Method, device, equipment and medium for post-disaster recovery of distribution networks involving electric vehicles

Abstract

The present invention discloses a method for post-disaster recovery of a distribution network in which electric vehicles participate, relates to the technical field of distribution network technology, and is used to solve the existing problem of a lack of electric vehicles participating in post-disaster recovery. The method comprises the following steps: spatially dividing the disaster-stricken area based on distribution network information and fault line information, and establishing a random spatiotemporal distribution model of electric vehicles through a generative adversarial network; constructing a power supply incentive mechanism based on the post-disaster electric vehicle position distribution output by the random spatiotemporal distribution model to encourage the participation of electric vehicles in post-disaster emergency repair and recovery; establishing a post-disaster emergency repair and recovery model for electric vehicles in order to minimize the comprehensive emergency repair and recovery cost of the distribution network after a disaster, and solving the post-disaster recovery strategy for the distribution network. The present invention also discloses a post-disaster recovery device for a distribution network in which electric vehicles participate, an electronic device, and a computer storage medium. The present invention calculates the distribution of electric vehicles and combines it with distribution network information to obtain the optimal emergency repair and recovery strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and in particular to a method, device, equipment and medium for post-disaster recovery of a distribution network involving electric vehicles. Background Art

[0002] In recent years, extreme disasters have become frequent worldwide. Typhoons and other extreme disasters have severely damaged distribution network infrastructure and triggered large-scale power outages. Traditional post-disaster emergency repair strategies rely on on-site repair personnel, distributed power generation (DG) support, and line reinforcement and intelligent switch deployment. However, these current emergency repair strategies have many limitations. For example, manual repairs are inefficient due to environmental and safety risks; DGs are limited in capacity and geographic coverage for large-scale power outage scenarios; and line reinforcement and intelligent switch deployment are costly and lack reliability in extreme disasters.

[0003] In this context, electric vehicles provide a new path for post-disaster distribution network recovery due to their high efficiency, flexibility, high penetration rate and bidirectional charging and discharging capabilities.

[0004] However, the random spatiotemporal distribution modeling of electric vehicles in distribution network emergency repair scenarios is insufficient and the response of electric vehicle owners is insufficient. Therefore, there is an urgent need for a strategy for V2G electric vehicles with random spatiotemporal distribution to actively participate in distribution network post-disaster repair and recovery, guide randomly distributed electric vehicles to actively participate in post-disaster distribution network repair and recovery, and improve the resilience of the distribution network. Summary of the Invention

[0005] In order to overcome the shortcomings of the existing technology, one of the purposes of the present invention is to provide a distribution network post-disaster recovery method involving electric vehicles, which spatially divides the disaster-stricken area and constructs a random spatiotemporal distribution model of electric vehicles to obtain a distribution network post-disaster recovery strategy.

[0006] One of the purposes of the present invention is achieved by the following technical solution:

[0007] A method for post-disaster recovery of a distribution network involving electric vehicles comprises the following steps:

[0008] Based on the distribution network information and fault line information, the affected area is spatially divided, and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks.

[0009] According to the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model, a power supply incentive mechanism is constructed to encourage electric vehicles to participate in post-disaster emergency repair and restoration;

[0010] With the goal of minimizing the comprehensive repair and restoration cost of the distribution network after a disaster, a post-disaster repair and restoration model for electric vehicles is established, and the distribution network post-disaster recovery strategy is solved.

[0011] Furthermore, the distribution network information and fault line information include: travel time of traffic lines at each node of the distribution network, electric vehicle power supply port information, repair team departure point information, distribution network grid structure, and load at each node of the distribution network.

[0012] Furthermore, the affected area is spatially divided, and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks, including:

[0013] Taking the distribution network node as the center point, the disaster-stricken area is divided into N independent areas using the Thiessen polygon rule, and the historical data is coded into regional types according to the independent areas;

[0014] According to the divided independent areas, the electric vehicle location distribution is generated through a generative adversarial network, including: receiving the area type code and the independent area through the generator of the generative adversarial network, and verifying the mapping consistency between the spatial coordinates output by the generative adversarial network and the area category through the discriminator. After adversarial training, the post-disaster electric vehicle starting position set is output.

