Mobile energy storage resource dynamic scheduling method and device for power recovery after disaster and medium

Abstract

The invention discloses a mobile energy storage resource dynamic scheduling method and device for power recovery after a disaster and a medium. The method comprises the following steps: acquiring power equipment information and traffic network information in a city, and establishing a power-traffic coupling digital twinborn body; determining the comprehensive hazard risk level of each region in the city, and solving the optimal power flow of the city according to the comprehensive hazard risk level of each region in the city; and generating an intelligent agent scheduling strategy according to the optimal power flow, and scheduling the intelligent agent through the intelligent agent scheduling strategy. According to the method, a coupling model of a traffic network and a power grid is constructed, and it is ensured that the mobile energy storage system can efficiently transmit and allocate electric power resources among areas affected by storm surge disasters. By constructing a storm surge risk evaluation framework, a real-time scheduling strategy of mobile energy storage resources is effectively optimized, the power recovery efficiency is maximized, and the recovery time is minimized; and the recovery speed and the power utilization safety of the urban power system after the storm surge disaster are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power systems, and in particular to a method, device and medium for dynamically scheduling mobile energy storage resources for post-disaster power recovery. Background Art

[0002] In recent years, extreme weather has occurred frequently in coastal areas, seriously threatening the safe and reliable operation of the power system. Due to severe atmospheric disturbances, the sea water fluctuates abnormally, causing the tide level in the affected sea area to far exceed the average tide level, that is, the storm surge.

[0003] The backflow of water caused by storm surges will cause the inland water level of coastal cities to rise, exceeding the limited drainage capacity of urban construction projects, and the flood height may exceed the flood depth allowed by power equipment, causing a large number of power and communication equipment in coastal cities to be flooded. This flooding may subsequently lead to the failure of these systems, resulting in a large-scale collapse of power and communication supply.

[0004] However, the power system lacks knowledge about storm surge disasters. In the field of power system research, only a few inventions have used digital twin technology to predict power outages in power plants before storm surge disasters occur. There is no other research on improving the ability of power grids to resist storm surges. Therefore, in order to ensure the power supply of coastal cities under storm surge disasters and improve the resilience of distribution networks, it is urgent to make comprehensive use of energy storage resources to reduce power outage losses. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method, device and medium for dynamically scheduling mobile energy storage resources for post-disaster power recovery.

[0006] A first aspect of the present invention provides a method for dynamically scheduling mobile energy storage resources for post-disaster power recovery, comprising the following steps:

[0007] Obtaining information on power equipment and traffic network in the city, and establishing a power-traffic coupling digital twin; the power-traffic coupling digital twin includes a plurality of mobile energy storage units as intelligent entities;

[0008] Determine the comprehensive hazard risk level of each area in the city, and solve the optimal power flow of the city based on the comprehensive hazard risk level of each area in the city;

[0009] An intelligent agent scheduling strategy is generated according to the optimal power flow, and the intelligent agent is scheduled according to the intelligent agent scheduling strategy.

[0010] Furthermore, the power-transportation coupled digital twin is presented as a coupled network of the urban power grid and the transportation network; the optimal power flow is represented by the power grid; and the intelligent agent scheduling strategy is represented by the transportation network.

[0011] Furthermore, the comprehensive hazard risk level of each area in the city is obtained by solving the following steps:

[0012] Determine the danger level of each area in the city based on the risk level of each danger indicator in the area and the corresponding combined weight;

[0013] Determine the exposure level of each area in the city based on the exposure level of each exposure indicator in the area combined with the corresponding combined weight;

[0014] The vulnerability level of each area in the city is determined based on the vulnerability level of each vulnerability indicator in the area and the corresponding combined weight;

[0015] Determine the social vulnerability level of each area within the city based on the exposure and vulnerability levels of the area;

[0016] The comprehensive hazard risk level of each area in the city is determined based on the area's hazard level and social vulnerability level.

[0017] Furthermore, the danger indicators include the maximum flood depth, average flood depth, maximum flood velocity, flood area ratio and flood duration of the region;

[0018] The exposure indicators include population density, population dependency ratio, population education level, number of old residential areas, number of water supply facilities, number of electricity facilities, number of markets, number of historical buildings and number of public parking lots in the area;

[0019] The vulnerability indicators include the distance to rescue departments, the distance to security departments, the distance to emergency shelters, and the distance to medical institutions in the area.

