Emergency power supply planning method, device and equipment for mobile energy storage vehicle and storage medium

Abstract

The invention discloses an emergency power supply planning method, device and equipment for a mobile energy storage vehicle and a storage medium. The method comprises the following steps: acquiring traffic data, power demand data and energy storage vehicle data in real time; performing clustering analysis on the traffic data and the electricity demand data through an improved clustering algorithm so as to divide the power failure area into a plurality of sub-areas; and inputting the traffic data, the power consumption demand data and the energy storage vehicle data corresponding to each sub-region into a preset path optimization model, and solving under constraint conditions through an improved adaptive genetic algorithm by taking the minimization of the planning total cost of each sub-region as a target until a preset condition is met, thereby obtaining a path optimization result. And obtaining a target planning scheme corresponding to each sub-region, and planning a power supply path of the energy storage vehicle based on each target planning scheme. According to the invention, the power supply path planning reliability of the energy storage vehicle can be improved under a complex road traffic condition.

Description

Technical Field

[0001] This invention relates to the field of emergency power path planning, and more particularly to emergency power supply planning methods, devices, equipment, and storage media for mobile energy storage vehicles. Background Technology

[0002] Complex road conditions, such as congestion caused by disasters or accidents, temporary traffic control, and peak traffic periods, directly affect the efficiency and arrival time of mobile energy storage vehicles. The core requirement for emergency power supply is to provide continuous and uninterrupted power to critical loads such as hospitals and communication base stations. If the reliability of vehicle route planning is insufficient, energy storage vehicles may fail to arrive on time due to road obstructions, insufficient power supply duration, or missed service nodes, leading to the interruption of critical load operations and potentially causing serious consequences such as medical safety risks or emergency communication paralysis. Therefore, improving the reliability of energy storage vehicle power supply route planning under complex road conditions is a core objective of emergency power security systems.

[0003] Existing mobile energy storage vehicle route planning methods lack comprehensive modeling and optimization of dynamic changes in urban traffic congestion and traffic control policy constraints, making them ineffective in addressing changes in actual road conditions under disaster emergency environments. Specifically: route planning often employs static algorithms or time estimates based on historical averages, ignoring the evolving characteristics of traffic congestion in different time periods and regions. It fails to comprehensively consider the nonlinear impact of multiple factors such as road grade and departure time on travel time, and lacks probabilistic modeling and opportunity constraint control for traffic uncertainty, resulting in high power supply risks and difficulty in ensuring the reliability target of continuous power supply to critical loads for at least the preset time. Route planning optimization is often based on unified modeling across the entire network, without scientifically clustering and dividing regions. As the number of nodes increases, the computational complexity grows exponentially, failing to meet real-time emergency needs. Traffic congestion modeling is crude, and route optimization relies on traditional heuristic algorithms, exhibiting slow convergence, weak global search capabilities, and susceptibility to local optima, making it difficult to adapt to large-scale, multi-objective, and multi-constraint scenarios. Furthermore, the models generally lack clear power supply reliability constraints and objective functions, making it impossible to accurately control key safety indicators such as the minimum continuous power supply duration for critical loads. Summary of the Invention

[0004] This invention provides an emergency power supply planning method, apparatus, equipment, and storage medium for mobile energy storage vehicles, which can improve the reliability of power supply path planning for energy storage vehicles under complex road traffic conditions.

[0005] In a first aspect, an embodiment of the present invention provides an emergency power supply planning method for a mobile energy storage vehicle, characterized in that it includes: Real-time acquisition of traffic data in the power outage area, user electricity demand data, and energy storage vehicle data of currently available energy storage vehicles; By improving the clustering algorithm, the traffic data and the electricity demand data are clustered and analyzed to divide the power outage area into several sub-regions; The traffic data, electricity demand data, and energy storage vehicle data corresponding to each sub-region are input into a preset path optimization model. The goal is to minimize the total planning cost of each sub-region. An improved adaptive genetic algorithm is used to solve the problem under constraints until the preset conditions are met, thereby obtaining the target planning scheme for each sub-region. Based on each target planning scheme, the power supply path for the energy storage vehicle is planned. The improved adaptive genetic algorithm is obtained by introducing traffic control constraints and power supply time gaps into the traditional genetic algorithm to construct a dual-track evolution of electric and transportation systems.