[0015] Furthermore, based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model, a power supply incentive mechanism is constructed to encourage electric vehicles to participate in post-disaster emergency repair and restoration, including: constructing an incentive mechanism based on the charging power of the electric vehicle and the power supply power conversion income of the electric vehicle, and the calculation of the incentive mechanism satisfies:

[0016] ,in, Incentives for electric vehicle power supply, is the profit coefficient, which converts the power supplied by the electric vehicle into power supply profit. is the time that the electric vehicle stays at the power supply point, Charging power for electric vehicles.

[0017] Furthermore, with the goal of minimizing the comprehensive repair and restoration cost of the distribution network after a disaster, the objective function satisfies:

[0018] ,in, Comprehensive repair and restoration costs for distribution networks, The cost of powering electric vehicles, To dispatch the repair team, is the load loss cost; the electric vehicle power supply cost is obtained by calculating the power supply incentives of all electric vehicles, the repair team scheduling cost is calculated based on the scheduling example and the number of teams, and the load loss cost is obtained by calculating the total economic loss caused by the load loss of each node.

[0019] Furthermore, the electric vehicle constraints of the electric vehicle collaborative post-disaster emergency repair and recovery model include: when electric vehicles participate in the scheduling of distribution network power supply restoration, they must ensure that they retain enough power to meet travel needs after completing the power supply task; the output power of electric vehicles must be lower than the capacity limit of the power supply point; electric vehicles must meet time and space constraints during the emergency power supply process; and the time when electric vehicles participate in the emergency power supply must meet continuity constraints.

[0020] Constraints for the emergency repair team include: each fault point is handled by only one team; the movement path of the emergency repair team between fault points must comply with flow conservation; the time the emergency repair team participates in the emergency power supply repair must comply with continuity constraints; and the emergency repair team must complete the emergency repair scheduling of all fault points in the distribution network.

[0021] The power flow constraints include: the distribution network operation ensures the power balance of each node; the transmission line power meets the upper and lower limit constraints; the generator set output should meet the upper and lower limit constraints.

[0022] Furthermore, a distribution network post-disaster recovery strategy is obtained by solving the linearized electric vehicle collaborative post-disaster repair and recovery model using a Gurobi solver to obtain an optimal solution for distribution network post-disaster recovery.

[0023] A second object of the present invention is to provide a distribution network post-disaster recovery device involving electric vehicles.

[0024] The second object of the present invention is achieved by adopting the following technical solutions:

[0025] A distribution network post-disaster recovery device involving electric vehicles, comprising:

[0026] The modeling module is used to spatially divide the affected area based on distribution network information and fault line information, and to establish a random spatiotemporal distribution model of electric vehicles through a generative adversarial network;

[0027] An incentive module, configured to construct a power supply incentive mechanism based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model to encourage electric vehicles to participate in post-disaster emergency repair and restoration;

[0028] The strategy generation module is used to establish a post-disaster repair and recovery model for electric vehicles with the goal of minimizing the comprehensive repair and recovery cost of the distribution network after a disaster, and to solve the distribution network post-disaster recovery strategy.

[0029] The third object of the present invention is to provide an electronic device for performing one of the objects of the invention, which includes a processor, a storage medium and a computer program, wherein the computer program is stored in the storage medium, and when the computer program is executed by the processor, it implements the above-mentioned distribution network post-disaster recovery method involving electric vehicles.

[0030] A fourth object of the present invention is to provide a computer-readable storage medium for storing one of the objects of the invention, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned distribution network post-disaster recovery method involving electric vehicles is implemented.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention divides the disaster-stricken area into spatial parts and uses generative adversarial networks to calculate the starting position set of electric vehicles after the disaster, accurately depicting the random spatiotemporal distribution characteristics of electric vehicles after the disaster; the present invention improves the willingness of electric vehicle owners to actively participate in post-disaster power supply by constructing a power supply incentive mechanism in which the contribution of electric vehicle charging power is directly related to economic benefits; finally, the present invention combines electric vehicles with repair teams to establish an electric vehicle collaborative post-disaster repair and recovery model with the goal of minimizing the comprehensive repair and recovery cost of the post-disaster distribution network. This model comprehensively considers electric vehicle scheduling, repair team planning and network trends, solves the model to obtain the optimal fault recovery plan, and improves the resilience of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of the distribution network post-disaster recovery method involving electric vehicles of the present invention;