[0020] Furthermore, solving the optimal power flow of the city according to the comprehensive hazard risk level of each area in the city specifically includes the following steps:

[0021] Represent the post-disaster recovery time in the form of multiple time steps;

[0022] Determine the power load demand of each node in the urban power grid at each time step according to the comprehensive hazard risk level of each area in the city; the power load demand includes necessary power load and non-essential power load;

[0023] Calculating the optimal charge and discharge amount of each node in each time step, wherein the optimal charge and discharge amount is determined according to the necessary power load of each node;

[0024] The optimal charge and discharge amount of each node is calculated by multiple time steps as the optimal power flow.

[0025] Furthermore, generating an agent scheduling strategy according to the optimal power flow specifically includes the following steps:

[0026] Set the reinforcement learning algorithm parameters and the agent observation space;

[0027] The reinforcement learning algorithm parameters include a reward function and a Q function; the reward function is determined according to the necessary power load of each node in the environmental state space in each time step; the Q function includes the expected node state of each node in the power grid formed by comparing the intelligent agent with the reward function after moving in various directions to perform charging and discharging operations based on the optimal power flow;

[0028] The agent observation space includes an environment state space and an agent action space; wherein the environment state space is used to simulate the power load demand of each node in the power grid in each time step; the agent action space is used to simulate the moving path of the agent in each time step; wherein the position of the agent in the first time step is the initial position of the mobile energy storage unit in the city;

[0029] In each time step, the path selection action of the agent is merged into the agent action space; the expected node state after receiving the charging and discharging operation is merged into the environment state space; after all time steps are completed, the environment state space and agent action space data are retrieved to obtain multiple sets of expected movement strategies of the agent;

[0030] Select the optimal expected movement strategy as the agent scheduling strategy.

[0031] Furthermore, the method also includes the step of setting a central aggregator; the central aggregator is used to share the agent observation space of multiple agents; and the coordinated scheduling between multiple agents is achieved through the central aggregator.

[0032] Furthermore, an unexpected coefficient is also provided in the Q function, and the unexpected coefficient is used to indicate the probability that the agent stops moving when encountering an unexpected situation.

[0033] A second aspect of the present invention discloses an electronic device, comprising a processor and a memory;

[0034] The memory is used to store programs;

[0035] The processor executes the program to implement the method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery.

[0036] A third aspect of the present invention discloses a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method for dynamically scheduling mobile energy storage resources for post-disaster power recovery.

[0037] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0038] The embodiments of the present invention have the following beneficial effects: The present invention provides a method, device and medium for dynamic scheduling of mobile energy storage resources for post-disaster power recovery, which constructs a coupling model of the transportation network and the power grid, ensuring that the mobile energy storage system can efficiently transmit and distribute power resources between areas affected by storm surge disasters. The present invention constructs a storm surge hazard assessment framework to effectively optimize the real-time scheduling strategy of mobile energy storage resources, maximize power recovery efficiency and minimize recovery time. The present invention effectively improves the recovery speed and power safety of urban power systems after storm surge disasters.

[0039] Additional aspects and advantages of the present invention will be given in part in the following description, and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. 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 creative work.

[0041] Figure 1 It is a basic flow chart of a method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to the present invention.

[0042] Figure 2 It is a schematic diagram of a framework for solving the comprehensive hazard risk level of each area in a city according to the present invention.

[0043] Figure 3 It is a schematic diagram of the dynamic scheduling effect of mobile energy storage resources based on multi-agent reinforcement learning of the present invention.

[0044] Figure 4 This is an example diagram of the dynamic scheduling of mobile energy storage in the present invention.

[0045] Figure 5 It is a structural schematic diagram of an electronic device of the present invention.

[0046] Figure 6 It is a schematic diagram of the structure of a computer-readable storage medium of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] In the field of disaster science, several studies have focused on simulating hydrological processes in urban areas. One invention uses differential methods to solve urban non-steady-state surface flow problems under extreme weather conditions based on classical theorems such as the shallow water equation. One invention further simulates the storm surge in Hong Kong, China during typhoon disasters based on previous inventions. Storm surge has become one of the major disasters affecting the power industry, but the power system lacks awareness of storm surge disasters. In the field of power system research, only a few inventions have used digital twin technology to predict power outages in power stations before storm surge disasters occur. There is currently no other research on improving the power grid's ability to resist storm surges.