[0006] By acquiring real-time traffic data, user electricity demand data, and available energy storage vehicle data for the power outage area, comprehensive and dynamic basic data support is provided for route planning, improving the reliability of route planning from the data source. An improved clustering algorithm is used to divide the area into sub-regions based on traffic data and electricity demand data, achieving deep integration of traffic control characteristics and user distribution characteristics. This makes the traffic constraints and user needs in each sub-region more homogeneous and reduces interference from complex road conditions across regions. With the goal of minimizing the total planning cost of sub-regions, an improved adaptive genetic algorithm is used to solve the route optimization model. By introducing traffic control constraints and power supply time gaps, a dual-track evolution of power and traffic is constructed to obtain the target planning scheme for energy storage vehicles to supply power along the power supply path. This can accurately control economic indicators such as vehicle fixed costs and operating costs, and can also force the power supply needs of important loads through the power supply time gap related mechanism, achieving the goals of optimal cost and reliable power supply. This significantly improves the reliability of planning energy storage vehicle power supply paths under complex road traffic conditions.

[0007] Furthermore, the traffic data includes restricted time periods and restricted vehicle data, and the electricity demand data includes address data. The improved clustering algorithm is used to perform cluster analysis on the traffic data and the electricity demand data to divide the power outage area into several sub-regions, specifically including: The restricted time period data, the restricted vehicle data, and the address data are weighted according to a preset ratio to obtain a weighted feature vector; Based on the weighted feature vector, the power outage area is clustered using a clustering algorithm until a preset condition is met, resulting in several sub-regions. The clustering algorithm is the k-means clustering algorithm.

[0008] This approach utilizes traffic data (restricted time periods, restricted vehicle data) and electricity demand data (address data) to form a weighted feature vector, which is then weighted according to a preset ratio. This vector is combined with a k-means clustering algorithm to divide the data into sub-regions. Each sub-region shares similarities in geographical location and traffic characteristics with its user network points, achieving a fusion of traffic control features and user location information. Compared to fuzzy clustering dimensions, the targeted selection of the three data types and weight configuration allows the divided sub-regions to better adapt to traffic control policies, reducing interference between regions and improving path planning efficiency. Furthermore, the k-means algorithm ensures efficient and stable region division, allowing subsequent path planning to focus on homogeneous sub-regions. This regional division provides a fundamental support for the reliability of energy storage vehicle path planning under complex road conditions.

[0009] Furthermore, before inputting the traffic data, electricity demand data, and energy storage vehicle data corresponding to each of the sub-regions into the preset path optimization model, the method further includes: establishing an objective function and constraints with the lowest total cost based on the traffic data, electricity demand data, energy storage vehicle data, and preset penalty coefficients corresponding to each of the sub-regions, wherein the constraints include service integrity constraints, resource coordination constraints, and spatiotemporal coordination constraints.

[0010] This approach, based on sub-regional data and preset penalty coefficients, constructs an objective function that minimizes the total planning cost, along with constraints on service integrity, resource coordination, and spatiotemporal coordination. This enables the path optimization model to adapt to complex scenarios. The service integrity constraint ensures that each user node receives power without omission or duplication, preventing reliability degradation due to service deficiencies. The resource coordination constraint matches the number of vehicles with power supply capacity, preventing power outages due to resource mismatches. The spatiotemporal coordination constraint adapts to traffic control and power supply timeliness, avoiding path failures caused by time conflicts or traffic restrictions. The combination of these three types of constraints and the cost objective ensures that the model solution always revolves around "feasibility and reliability," providing a model foundation for the feasibility of path planning schemes and the reliability of power supply under complex road conditions.