[0034] Figure 2 This is a flow chart of the distribution network post-disaster recovery method involving electric vehicles in Example 1;

[0035] Figure 3 This is a diagram of a system failure in a certain city in Example 2;

[0036] Figure 4 This is a city division map of Example 2;

[0037] Figure 5 is a graph of the starting positions of electric vehicles in Example 2;

[0038] Figure 6 This is the post-disaster repair team dispatch diagram of Example 2;

[0039] Figure 7 This is the power supply point output diagram of Example 2;

[0040] Figure 8 This is a structural block diagram of a distribution network post-disaster recovery device involving electric vehicles in Example 3;

[0041] Figure 9 It is a structural block diagram of an electronic device according to a fourth embodiment. DETAILED DESCRIPTION

[0042] The present invention will be described in more detail below with reference to the accompanying drawings. It should be noted that the following description of the present invention with reference to the accompanying drawings is merely illustrative and non-limiting. Various embodiments may be combined with each other to form other embodiments not shown in the following description.

[0043] Example 1

[0044] Example 1 provides a distribution network post-disaster recovery method involving electric vehicles, and proposes a recovery method for random temporal and spatially distributed electric vehicles V2G participating in distribution network post-disaster emergency repair. By guiding randomly distributed electric vehicles to actively participate in post-disaster distribution network emergency repair and recovery, rapid fault elimination is achieved.

[0045] Please refer to Figure 1 As shown in the overall strategy diagram, the method of this embodiment spatially partitions the disaster-stricken area using the Thiessen polygon rule and utilizes a generative adversarial network to generate a set of post-disaster electric vehicle starting positions, accurately characterizing the random spatiotemporal distribution characteristics of post-disaster electric vehicles. A power supply incentive mechanism is constructed that directly links the contribution of electric vehicle charging power to economic benefits, increasing the willingness of electric vehicle owners to actively participate in post-disaster power supply. A post-disaster repair and recovery model for electric vehicles is established by integrating electric vehicles with repair teams, aiming to minimize the comprehensive repair and recovery costs of the post-disaster distribution network. This model comprehensively considers electric vehicle scheduling, repair team planning, and network power flow constraints, and uses Gurobi to solve for the optimal fault recovery solution.

[0046] For details, please refer to Figure 2 As shown, a method for post-disaster recovery of a distribution network involving electric vehicles includes the following steps:

[0047] S1. Based on the distribution network information and fault line information, the affected area is spatially divided and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks.

[0048] The main purpose of S1 is to construct a random spatiotemporal distribution model of electric vehicles for generating post-disaster electric vehicles.

[0049] S1's distribution network and fault line information includes: travel time for each distribution network node, electric vehicle power port information, repair team departure point information, distribution network structure, and load at each distribution network node. The travel time for each distribution network node is used to calculate the travel time between electric vehicles and the repair team; the electric vehicle power port information is used to determine the electric vehicle repair destination; the repair team departure point information, including the fault line location information, is used to determine the repair team's starting point; the distribution network structure and load at each distribution network node are used in subsequent model optimization calculations.

[0050] In S1, the affected area is spatially divided and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks, including:

[0051] Taking the distribution network node as the center point, the disaster-stricken area is divided into N independent areas using the Thiessen polygon principle, and the historical data is coded according to the independent areas; that is, the disaster-stricken area containing N distribution network nodes is divided into N independent areas using the Thiessen polygon principle.

[0052] According to the divided independent areas, the electric vehicle location distribution is generated through a generative adversarial network, including: receiving the area type code and the independent area through the generator of the generative adversarial network, and verifying the mapping consistency between the spatial coordinates output by the generative adversarial network and the area category through the discriminator. After adversarial training, the post-disaster electric vehicle starting position set is output.

[0053] S2. Constructing a power supply incentive mechanism based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model to encourage electric vehicles to participate in post-disaster emergency repair and restoration;

[0054] The purpose of S2 is to build a power supply incentive mechanism to encourage electric vehicles to participate in post-disaster recovery.