[0049] As the coupling relationship between power and transportation systems becomes increasingly close, information interconnection can be achieved between the power grid system and the transportation network system. When an extreme event occurs, the line breakage will decompose the distribution network into multiple areas. At the same time, due to the impact of extreme events, some sections of the transportation network will also be damaged, thus affecting the distribution of traffic flow. In order to improve the resilience of the distribution network, in addition to using local distributed generation (DG) for island operation, for power outages in island areas without local DG power consumption paths, mobile power resources such as mobile energy storage systems (MESS) can be selected as auxiliary power sources. Some such applications have been explored, such as releasing power stored in electric vehicles (vehicle to grid) or using road networks to consume electricity through large batteries. An invention has proposed the concept of detachable mobile energy storage, which expands the traditional dispatching mode and enables MESS to provide more flexible multi-period active power supplementation for post-disaster power grids. However, the actual transportation network is the driving carrier of MESS; the above research has not yet conducted an in-depth study of the road network-grid coupling, and only simply processed the driving process. Traffic flow is a measure of the traffic conditions of the road network, and the path planning of mobile resources needs to fully consider the impact of traffic flow. Another invention directly quantifies the impact of traffic flow into known traffic time and proposes a power grid repair strategy that considers the alternation of emergency repair teams and emergency repair teams. The above studies consider the impact of real-time traffic conditions on the path planning of mobile resources.

[0050] However, based on the preset full-time traffic flow information, most of the time, detailed models are needed to describe the dynamic changes of traffic flow. Therefore, the impact of actual road conditions on the actual scheduling of MESS can only be partially considered, and the scheduling strategy is divorced from the actual situation of the traffic layer. Therefore, the scheduling results can be better. MESS is a coupling device connecting the traffic network and the distribution network, so it is impossible to independently formulate a scheduling strategy without considering the actual traffic background. Research on the disaster scheduling of distributed power grids under the dual network of road and power can improve the load recovery effect and the coordination ability with the distributed power grid during storm surge disasters, which is of great significance.

[0051] To this end, the first embodiment of the present invention provides a method for dynamically scheduling mobile energy storage resources for post-disaster power recovery, such as Figure 1 As shown, the following steps are included:

[0052] S1. Obtain information on power equipment and transportation networks in the city and establish a power-transportation coupled digital twin;

[0053] S2. Determine the comprehensive hazard risk level of each area in the city, and solve the optimal power flow of the city based on the comprehensive hazard risk level of each area in the city;

[0054] S3. Generate an agent scheduling strategy according to the optimal power flow, and schedule the agent through the agent scheduling strategy.

[0055] The embodiment of the present invention constructs a coupling model of the transportation network and the power grid to ensure that the mobile energy storage system can efficiently transmit and distribute power resources between areas affected by storm surge disasters. By constructing a storm surge hazard assessment framework, the real-time scheduling strategy of mobile energy storage resources is effectively optimized, and the efficiency of power recovery is maximized and the recovery time is minimized.

[0056] The following is a detailed description of the implementation process of each step of the present invention:

[0057] S1. Obtain information on power equipment and transportation networks in the city and establish a power-transportation coupled digital twin.

[0058] In the embodiment of the present invention, the actual electrical component configuration, city map, load distribution, distribution network topology and other power equipment information and traffic network information in the coastal area are obtained to construct a power-transportation coupling digital twin. The constructed power-transportation coupling digital twin includes multiple mobile energy storage units (MESS) as intelligent entities; the mobile energy storage units are used to coordinate with local distributed power generation units such as photovoltaic generators (PV), diesel generators (DEG), and electric vehicle charging piles (EV) to promote post-disaster power restoration.

[0059] The constructed power-transportation coupling digital twin is presented as a coupling network of the power grid and the transportation network in the city. There are multiple power consumption nodes in the power grid, which are distributed in various locations of the transportation network. At the same time, there are also multiple mobile energy storage units in the transportation network. The mobile energy storage units can charge and discharge certain nodes of the power grid by moving in the transportation network and charging and discharging the nodes.

[0060] When a disaster strikes, short circuit faults may occur in the distribution lines between the power nodes of the power grid, causing some nodes to fail to work normally or have insufficient working power, thereby generating power load demand. Specifically, the power load demand includes necessary power load and non-essential power load. In the embodiment of the present invention, the power nodes are divided into important nodes and non-important nodes. The power load demand of important nodes is regarded as necessary power load, and the power load demand of non-important nodes is regarded as non-essential power load.