[0011] Furthermore, the construction process of the objective function specifically includes: The fixed cost of the vehicle is calculated based on the unit vehicle cost and preset decision variables. The vehicle driving cost is calculated based on the transportation distance, unit driving cost and decision variables. The timeout penalty cost is calculated based on the unit penalty cost, the vehicle arrival time at the departure point, the interval time, the time period number and the maximum service time of a single mobile energy storage vehicle. The power supply reliability penalty cost is calculated based on the important load set, the actual power supply time, the preset required power supply time and the preset penalty coefficient. The objective function is derived based on the vehicle fixed cost, the vehicle operating cost, the timeout penalty cost, and the power supply reliability penalty cost.

[0012] By calculating and integrating vehicle fixed costs, vehicle operating costs, overtime penalty costs, and power supply reliability penalty costs into an objective function, a quantitative balance between economic efficiency and power supply reliability is achieved. Among these, the power supply reliability penalty cost is directly related to the power supply time gap of critical loads through a preset penalty coefficient, which can force the optimization process to prioritize the needs of critical loads. Compared with general cost accounting, the refined modeling of multi-dimensional costs can avoid sacrificing power supply safety for cost reduction, ensuring that the solution can control operating costs under complex road conditions and force critical loads to meet power supply standards through the penalty mechanism, thus significantly improving the reliability of route planning.

[0013] Furthermore, the step of solving the problem using an improved adaptive genetic algorithm under constraints until preset conditions are met, to obtain the target planning scheme corresponding to each sub-region, specifically includes: Based on the path optimization model, a first set of individuals is randomly generated according to preset generation conditions. The fitness of each individual in the first set of individuals is calculated. Several selection probabilities are determined based on each fitness. The first set of individuals is then filtered by combining each selection probability to obtain a second set of individuals. Based on the fitness of each individual in the second individual set, several mutation probabilities are determined. The second individual set is then mutated according to each mutation probability to obtain a third individual set. A local optimization operation is then performed on the third individual set to obtain a fourth individual set. The target planning scheme is output after the preset conditions are met.

[0014] Based on the path optimization model, a first set is generated under preset conditions. A second set is obtained by combining fitness and selection probability. This prioritizes high-quality individuals that fit the traffic, demand, and energy storage vehicle data of the sub-regions, while eliminating invalid solutions. The mutation probability is dynamically determined based on the fitness of individuals in the second set, and mutation is performed to obtain a third set. The mutation intensity can be adjusted as needed to explore new solutions or protect high-quality individuals, enhancing adaptability to dynamic constraints under complex road conditions. Local optimization of the third set yields a fourth set, which can further optimize the defects of the individual set, allowing individuals to iterate towards traffic adaptation, power supply reliability, and cost optimization. Through iterative operations until the preset conditions are met, the final target planning scheme adapted to each sub-region is output, effectively reducing the risk of path failure and power outage, and improving the reliability of energy storage vehicle power supply planning under complex road conditions.

[0015] Furthermore, the planning of the power supply path for the energy storage vehicle based on each of the target planning schemes specifically includes: Based on the target planning scheme, a path navigation command is issued to the energy storage vehicle; The energy storage vehicle is planned to arrive at the corresponding sub-area according to the path navigation instructions, and execute a preset standardized grid connection operation procedure to supply power.

[0016] This approach, by issuing path navigation instructions based on the target planning scheme and controlling the energy storage vehicle to execute standardized grid connection procedures, achieves a closed loop from path planning to power supply execution. The path navigation instructions ensure that the energy storage vehicle travels along the optimized and reliable path, avoiding blind detours in complex road conditions. The standardized grid connection operation strictly controls power supply parameters to avoid power outages caused by grid connection impacts. This instruction guidance and standardized execution can effectively reduce human error and equipment failure risks during the implementation of the planning scheme, ensure the stable execution of energy storage vehicle power supply in complex road conditions, and improve the reliability of path planning.

[0017] Furthermore, after planning the power supply path for the energy storage vehicle based on each of the aforementioned target planning schemes, the method further includes: Real-time traffic congestion data is acquired, and the traffic status is determined based on the traffic congestion data to obtain the determination result; The three-level response mechanism is activated based on the judgment result to ensure the normal power supply of the energy storage vehicle. The three-level response mechanism includes a primary response stage, an intermediate response stage, and a high-level response stage. The primary response stage controls the energy storage vehicle to automatically switch to a preset parallel branch detour scheme. The intermediate response stage plans for idle energy storage vehicles within a preset range to jointly undertake a preset ratio of load tasks. The high-level response stage controls the energy storage vehicle to complete power transmission in a designated safety island.