[0055] S2 includes: constructing an incentive mechanism based on the conversion income of the charging power of the electric vehicle and the power supply power of the electric vehicle, wherein the calculation of the incentive mechanism satisfies:

[0056] ,in, Indicates the electric vehicle number, For electric vehicles Power supply incentive, As the profit coefficient, electric vehicles The supplied power is converted into power supply income. For electric vehicles The time spent at the power supply point, Charging power for electric vehicles.

[0057] S3. With the goal of minimizing the comprehensive repair and restoration cost of the distribution network after a disaster, a post-disaster repair and restoration model for electric vehicles is established, and the distribution network post-disaster recovery strategy is solved.

[0058] The purpose of S3 is to combine the electric vehicles stimulated by S2 with the emergency repair team to jointly carry out post-disaster repair and recovery work.

[0059] In S3, the goal is to minimize the comprehensive repair and restoration cost of the distribution network after a disaster, and the objective function satisfies:

[0060] ,in, Comprehensive repair and restoration costs for distribution networks, The cost of powering electric vehicles, To dispatch the repair team, is the load loss cost; the electric vehicle power supply cost is obtained by calculating the power supply incentives of all electric vehicles, the repair team scheduling cost is calculated based on the scheduling example and the number of teams, and the load loss cost is obtained by calculating the total economic loss caused by the load loss of each node.

[0061] The electric vehicle power supply cost is composed of all electric vehicle power supply incentives, and its calculation satisfies:

[0062] ,in, is the number of electric vehicles, Number of power supply points for electric vehicles.

[0063] The calculation of the repair team dispatch cost meets the following requirements:

[0064] ,in, For all nodes in the system, is the total number of emergency repair teams, is the distance coefficient, which converts the dispatch distance into dispatch cost; Is the decision variable, representing the repair team Whether the node Go to Node ; For nodes To Node The distance between Indicates the repair team number. It has no practical meaning and only represents the repair team.

[0065] The load loss cost is the load loss cost during the post-disaster recovery phase of the distribution network, which can be quantified as the sum of the economic losses caused by the load loss of each node, satisfying:

[0066] ,in, Restore all time periods for emergency repairs; is the electricity price coefficient, which converts the lost load power into the lost load cost; Is the node state variable, indicating the node exist The state of the moment; For nodes exist The amount of load loss at a moment.

[0067] To ensure the accuracy of the output results of the electric vehicle collaborative post-disaster emergency repair and recovery model, the constraints include: when electric vehicles participate in the scheduling of distribution network power supply restoration, they must ensure that they retain enough power to meet travel needs after completing the power supply task; the output power of electric vehicles must be lower than the capacity limit of the power supply point; electric vehicles must meet time and space constraints during the emergency power supply process; and the time when electric vehicles participate in the emergency power supply must meet continuity constraints.

[0068] Specifically, when electric vehicles participate in the scheduling of distribution network power restoration, it is necessary to ensure that electric vehicle owners can still retain sufficient power to meet travel needs after completing the power supply task:

[0069] ,

[0070] in, For electric vehicles Arrival at the power supply point When its own capacity; For electric vehicles Leave the power supply point When its own capacity.

[0071] The output power of electric vehicles should not exceed the capacity limit of the power supply point:

[0072] ,

[0073] in, For electric vehicles Time access point The maximum output active power; For electric vehicles Time access point The power coefficient.

[0074] During the emergency power supply repair process, electric vehicles should meet the time and space constraints:

[0075] ,

[0076] in, Indicates electric vehicles exist Whether the power supply point is reached at the moment ; Indicates electric vehicles exist Whether to leave the power supply point at all times .

[0077] The time when electric vehicles participate in emergency power supply should meet the continuity constraint:

[0078] ,

[0079] in, is the decision variable, representing electric vehicles Whether the node Go to Node ; Extreme repair time for electric vehicles; Arrival node for electric vehicles time; For electric vehicles at the node Time spent on emergency repairs; For electric vehicles By node Go to Node Time spent.