[0061] In other embodiments, the type of power load can also be determined based on the specific power demand of the node. For example, the power demand when the power node recovers from a state of being unable to work normally to a state of insufficient working power can be regarded as a necessary power load, and the power demand when the power node recovers from a state of insufficient working power to a normal working state can be regarded as a non-essential power load, etc.

[0062] Meeting the power load demand of power-consuming nodes requires that the mobile energy storage unit discharges the nodes to provide power supply for the nodes; and the mobile energy storage unit itself also has capacity limitations, so after the stored power is consumed, it also needs to be charged at the normally operating local power generation unit. Since the urban area environment where the power-consuming nodes are located is different, the embodiment of the present invention combines the comprehensive hazard risk level of each area in the city to solve the optimal power flow of the city, and uses the optimal power flow as the data basis for intelligent body scheduling.

[0063] S2. Determine the comprehensive hazard risk level of each area in the city, and solve the optimal power flow of the city based on the comprehensive hazard risk level of each area in the city.

[0064] The comprehensive hazard risk level of each area in the city in the embodiment of the present invention is obtained by the following steps:

[0065] S2-1. Determine the hazard level of each area in the city based on the risk level of each hazard indicator in the area and the corresponding combined weight;

[0066] S2-2. Determine the exposure level of each area in the city based on the exposure level of each exposure indicator in the area and the corresponding combined weight;

[0067] S2-3. Determine the vulnerability level of each area in the city based on the vulnerability level of each vulnerability indicator in the area and the corresponding combined weight;

[0068] S2-4. Determine the social vulnerability level of each area in the city based on the exposure level and vulnerability level of the area;

[0069] S2-5. Determine the comprehensive hazard risk level of each area in the city based on the area's hazard level and social vulnerability level.

[0070] like Figure 2 As shown, the embodiment of the present invention uses the danger index, exposure index and vulnerability index as the evaluation index of the city's disaster. The weight of each index includes the sovereign weight and the objective weight. The specific weight value is determined by expert experience, game theory and entropy weight method, as shown in Table 1:

[0071] Table 1 Index and weight of each indicator

[0072]

[0073] In the embodiment of the present invention, the risk index uses fuzzy analysis to determine a specific risk level, as shown in Table 2:

[0074] Table 2 Risk levels and thresholds of various risk indicators

[0075]

[0076]

[0077] After coupling the weights corresponding to each indicator, the danger level of the area is defined by the following formula:

[0078]

[0079] Where j is the risk index, A j is the danger level of the danger indicator, W j is the combined weight of the risk index.

[0080] The corresponding characteristics of the hazard levels are shown in Table 3:

[0081] Table 3 Hazard levels and characteristics

[0082]

[0083] In terms of social vulnerability level, the embodiment of the present invention adopts a fuzzy comprehensive evaluation method to determine the exposure level and vulnerability level, namely E and V:

[0084] S = E / V;

[0085] Among them, S is the social vulnerability level, E is the exposure level, and V is the vulnerability level. The division symbol indicates that the variables are negatively correlated, as shown in Table 4:

[0086] Table 4 Social vulnerability levels

[0087]

[0088]

[0089] The characteristics corresponding to each level are shown in Table 5:

[0090] Table 5 Characteristics of social vulnerability

[0091]

[0092] After obtaining the hazard level and social vulnerability level, the comprehensive hazard risk level of the region is determined by the following formula:

[0093] R=H×S

[0094] Where R is the flood risk level, H is the flood risk level, and S is the social vulnerability level. The multiplication sign indicates that these variables are positively correlated, as shown in Table 6.

[0095] Table 6 Comprehensive risk level of urban flooding

[0096]

[0097] In step S2, the optimal power flow of the city is solved according to the comprehensive hazard risk level of each area in the city, which specifically includes the following steps:

[0098] S2-1. Represent the post-disaster recovery time in the form of multiple time steps.

[0099] Since the power load demand of each power consumption node will change over time, the embodiment of the present invention characterizes the post-disaster recovery time in the form of multiple time steps to represent the demand changes of the power consumption nodes at different times.

[0100] S2-2. Determine the power load demand of each node in the urban power grid at each time step based on the comprehensive hazard risk level of each area in the city.