[0018] In this way, by monitoring traffic congestion data in real time and activating a three-level response mechanism during the power supply process, dynamic adaptation to sudden situations in complex road conditions is achieved. When an anomaly is detected, the graded response of primary detour, intermediate coordination, and advanced power transfer can quickly resolve sudden traffic risks and avoid power supply delays or interruptions caused by sudden changes in road conditions. This monitoring and response mechanism makes up for the limitations of static planning schemes, enabling energy storage vehicles to maintain power supply continuity even in complex road condition fluctuations, and significantly improving the planning reliability in emergency scenarios.

[0019] Secondly, an embodiment of the present invention provides an emergency power supply planning device for a mobile energy storage vehicle, characterized in that it includes a data acquisition module, a partitioning module, and a planning module; The acquisition module is used to acquire in real time traffic data of the power outage area, user electricity demand data, and energy storage vehicle data of currently available energy storage vehicles; The partitioning module is used to perform cluster analysis on the traffic data and the electricity demand data through an improved clustering algorithm, so as to divide the power outage area into several sub-regions. The planning module is used to input the traffic data, electricity demand data, and energy storage vehicle data corresponding to each sub-region into a preset path optimization model. The goal is to minimize the total planning cost of each sub-region. An improved adaptive genetic algorithm is used to solve the problem under constraints until the preset conditions are met, thereby obtaining the target planning scheme for each sub-region. Based on each target planning scheme, the power supply path for the energy storage vehicle is planned. The improved adaptive genetic algorithm is obtained by introducing traffic control constraints and power supply time gaps into the traditional genetic algorithm to construct a dual-track evolution of electric and transportation systems.

[0020] This approach, through the acquisition module, acquires real-time traffic data, user electricity demand data, and available energy storage vehicle data for the power outage area, providing comprehensive and dynamic basic data support for route planning and improving the reliability of route planning from the data source. The partitioning module uses an improved clustering algorithm to perform cluster analysis based on traffic data and electricity demand data to divide the area into sub-regions, achieving deep integration of traffic control characteristics and user distribution characteristics. This makes the traffic constraints and user needs within each sub-region more homogeneous and reduces interference from complex road conditions across regions. The planning module aims to minimize the total planning cost of sub-regions. It combines an improved adaptive genetic algorithm to solve the route optimization model. By introducing traffic control constraints and power supply time gaps, it constructs a dual-track evolution of power and traffic to obtain the target planning scheme. The plan allows energy storage vehicles to supply power along the power supply path, accurately controlling economic indicators such as vehicle fixed costs and operating costs. It also forces the power supply needs of important loads to be guaranteed through the power supply time gap mechanism, achieving the goals of optimal cost and reliable power supply. This significantly improves the reliability of planning energy storage vehicle power supply paths under complex road traffic conditions.

[0021] Thirdly, another embodiment of the present invention provides a terminal device, characterized in that it includes: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction that causes the processor to perform an operation of an emergency power supply planning method for a mobile energy storage vehicle.

[0022] Fourthly, another embodiment of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device or apparatus where the computer-readable storage medium is located to perform an emergency power supply planning method for a mobile energy storage vehicle. Attached Figure Description

[0023] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating one embodiment of an emergency power supply planning method for a mobile energy storage vehicle provided in this application; Figure 2 This is a schematic diagram of the solution process of an improved adaptive genetic algorithm provided in this application; Figure 3 This is a structural schematic diagram of an emergency power supply planning device for a mobile energy storage vehicle provided in this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0027] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0030] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0031] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0032] In the field of emergency power planning for mobile energy storage vehicles, the reliability of route planning under complex road traffic conditions is crucial to ensuring power supply to critical loads. However, current route planning methods face significant challenges. Existing methods have the following shortcomings: they lack comprehensive modeling of dynamic changes in traffic congestion and regulatory constraints; route planning relies on static algorithms or historical averages, ignoring the influence of multidimensional factors and lacking uncertainty modeling; they do not scientifically cluster regions, and modeling the entire network leads to excessively high computational complexity, making it difficult to meet real-time requirements; they rely on traditional heuristic algorithms, resulting in slow convergence and susceptibility to local optima; and the models lack power supply reliability constraints and objective functions, making it impossible to accurately guarantee the duration of power supply to critical loads.