[0080] Constraints on the emergency repair team include: each fault point is handled by only one team; the movement path of the repair team between fault points must comply with flow conservation; the time the emergency repair team participates in the emergency power supply repair must comply with continuity constraints; and the emergency repair team must complete the emergency repair scheduling of all fault points in the distribution network.

[0081] Specifically, in the allocation of emergency repair tasks, to ensure the independence of the emergency repair teams, it is necessary to ensure that each fault point is handled by only one team:

[0082] ,in, Indicates whether the node is selected by the emergency repair team.

[0083] The movement path of the repair team between fault points must satisfy the flow conservation principle:

[0084] ,

[0085] .

[0086] The time that the emergency repair team participates in the emergency power supply repair should meet the continuity constraint:

[0087] ,

[0088] in, The maximum repair time for the repair team; For the repair team Arrival Node time; For the repair team At the node Time spent on emergency repairs; For the repair team For the node To Node Time spent.

[0089] The emergency repair team needs to complete the emergency repair dispatch of all fault points in the distribution network:

[0090] ,

[0091] in, is the total number of distribution network fault points after the typhoon disaster.

[0092] The power flow constraints include: the distribution network operation ensures the power balance of each node; the transmission line power meets the upper and lower limit constraints; the generator set output should meet the upper and lower limit constraints.

[0093] Specifically, the distribution network operation needs to consider the power balance of each node:

[0094] ,

[0095] ,

[0096] in, and For nodes exist Active power and reactive power input at all times; and For nodes exist Active power and reactive power of the power supply at all times; and For nodes exist Active load loss power and reactive load loss power at the moment; and node exist Active load and reactive load at the moment.

[0097] The transmission line power should meet the upper and lower limit constraints:

[0098] ,

[0099] ,

[0100] in, and are the upper limit of active power and reactive power of the transmission line.

[0101] The output of each generator set should meet the upper and lower limit constraints:

[0102] ,

[0103] ,

[0104] in, and For nodes The upper limit of active power output and reactive power output of all units.

[0105] In this embodiment, the linearized post-disaster emergency repair and recovery model of the electric vehicles is solved by a Gurobi solver to obtain the optimal solution for the post-disaster recovery of the distribution network.

[0106] The Gurobi solver was chosen because it is a high-performance mathematical optimization solver with the advantages of fast speed, strong solving ability, and support for a wide range of problem types. It also has interfaces in multiple programming languages ​​and can accurately adapt to the method described in this embodiment.

[0107] Example 2

[0108] Example 2 is a specific experimental description of the method described in Example 1.

[0109] This embodiment reads the distribution network grid structure of the test distribution network, the load of each node of the distribution network, the location information of the fault line, the travel time of the traffic line at each node of the distribution network, the electric vehicle power supply port, and the starting point of the emergency repair team. In the IEEE 33-node distribution system, there are 13 fault nodes, 3 electric vehicle power supply ports and 1 emergency repair team starting point. Among them, the 13 distribution network fault points are shown in Table 1.1. The electric vehicle power supply ports are located at nodes 14, 20 and 31 respectively, and the emergency repair team starting point is located at node 32. The fault situation of a certain city system is shown in the figure below. Figure 3 The travel time of traffic lines at each node of the distribution network is shown in Table 1.2.

[0110] Table 1.1 13 distribution network fault points

[0111]

[0112] Table 1.2 Traffic route travel time for each node in the distribution network

[0113]

[0114] The disaster-stricken area is divided with the distribution network node as the center point. The disaster-stricken area containing 33 distribution network nodes is divided into 33 independent areas using the Thiessen polygon rule. The division diagram of a city is as follows: Figure 4 shown.

[0115] The starting position of the electric vehicle is calculated according to the method described in Example 1. Please refer to the calculation results. Figure 5 shown.