[0101] After obtaining the comprehensive hazard risk level of each area in the city, it can be found that the disaster risks of power nodes in different areas are different. Therefore, when a disaster occurs, some nodes are easily affected by the disaster, while some nodes are not. At this time, combined with the power load of the node in normal working state, an expected power load demand can be obtained, and the node can be characterized by the power load demand.

[0102] S2-3. Calculate the optimal charge and discharge amount of each node in each time step, and the optimal charge and discharge amount is determined according to the necessary power load of each node;

[0103] After determining the power load demand of the power consumption node, determine whether each power consumption node needs the mobile energy storage unit to discharge or can charge the mobile energy storage unit in each time step, as well as the specific charge and discharge amount, based on the capacity, charge and discharge speed and other parameters of the mobile energy storage unit, and finally obtain multiple groups of charge and discharge amounts of each node in each time step. The charge and discharge amount with the least time step is used as the optimal charge and discharge amount.

[0104] In some nodes connected to local power generation facilities, local power generation costs can also be introduced for calculation. By setting the power generation cost of each node and coordinating power supply with the charge and discharge capacity of the mobile energy storage unit, the optimal charge and discharge capacity of the node can be further determined.

[0105] S2-4. Calculate the optimal charge and discharge amount of each node in multiple time steps as the optimal power flow.

[0106] After obtaining the optimal charge and discharge amount, the optimal charge and discharge amounts of multiple time steps are combined to form the optimal power flow.

[0107] S3. Generate an agent scheduling strategy according to the optimal power flow, and schedule the agent through the agent scheduling strategy.

[0108] The purpose of the embodiments of the present invention is to restore the operation of the affected power nodes in the shortest time possible, while restoring the power load of important nodes as much as possible to improve the resilience of the power grid; therefore, it is necessary to dispatch mobile energy storage units within the urban area to meet the power load requirements of each power node.

[0109] Specifically, Figure 3 As shown, the embodiment of the present invention regards each mobile energy storage unit as an intelligent agent, and sets an intelligent agent observation space and a reinforcement learning algorithm for the intelligent agent.

[0110] The agent observation space includes the environment state space and the agent action space. The environment state space is used to simulate the power load demand of each node in the power grid at each time step; the agent action space is used to simulate the movement path of the agent at each time step. The position of the agent in the first time step is the initial position of the mobile energy storage unit in the city.

[0111] The parameters of the reinforcement learning algorithm include a reward function and a Q function. In the embodiment of the present invention, the meaning of the reward function is the sum of all necessary power loads of the power nodes in a certain time step, and the purpose is to make the intelligent agent more inclined to restore the active power of the necessary power load during continuous training. The Q function determines the expected node state of each node in the power grid formed by comparing the intelligent agent with the reward function after executing a movement in a certain direction and performing charging and discharging operations based on the optimal power flow.

[0112] In some embodiments, a central aggregator is also provided, which is used to share the agent observation space of multiple agents and realize the coordinated scheduling among multiple agents through the central aggregator.

[0113] For example, 10 time steps are set, and the two agents are labeled MESS1 and MESS2 respectively. t1 、MESS1 position coordinate y t1 、Power level of MESS1 t1 , load level l at the location of MESS1 t1 , a flag indicating whether the adjacent line where MESS1 is located is open (b t1 ), the position coordinate x of MESS2 t2 、MESS2 position coordinate y t2 、The power level at the location of MESS2 t2 , load level l t2 , indicating whether the adjacent line where MESS2 is located is open (b t2 ) enters the shared observation space of the agent, and the following observation space can be obtained:

[0114] [x t1 ,y t1 ,e t1 ,l t1 ,b t1 ,x t2 ,y t2 ,e t2 ,l t2 ,b t2 ], x t ∈{0,1,2},y t ∈{0,1,2},e t ∈{1,…,5},l t ∈{1,…,5},b t ∈{0,1}.

[0115] Incorporate the agent’s path selection actions (forward, backward, left, right, stay) into its action space:

[0116] [g a ,g b ,t l ,t r ,h s ].

[0117] In addition, the Q function also has an unexpected coefficient μ, which represents the probability that mobile energy storage will encounter unexpected situations such as road congestion or excessive flooding in the traffic network.

[0118] When MESSs encounter unexpected conditions on the transportation network, their action is set to "suspend transportation".