[0033] See Figure 1 To improve the reliability of power supply path planning for energy storage vehicles under complex road traffic conditions, an embodiment of the present invention provides an emergency power supply planning method for mobile energy storage vehicles, including steps S101 to S103. Step S101: Real-time acquisition of traffic data in the power outage area, user electricity demand data, and energy storage vehicle data of currently available energy storage vehicles; In some embodiments, the real-time acquisition of traffic data, user electricity demand data, and currently available energy storage vehicle data in the power outage area specifically includes: using data interfaces such as Gaode Map API and Baidu Map API to collect real-time traffic congestion information on urban roads, including road conditions, traffic flow, and traffic accidents, and to acquire traffic control policy information, such as data on restricted driving times and restricted vehicles in specific areas; cleaning and normalizing the collected traffic data so that subsequent models can accurately use this data; acquiring user electricity demand data in the power outage area, including user address data, electricity load size, power outage duration, and importance level, and classifying users into ordinary loads and important loads based on importance level (such as critical loads like hospitals and communication base stations), ensuring that subsequent models prioritize high-priority nodes.

[0034] Step S102: Perform cluster analysis on the traffic data and the electricity demand data using an improved clustering algorithm to divide the power outage area into several sub-regions; In some embodiments, the traffic data includes restricted traffic time period data and restricted vehicle data, and the electricity demand data includes address data. The step of performing cluster analysis on the traffic data and the electricity demand data using an improved clustering algorithm to divide the power outage area into several sub-regions specifically includes: assigning weights to the restricted traffic time period data, the restricted vehicle data, and the address data according to a preset ratio to obtain a weighted feature vector; and performing cluster analysis on the power outage area based on the weighted feature vector, combined with a clustering algorithm, until a preset condition is met to obtain several sub-regions. The clustering algorithm is a k-means clustering algorithm. Specifically, an improved k-means clustering algorithm is used, adjusting the weight configuration based on three dimensions: user outlet address data, node restricted traffic time period data, and node restricted vehicle data (e.g., a weight ratio of 0.4:0.3:0.3), to obtain a weighted feature vector. This weighted feature vector is then used to perform cluster analysis on all user outlets within the power outage area, dividing the entire power outage area into multiple sub-regions. User outlets within each sub-region are similar in geographical location and traffic characteristics. Sub-regions defined by cluster analysis can better adapt to traffic control policies, reduce interference between regions, and improve route planning efficiency.

[0035] This approach utilizes traffic data (restricted time periods, restricted vehicle data) and electricity demand data (address data) to form a weighted feature vector, which is then weighted according to a preset ratio. This vector is combined with a k-means clustering algorithm to divide the data into sub-regions. Each sub-region shares similarities in geographical location and traffic characteristics with its user network points, achieving a fusion of traffic control features and user location information. Compared to fuzzy clustering dimensions, the targeted selection of the three data types and weight configuration allows the divided sub-regions to better adapt to traffic control policies, reducing interference between regions and improving path planning efficiency. Furthermore, the k-means algorithm ensures efficient and stable region division, allowing subsequent path planning to focus on homogeneous sub-regions. This regional division provides a fundamental support for the reliability of energy storage vehicle path planning under complex road conditions.

[0036] Step S103: Input the traffic data, electricity demand data, and energy storage vehicle data corresponding to each sub-region into a preset path optimization model. With the goal of minimizing the total planning cost of each sub-region, solve the problem under constraints using an improved adaptive genetic algorithm until the preset conditions are met, and obtain the target planning scheme corresponding to each sub-region. Then, plan the power supply path of the energy storage vehicle based on each target planning scheme. The improved adaptive genetic algorithm is obtained by introducing traffic control constraints and power supply time gaps into the traditional genetic algorithm to construct a dual-track evolution of electric transportation.