[0116] Finally, the Gurobi solver is used to solve the linearized model and output the optimal solution for emergency restoration of the distribution network fault. Figure 6As shown, among the five repair teams, repair team 4 went to fault points 3, 28, and 26 in turn to complete the repair, which took the longest time, a total of 10.25 hours. Figure 7 As shown in the figure, during the initial operation period (0:00-4:00 hours), the power output of the electric vehicle power supply point continued to increase. This is primarily due to two factors: First, the distribution network system had not yet completed most of the emergency repair work at the time the dispatch order was issued, resulting in limited power resources in the initial stage. Second, as time passed, electric vehicle owners responded to the dispatch and arrived at the designated power supply node from various starting points, gradually increasing the number of vehicles participating in the power supply. By the 4:00 hour, the combined power of each power supply node reached its peak, and the power output of the power supply point entered a stable maintenance phase. From the 7:00 hour onwards, the emergency repair team completed most of the emergency repair work, the distribution network system reduced the power demand of the electric vehicles, and the power output of the power supply point began to decline.

[0117] Example 3

[0118] Example 3 discloses a device corresponding to the distribution network post-disaster recovery method for electric vehicles participating in the above embodiment, which is a virtual device structure of the above embodiment. Please refer to Figure 8 Shown, including:

[0119] Modeling module 310, for performing spatial division of the affected area based on the distribution network information and fault line information, and establishing a random spatiotemporal distribution model of electric vehicles through a generative adversarial network;

[0120] An incentive module 320 is configured to construct a power supply incentive mechanism based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model to encourage electric vehicles to participate in post-disaster emergency repair and restoration;

[0121] The strategy generation module 330 is used to establish a post-disaster emergency repair and restoration model for electric vehicles with the goal of minimizing the comprehensive emergency repair and restoration cost of the distribution network after a disaster, and to solve and obtain a post-disaster restoration strategy for the distribution network.

[0122] Preferably, the distribution network information and fault line information include: travel time of traffic lines at each node of the distribution network, electric vehicle power supply port information, repair team departure point information, distribution network grid structure, and load at each node of the distribution network.

[0123] Preferably, the affected area is spatially divided, and a random spatiotemporal distribution model of electric vehicles is established through a generative adversarial network, including:

[0124] Taking the distribution network node as the center point, the disaster-stricken area is divided into N independent areas using the Thiessen polygon rule, and the historical data is coded into regional types according to the independent areas;

[0125] According to the divided independent areas, the electric vehicle location distribution is generated through a generative adversarial network, including: receiving the area type code and the independent area through the generator of the generative adversarial network, and verifying the mapping consistency between the spatial coordinates output by the generative adversarial network and the area category through the discriminator. After adversarial training, the post-disaster electric vehicle starting position set is output.

[0126] Preferably, a power supply incentive mechanism is constructed based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model to encourage electric vehicles to participate in post-disaster repair and restoration, including: constructing an incentive mechanism based on the charging power of the electric vehicle and the power supply power conversion income of the electric vehicle, and the calculation of the incentive mechanism satisfies:

[0127] ,in, Incentives for electric vehicle power supply, is the profit coefficient, which converts the power supplied by the electric vehicle into power supply profit. is the time that the electric vehicle stays at the power supply point, Charging power for electric vehicles.

[0128] Optimally, the goal is to minimize the comprehensive repair and restoration cost of the distribution network after a disaster, and the objective function satisfies:

[0129] ,in, Comprehensive repair and restoration costs for distribution networks, The cost of powering electric vehicles, To dispatch the repair team, is the load loss cost; the electric vehicle power supply cost is obtained by calculating the power supply incentives of all electric vehicles, the repair team scheduling cost is calculated based on the scheduling example and the number of teams, and the load loss cost is obtained by calculating the total economic loss caused by the load loss of each node.

[0130] Preferably, the electric vehicle constraints of the electric vehicle collaborative post-disaster emergency repair and recovery model include: when electric vehicles participate in the scheduling of distribution network power supply restoration, they must ensure that they retain sufficient power to meet travel needs after completing the power supply task; the output power of electric vehicles must be lower than the capacity limit of the power supply point; electric vehicles must meet time and space constraints during the emergency power supply process; the time when electric vehicles participate in the emergency power supply must meet continuity constraints;

[0131] Constraints for the emergency repair team include: each fault point is handled by only one team; the movement path of the emergency repair team between fault points must comply with flow conservation; the time the emergency repair team participates in the emergency power supply repair must comply with continuity constraints; and the emergency repair team must complete the emergency repair scheduling of all fault points in the distribution network.

