability 0.3 is less than the random number 0.6, then component d is defined as intact. Similarly, the damage status of components e and f can be determined. Once the computer has determined the damage status of each component in the distribution network, it can simulate a flooding disaster scenario. The computer can repeat this process until multiple flooding disaster scenarios are generated.

[0101] In some embodiments, the computer device can use the k-center point clustering algorithm to cluster the multiple generated urban flooding disaster scenes to obtain clustering results, namely multiple cluster centers and the clusters where the multiple cluster centers are located, thereby obtaining multiple typical urban flooding disaster scenes.

[0102] In this embodiment, by generating typical urban flooding disaster scenarios, different urban flooding disaster situations can be rehearsed, which is beneficial to improving the restoration accuracy of the distribution network.

[0103] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0104] Based on the same inventive concept, an embodiment of the present application further provides a distribution network restoration deployment plan determination device for implementing the distribution network restoration deployment plan determination method involved above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more distribution network restoration deployment plan determination device embodiments provided below can be found in the above-mentioned limitations on the distribution network restoration deployment plan determination method, and will not be repeated here.

[0105] In an exemplary embodiment, as shown in FIG4 , a device for determining a distribution network restoration deployment plan is provided, comprising: a scenario generation module 402 , a function generation module 404 , a constraint condition determination module 406 , a first plan determination module 408 , and a second plan determination module 410 , wherein:

[0106] Scenario generation module 402 is used to generate a typical flooding disaster scenario of the distribution network; the typical flooding disaster scenario is represented by the damage status of multiple components in the distribution network;

[0107] Function generation module 404 is configured to determine a load recovery term and a repair time term corresponding to a typical flood disaster scenario, and generate an objective function corresponding to the typical flood disaster scenario based on the load recovery term and the repair time term. The objective function is positively correlated with the load recovery term, and negatively correlated with the repair time term. The load recovery term represents the degree of recovery of the load carried at the node, and the repair time term represents the time required to restore damaged components in the distribution network. The node represents a structure in the distribution network used to convert voltage.

[0108] The constraint condition determination module 406 is used to determine at least one component recovery constraint condition of the objective function; the component recovery constraint condition is used to constrain the distribution network recovery process;

[0109] A first solution determination module 408 is configured to determine a target drainage solution and a target maintenance solution that satisfy at least one component restoration constraint and maximize an objective function;

[0110] The second solution determination module 410 is configured to obtain a distribution network restoration deployment solution based on the target drainage solution and the target maintenance solution.

[0111] In some embodiments, the function generation module includes an objective function, which is:

[0112] in, is the load recovery term, is the maintenance time term, s represents any typical flooding disaster scenario in S, S is a set of multiple typical flooding disaster scenarios, π s is the probability of a typical flood disaster scenario s occurring, α1 is the weight of the load recovery term, and α2 is the weight of the maintenance time term; t is the moment in the distribution network recovery process, t∈{1,2,…,T}, Δt is the time interval between two adjacent moments in {1,2,…,T}, and T represents the Tth moment in the distribution network recovery process; V represents the node set of the distribution network; j is any node in the node set of the distribution network; w j is the weight of the load carried by node j; Indicates whether the load carried by node j is restored at time t in any typical flooding disaster scenario s; represents the active power of the load carried by node j at time t in any typical flood disaster scenario s; n represents an element in the distribution network, N s is the set of damaged components of the distribution network under any typical flooding disaster scenario s; Indicates whether component n is repaired at time t in any typical flooding disaster scenario s.

[0113] In some embodiments, the constraint determination module further includes

[0114] Where i is any node in the node set of the distribution network; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; represents the power-on status of node i at time t in any typical flood disaster scenario s; represents the available state of node i at time t in any typical flood disaster scenario s; Equivalent to the objective function

[0115] In some embodiments, the constraint determination module further includes

[0116] Where L is the line set of the distribution network, (j, i) is a line segment in the distribution network line set that starts at node j and ends at node i; represents the active power transmitted by line (j, i) at time t under any typical flood disaster scenario s; represents the active power injected into node i at time t under any typical flooding disaster scenario s; represents the active power of the power source at node i at time t under any typical flood disaster scenario s; the power source is a distributed power source; (i, j) is a line in the distribution network that starts at node i and ends at node j; represents the active power transmitted by line (i, j) at time t under any typical flood disaster scenario s; Indicates whether the load carried by node i is restored at time t in any typical flooding disaster scenario s; In any typical flood disaster scenario s, the active power of the load carried by node i at time t; Equivalent to the objective function