[0119] In this way, the agent will autonomously make multiple sets of movement strategies according to the reward function, and cooperate with the optimal power flow to realize the charging and discharging operations of each power node; the results of the charging and discharging operations will be updated in the environment state space as the environment update logic, and the action results of the agent will be merged in the agent action space. When the time step ends, that is, the power load requirements of all nodes are met, the environment state space and agent action space data are retrieved to obtain multiple sets of agent expected movement strategies.

[0120] After obtaining multiple groups of expected mobility strategies of intelligent agents, the optimal expected mobility strategy can be determined based on the shortest time, shortest moving path, or lowest electricity cost. The optimal expected mobility strategy is used as the intelligent agent scheduling strategy to drive the intelligent agent to perform scheduling.

[0121] As a specific example, Figure 4 As shown, the present invention uses the position bus27 as the initial position of MESS1 and MESS2 on the power grid and transportation network, and records the changes in the positions and charging and discharging capacities of the two MESS1. The electrical components include MESS, DG, photovoltaic power plants, and electric vehicle charging piles to simulate the key links of the urban power grid. At the same time, interconnection lines are set at specific locations. Before the storm surge disaster, some lines in the power grid had been partially set with circuit breaker faults, as shown in Table 8. Load parameters such as the cost of basic and non-basic loads, as well as the power supply parameters of energy storage resources are defined, as shown in Table 7. In order to simulate the failure of the power grid after a storm surge disaster, a set of circuit breaker faults are set in an embodiment of the present invention, as shown in Table 8.

[0122] Table 7 Power supply parameters

[0123]

[0124]

[0125] Table 8 Failures at different times

[0126] period Faulty circuit breaker Before a storm surge disaster strikes 9-15、19-20、31-32 After the storm surge disaster 0-1、3-4、7-8、12-22、28-29

[0127] The scheduling results are shown in Table 9.

[0128] Table 9 Dynamic dispatch results of mobile energy storage

[0129]

[0130] After the storm surge disaster, all faults in the power grid divide it into three isolated islands, and two MESSs take turns to charge and discharge at the traffic network nodes corresponding to the three islands. Considering the characteristics of the reward function set, the agent pays more attention to important loads, and the recovery goal is to restore as many important loads as possible. Therefore, the two MESSs move more on the two isolated islands, the total necessary load is larger, and the discharge action is applied. Since the load demand of each node changes over time, the amount of charge and discharge applied by the MESSs is also different at different nodes and time steps. However, as the MESS decision-making process continues, the hazard evaluation results change from high to low and then stabilize. Although the indicator fluctuates slightly in the subsequent scheduling process, it is generally at a low level, indicating that the resilience of the power grid has improved in the process of mobile energy storage decision-making.

[0131] Figure 5 It is a structural diagram of the electronic device proposed in the second embodiment of the present invention. The memory of this embodiment stores program instructions for implementing a method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery of any of the above embodiments. The processor is used to execute the program instructions stored in the memory to perform dynamic scheduling of mobile energy storage resources for post-disaster power recovery. Among them, the processor can also be called a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0132] The contents of the method in the first embodiment of the present invention are all applicable to the electronic device embodiment. The functions specifically implemented by the electronic device embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0133] Figure 6It is a schematic diagram of the structure of the computer-readable storage medium of the third embodiment of the present invention. The computer-readable storage medium of the fourth embodiment of the present invention stores program instructions that can implement the above-mentioned method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery, wherein the program instructions can be stored in the above-mentioned storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0134] The contents of the method in the first embodiment of the present invention are all applicable to the computer-readable storage medium embodiment. The functions specifically implemented by the computer-readable storage medium embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0135] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement the dynamic scheduling method of mobile energy storage resources for post-disaster power recovery provided in the above-mentioned embodiment.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0137] Those skilled in the art will appreciate that the modules in the devices in the embodiments of the present invention may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments of the present invention may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including corresponding claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including corresponding claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0138] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0139] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0140] In addition, each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. In particular, for embodiments such as devices and equipment, since they are basically similar to method embodiments, the relevant parts can refer to the partial description of the method embodiments. The embodiments of the devices and equipment described above are merely schematic, wherein the modules, units, etc. described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed in multiple places, such as nodes of a system network. Specifically, some or all of the modules and units may be selected according to actual needs to achieve the purpose of the above-mentioned embodiment scheme. Those skilled in the art can understand and implement it without paying creative labor.

[0141] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0142] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0143] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0144] In the embodiments of the present invention, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present invention may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context in the specific embodiment.