[0132] The power flow constraints include: the distribution network operation ensures the power balance of each node; the transmission line power meets the upper and lower limit constraints; the generator set output should meet the upper and lower limit constraints.

[0133] Preferably, solving the distribution network post-disaster recovery strategy includes: solving the linearized electric vehicle collaborative post-disaster repair and recovery model through a Gurobi solver to obtain the optimal solution for the distribution network post-disaster recovery.

[0134] Example 4

[0135] Figure 9 This is a structural diagram of an electronic device provided in the fourth embodiment of the present invention, such as Figure 9 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the computer device can be one or more. Figure 9 In the figure, a processor 410 is used as an example; the processor 410, memory 420, input device 430 and output device 440 in the electronic device can be connected via a bus or other means. Figure 9 The bus connection is taken as an example.

[0136] Memory 420, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the distribution network post-disaster recovery method for electric vehicles in the embodiments of the present invention. Processor 410 executes the software programs, instructions, and modules stored in memory 420 to execute various functional applications and data processing of the electronic device, thereby implementing the distribution network post-disaster recovery method for electric vehicles in the first and second embodiments described above.

[0137] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal, etc. In addition, the memory 420 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely located relative to the processor 410, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0138] The input device 430 may be used to receive input user identity information, power distribution network data, fault data, etc. The output device 440 may include a display device such as a display screen.

[0139] Example 5

[0140] The fifth embodiment of the present invention further provides a storage medium containing computer-executable instructions, which can be used by a computer to execute a method for post-disaster recovery of a distribution network involving electric vehicles, the method comprising:

[0141] Based on the distribution network information and fault line information, the affected area is spatially divided, and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks.

[0142] According to the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model, a power supply incentive mechanism is constructed to encourage electric vehicles to participate in post-disaster emergency repair and restoration;

[0143] With the goal of minimizing the comprehensive repair and restoration cost of the distribution network after a disaster, a post-disaster repair and restoration model for electric vehicles is established, and the distribution network post-disaster recovery strategy is solved.

[0144] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present invention is not limited to the method operations described above, and can also execute relevant operations in the distribution network post-disaster recovery method based on electric vehicle participation provided in any embodiment of the present invention.

[0145] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware. Of course, it can also be implemented with hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling an electronic device (such as a mobile phone, personal computer, server, or network device) to execute the methods described in various embodiments of the present invention.

[0146] It is worth noting that in the embodiment of the distribution network post-disaster recovery method device based on the participation of electric vehicles, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0147] Those skilled in the art can make various other corresponding changes and deformations based on the technical solutions and concepts described above, and all of these changes and deformations should fall within the scope of protection of the claims of the present invention.

Claims

1. A method for post-disaster recovery of a distribution network involving electric vehicles, characterized in that: The following steps are involved: Based on the distribution network information and fault line information, the affected area is spatially divided, and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks. Among them, the spatial division of the disaster-stricken area is carried out, and a random spatiotemporal distribution model of electric vehicles is established through generative adversarial networks, including: Taking the distribution network node as the center point, the disaster-stricken area is divided into N independent areas using the Thiessen polygon rule, and the historical data is coded into regional types according to the independent areas; Generate an electric vehicle location distribution based on the divided independent areas through a generative adversarial network, including: receiving the area type code and the independent area through a generator of the generative adversarial network, and verifying the mapping consistency between the spatial coordinates output by the generative adversarial network and the area category through a discriminator, and outputting a post-disaster electric vehicle starting location set after adversarial training; According to the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model, a power supply incentive mechanism is constructed to encourage electric vehicles to participate in post-disaster emergency repair and restoration; With the goal of minimizing the comprehensive repair and restoration cost of the distribution network after a disaster, a post-disaster repair and restoration model for electric vehicles is established, and the distribution network post-disaster recovery strategy is solved.

2. The method for post-disaster recovery of a distribution network involving electric vehicles according to claim 1, characterized in that: The distribution network information and fault line information include: the travel time of traffic lines at each node of the distribution network, electric vehicle power supply port information, repair team departure point information, distribution network grid structure, and load at each node of the distribution network.