[0117] In some embodiments, the constraint determination module further includes

[0118] in, represents the time when maintenance team r starts to repair component n in any typical flood disaster scenario s. Maintenance team r is a team that repairs component n in the distribution network; represents the time consumed by maintenance team r to repair component n in any typical flood disaster scenario s; Indicates whether the accumulated water at component n is drained at time t in any typical flood disaster scenario s; represents the moment when drainage team p starts draining water at component n in any typical flooding disaster scenario s. Drainage team p is a team that drains water at component n in the distribution network. represents the time that drainage team p consumes in draining components under any typical flood disaster scenario s; Repair is the set of repair teams that repair damaged components in the distribution network; Pump is the set of drainage teams that remove water from each node in the distribution network; With the objective function Same meaning.

[0119] In some embodiments, the scenario generation module is also used to obtain precipitation information and disaster intensity information of the distribution network within a target time period; obtain component quality characterization values ​​of multiple components in the distribution network, and determine the damage probability of each component based on the disaster intensity information and the component quality characterization value of each component; generate multiple urban flooding disaster scenarios based on the damage probability of each component; each urban flooding disaster scenario is characterized by the damage status of multiple components, and for two different urban flooding disaster scenarios, there is at least one component with a different damage status; and determine multiple typical urban flooding disaster scenarios from the multiple urban flooding disaster scenarios.

[0120] Each module in the aforementioned distribution network restoration deployment plan determination device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0121] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in Figure 5. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store session data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for determining a distribution network recovery deployment plan is implemented.

[0122] In an exemplary embodiment, a computer device is provided, which may be a terminal. Its internal structure diagram may be as shown in FIG6 . The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and an external device. The communication interface of the computer device is configured to communicate with an external terminal via wired or wireless communication, where the wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for determining a distribution network restoration deployment plan. The display unit of the computer device is configured to produce a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0123] Those skilled in the art will understand that the structures shown in Figures 5 and 6 are merely block diagrams of partial structures related to the solution of the present application, and do not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figures, or combine certain components, or have a different component arrangement.

[0124] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0125] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0126] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0127] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0128] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for determining a distribution network restoration deployment plan, characterized in that: The method comprises: Generate multiple typical waterlogging disaster scenarios of the distribution network; the typical waterlogging disaster scenarios are characterized by respective damage states of multiple components in the distribution network; Determine the load recovery item and maintenance time item corresponding to the typical waterlogging disaster scenario, and generate the objective function corresponding to the typical waterlogging disaster scenario according to the load recovery item and the maintenance time item; the objective function is positively correlated with the load recovery item, and the objective function is negatively correlated with the maintenance time item; the load recovery item represents the degree of recovery of the load carried at the node, and the maintenance time item represents the time taken to restore the damaged components in the distribution network; the node represents the structure used for converting voltage in the distribution network; Determining at least one element recovery constraint of the objective function; the element recovery constraint is used to constrain the distribution network recovery process; Determining a target drainage solution and a target maintenance solution that satisfy the at least one component restoration constraint and maximizes the objective function; A distribution network restoration deployment plan is obtained based on the target drainage plan and the target maintenance plan.

2. The method according to claim 1, characterized in that The objective function is: in, is the load recovery term, is the maintenance time term, s represents any typical flood disaster scenario in S, S is a set of multiple typical flood disaster scenarios, π s is the probability of occurrence of the typical flood disaster scenario s, α1 is the weight of the load recovery item, and α2 is the weight of the maintenance time item; t is the moment in the distribution network recovery process, t∈{1,2,…,T}, Δt is the time interval between two adjacent moments in {1,2,…,T}, and T represents the Tth moment in the distribution network recovery process; V represents the node set of the distribution network; j is any node in the node set of the distribution network; w j is the weight of the load carried by node j; Indicates whether the load carried by the node j is restored at time t in any typical flood disaster scenario s; represents the active power of the load carried by the node j at the time t in any typical flood disaster scenario s; n represents an element in the distribution network, N s is a set of damaged components of the distribution network under any typical flood disaster scenario s; It indicates whether the component n has been repaired at the time t under any of the typical flood disaster scenarios s.