[0145] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and cannot be construed as limitations of the present invention, and those of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention. Those skilled in the art will readily come to think of other embodiments of the present invention after considering the specification and practicing the present invention. This application is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art that are not disclosed in the present invention. The specification and embodiments are intended to be exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

Claims

1. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery, characterized in that: The following steps are involved: Obtaining information on power equipment and traffic network in the city, and establishing a power-traffic coupling digital twin; the power-traffic coupling digital twin includes a plurality of mobile energy storage units as intelligent entities; Determine the comprehensive hazard risk level of each area in the city, and solve the optimal power flow of the city based on the comprehensive hazard risk level of each area in the city; An intelligent agent scheduling strategy is generated according to the optimal power flow, and the intelligent agent is scheduled according to the intelligent agent scheduling strategy.

2. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 1, characterized in that: The power-transportation coupling digital twin is presented as a coupling network of the urban power grid and the transportation network; the optimal power flow is represented by the power grid; and the intelligent agent scheduling strategy is represented by the transportation network.

3. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 1, characterized in that: The comprehensive hazard risk level of each area in the city is obtained by the following steps: Determine the danger level of each area in the city based on the risk level of each danger indicator in the area and the corresponding combined weight; Determine the exposure level of each area in the city based on the exposure level of each exposure indicator in the area combined with the corresponding combined weight; The vulnerability level of each area in the city is determined based on the vulnerability level of each vulnerability indicator in the area and the corresponding combined weight; Determine the social vulnerability level of each area within the city based on the exposure and vulnerability levels of the area; The comprehensive hazard risk level of each area in the city is determined based on the area's hazard level and social vulnerability level.

4. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 3, characterized in that: The danger indicators include the maximum flood depth, average flood depth, maximum flood velocity, flood area ratio and flood duration of the region; The exposure indicators include population density, population dependency ratio, population education level, number of old residential areas, number of water supply facilities, number of electricity facilities, number of markets, number of historical buildings and number of public parking lots in the area; The vulnerability indicators include the distance to rescue departments, the distance to security departments, the distance to emergency shelters, and the distance to medical institutions in the area.

5. The method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 1, characterized in that: The method of solving the optimal power flow of the city according to the comprehensive hazard risk level of each area in the city specifically includes the following steps: Represent the post-disaster recovery time in the form of multiple time steps; Determine the power load demand of each node in the urban power grid at each time step according to the comprehensive hazard risk level of each area in the city; the power load demand includes necessary power load and non-essential power load; Calculating the optimal charge and discharge amount of each node in each time step, wherein the optimal charge and discharge amount is determined according to the necessary power load of each node; The optimal charge and discharge amount of each node is calculated by multiple time steps as the optimal power flow.

6. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 5, characterized in that: The step of generating an intelligent agent scheduling strategy according to the optimal power flow specifically comprises the following steps: Set the reinforcement learning algorithm parameters and the agent observation space; The reinforcement learning algorithm parameters include a reward function and a Q function; the reward function is determined according to the necessary power load of each node in the environmental state space in each time step; the Q function includes the expected node state of each node in the power grid formed by comparing the intelligent agent with the reward function after moving in various directions to perform charging and discharging operations based on the optimal power flow; The agent observation space includes an environment state space and an agent action space; wherein the environment state space is used to simulate the power load demand of each node in the power grid in each time step; the agent action space is used to simulate the moving path of the agent in each time step; wherein the position of the agent in the first time step is the initial position of the mobile energy storage unit in the city; In each time step, the path selection action of the agent is merged into the agent action space; the expected node state after receiving the charging and discharging operation is merged into the environment state space; after all time steps are completed, the environment state space and agent action space data are retrieved to obtain multiple sets of expected movement strategies of the agent; Select the optimal expected movement strategy as the agent scheduling strategy.

7. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 6, characterized in that: The method also includes the step of setting a central aggregator; the central aggregator is used to share the agent observation space of multiple agents; and the coordinated scheduling among multiple agents is achieved through the central aggregator.

8. A method for dynamic scheduling of mobile energy storage resources for post-disaster power recovery according to claim 6, characterized in that: The Q function is also provided with an unexpected coefficient, which is used to indicate the probability that the agent stops moving when encountering an unexpected situation.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement a dynamic scheduling method for mobile energy storage resources for post-disaster power recovery as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement a dynamic scheduling method for mobile energy storage resources for post-disaster power recovery according to any one of claims 1-8.

Images