3. The method for post-disaster recovery of a distribution network involving electric vehicles according to claim 1, characterized in that: Based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model, a power supply incentive mechanism is constructed to encourage electric vehicles to participate in post-disaster emergency repair and restoration, including: constructing an incentive mechanism based on the charging power of the electric vehicle and the power supply power conversion income of the electric vehicle, and the calculation of the incentive mechanism satisfies: ,in, Incentives for electric vehicle power supply, is the profit coefficient, which converts the power supplied by the electric vehicle into power supply profit. is the time that the electric vehicle stays at the power supply point, Charging power for electric vehicles.

4. The method for post-disaster recovery of a distribution network involving electric vehicles according to claim 1, wherein: The goal is to minimize the comprehensive repair and restoration cost of the distribution network after a disaster, and the objective function satisfies: ,in, Comprehensive repair and restoration costs for distribution networks, The cost of powering electric vehicles, To reduce the cost of dispatching the repair team, is the load loss cost; the electric vehicle power supply cost is obtained by calculating the power supply incentives of all electric vehicles, the repair team scheduling cost is calculated based on the scheduling example and the number of teams, and the load loss cost is obtained by calculating the total economic loss caused by the load loss of each node.

5. The method for post-disaster recovery of a distribution network involving electric vehicles according to claim 4, characterized in that: The electric vehicle constraints of the electric vehicle collaborative post-disaster emergency repair and recovery model include: when electric vehicles participate in the scheduling of distribution network power supply restoration, they must ensure that they retain enough power to meet travel needs after completing the power supply task; the output power of electric vehicles must be lower than the capacity limit of the power supply point; electric vehicles must meet time and space constraints during the emergency power supply process; and the time when electric vehicles participate in the emergency power supply must meet continuity constraints. Constraints for the emergency repair team include: each fault point is handled by only one team; the movement path of the emergency repair team between fault points must comply with flow conservation; the time the emergency repair team participates in the emergency power supply repair must comply with continuity constraints; and the emergency repair team must complete the emergency repair scheduling of all fault points in the distribution network. The power flow constraints include: the distribution network operation ensures the power balance of each node; the transmission line power meets the upper and lower limit constraints; the generator set output should meet the upper and lower limit constraints.

6. The method for post-disaster recovery of a distribution network involving electric vehicles according to claim 1, characterized in that: Solving and obtaining a distribution network post-disaster recovery strategy includes: solving the linearized electric vehicle collaborative post-disaster repair and recovery model through a Gurobi solver to obtain an optimal solution for distribution network post-disaster recovery.

7. A distribution network post-disaster recovery device involving electric vehicles, characterized in that: It includes: The modeling module is used to spatially divide the affected area based on the distribution network information and the fault line information, and to establish a random spatiotemporal distribution model of electric vehicles through a generative adversarial network. The spatial division of the affected area and the establishment of a random spatiotemporal distribution model of electric vehicles through a generative adversarial network include: Taking the distribution network node as the center point, the disaster-stricken area is divided into N independent areas using the Thiessen polygon rule, and the historical data is coded into regional types according to the independent areas; Generate an electric vehicle location distribution based on the divided independent areas through a generative adversarial network, including: receiving the area type code and the independent area through a generator of the generative adversarial network, and verifying the mapping consistency between the spatial coordinates output by the generative adversarial network and the area category through a discriminator, and outputting a post-disaster electric vehicle starting location set after adversarial training; An incentive module, configured to construct a power supply incentive mechanism based on the post-disaster electric vehicle location distribution output by the random spatiotemporal distribution model to encourage electric vehicles to participate in post-disaster emergency repair and restoration; The strategy generation module is used to establish a post-disaster repair and recovery model for electric vehicles with the goal of minimizing the comprehensive repair and recovery cost of the distribution network after a disaster, and to solve the distribution network post-disaster recovery strategy.

8. An electronic device comprising a processor, a storage medium, and a computer program, wherein the computer program is stored in the storage medium, When the computer program is executed by a processor, the method for post-disaster recovery of a distribution network involving electric vehicles as described in any one of claims 1 to 6 is 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 method for post-disaster recovery of a distribution network involving electric vehicles as described in any one of claims 1 to 6 is implemented.

Images