3. The method according to claim 1, characterized in that At least one of the component recovery constraints comprises: Wherein, i is any node in the node set of the distribution network; Indicates whether the load carried by node i is restored at the time t in any typical flood disaster scenario s; represents the power-on state of the node i at the time t in any typical flood disaster scenario s; represents the available state of the node i at the time t under any typical flood disaster scenario s; The element recovery constraints Equivalent to the objective function 4. The method according to claim 3, characterized in that At least one of the component recovery constraints further comprises: Wherein, L is a line set of the distribution network, (j, i) is a line in the line set of the distribution network, the starting point of which is node j and the end point of which is node i; represents the active power transmitted by the line (j, i) at the time t under any typical flood disaster scenario s; represents the active power injected into the node i at the time t under any typical flood disaster scenario s; represents the active power of the power source at the node i at the time t under any typical flood disaster scenario s; the power source is a distributed power source; (i, j) is a line in the line set of the distribution network, the starting point of which is node i and the end point of which is node j; represents the active power transmitted by the line (i, j) at the time t under any typical flood disaster scenario s; Indicates whether the load carried by the node i is restored at time t in any typical flood disaster scenario s; represents the active power of the load carried by the node i at the time t under any typical flood disaster scenario s; The node power constraint condition Equivalent to the objective function 5. The method according to claim 3, characterized in that: At least one of the component recovery constraints further comprises: in, represents the time when the maintenance team r starts to repair the component n in any typical flood disaster scenario s, and the maintenance team r is a team that repairs the component n in the distribution network; represents the time consumed by the maintenance team r to repair the component n in any typical flood disaster scenario s; Indicates whether the accumulated water at the element n is drained at the time t under any typical flood disaster scenario s; represents the time when the drainage team p starts to drain water at the element n under any typical flood disaster scenario s, and the drainage team p is a team that drains water at the element n in the distribution network; represents the time consumed by the drainage team p in draining the component under any typical flood disaster scenario s; Repair is the set of maintenance teams that repair damaged components in the distribution network; Pump is the set of drainage teams that remove water from each node in the distribution network; The element recovery constraints With the objective function Same meaning.

6. The method according to claim 1, characterized in that The generation of multiple typical flood disaster scenarios of the distribution network includes: Obtaining precipitation information and disaster intensity information of the distribution network within a target time period; Obtaining component quality characterization values ​​of a plurality of components in the distribution network, and determining a damage probability of each of the components according to the disaster intensity information and the component quality characterization values ​​of each of the components; According to the damage probability of each of the components, a plurality of flood disaster scenarios are generated; each of the flood disaster scenarios is characterized by the damage state of each of the plurality of components, and for two different flood disaster scenarios, at least one component has a different damage state; A plurality of typical waterlogging disaster scenes are determined from the plurality of waterlogging disaster scenes.

7. A device for determining a distribution network restoration deployment plan, characterized in that: The device comprises: A scenario generation module, used to generate multiple typical waterlogging disaster scenarios of the distribution network; the typical waterlogging disaster scenarios are characterized by the damage states of multiple components in the distribution network; A function generation module, used to determine the load recovery item and the maintenance time item corresponding to the typical waterlogging disaster scenario, and generate an objective function corresponding to the typical waterlogging disaster scenario according to the load recovery item and the maintenance time item; the objective function is positively correlated with the load recovery item, and the objective function is negatively correlated with the maintenance time item; the load recovery item represents the degree of recovery of the load carried at the node, and the maintenance time item represents the time taken to restore the damaged components in the distribution network; the node represents the structure used for converting voltage in the distribution network; A constraint condition determination module, used to determine at least one element recovery constraint condition of the objective function; the element recovery constraint condition is used to constrain the distribution network recovery process; A first solution determination module is used to determine a target drainage solution and a target maintenance solution that satisfy the at least one component restoration constraint and maximize the objective function; The second solution determination module is used to obtain a distribution network restoration deployment solution based on the target drainage solution and the target maintenance solution.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images