[0037] In some embodiments, before inputting the traffic data, electricity demand data, and energy storage vehicle data corresponding to each of the sub-regions into a preset path optimization model, the method further includes: establishing an objective function and constraints with the lowest total cost based on the traffic data, electricity demand data, energy storage vehicle data, and preset penalty coefficients corresponding to each of the sub-regions, wherein the constraints include service integrity constraints, resource coordination constraints, and spatiotemporal coordination constraints.

[0038] Specifically, based on traffic data, electricity demand data, energy storage vehicle data, and preset penalty coefficients, an objective function is established to minimize the total cost, which includes the vehicle's fixed cost, the vehicle's operating cost, the timeout penalty cost, and the power supply reliability penalty cost. At the same time, constraints are set, including service integrity constraints, resource coordination constraints, and spatiotemporal coordination constraints. Service integrity constraints require that each node be served by only one vehicle and that each user node have exactly one energy storage vehicle departing. Resource coordination constraints address physical limitations on vehicle routing and power supply capacity, establishing a triple guarantee of vehicle planning balance, available vehicle restrictions, and power supply capacity constraints. Vehicle planning balance controls the total number of vehicles used to ensure that the number of vehicles departing from the starting point equals the number of vehicles returning to the starting point. Available vehicle restrictions require that the number of vehicles departing from the starting point cannot exceed the total number of available energy storage vehicles. Power supply capacity constraints require that the power supply capacity of each energy storage vehicle cannot exceed the battery capacity. Spatiotemporal coordination constraints involve time and regulatory constraints. The time dimension requires that the departure time from the user node be the arrival time at the user node plus the power supply time at the user node, and all energy storage vehicles must depart within the working time period of the starting point, while ensuring that the actual power supply time is greater than the planned power supply time, and mandating a minimum power supply duration for critical loads (e.g., a minimum of 2 hours) to ensure emergency power safety. Regulatory constraints prohibit vehicles from entering restricted road sections during restricted periods to ensure compliance with traffic regulations.

[0039] In some embodiments, the relevant formulas for the constraints specifically include: In the service integrity constraint, the formula that requires each node to be served by only one vehicle is: ; In the service integrity constraint, the formula that requires each user node to have exactly one energy storage vehicle leave is: ; The formula for vehicle planning balance is: ; The formula for limiting available vehicles is: ; The formula for power supply capacity constraints is: ; The formula for calculating the time to leave a user node as the time to arrive at the user node plus the power supply time at the user node is: ; The formula requiring all energy storage vehicles to depart within the working time period at their starting point is: ; The formula for ensuring that the actual power supply time is greater than the planned power supply time is: ; The minimum power supply duration for mandatory protection of critical loads is as follows: ; The formula for regulatory constraints is: ; In the formula, This represents the total number of available energy storage vehicles. This represents the total number of user nodes in the sub-region (excluding energy storage stations). Index for energy storage vehicles; and For node indexing; Let be the set of all nodes within the sub-region, where 0 represents the starting point of the energy storage vehicle; The set of all user nodes except the starting point; A collection of energy storage vehicles; Gather at the designated departure time; The preset decision variables are binary variables, representing the variables from the nodes. To the node Is it by the first Energy storage vehicle service, if the vehicle From node Drive to the node The value is 1 if it is 1, otherwise it is 0. For the power load demand of user nodes; The maximum power supply capacity for energy storage vehicles; For vehicles leaving user nodes Time; For the vehicle to reach the user node Time; The planned power supply time for the energy storage vehicle while it is stationed at the user node; For the first Each energy storage vehicle selects a time slot number from its starting point; Indicates the actual power supply time; Indicates the required power supply time (e.g., 2 hours); For important load sets; This is a binary variable representing a node. To the node Is there traffic control? Prohibited behavior: 1; Allowed behavior: 0. That is, when prohibition is in effect, a mandatory order is issued. .

[0040] It should be noted that the starting points of energy storage vehicles include, but are not limited to, substations and energy storage stations; for residential users, the electricity load demand is calculated based on the average daily electricity consumption or the duration of power outages, while for critical loads, it is determined based on the power requirements of key equipment and the expected operating time; the maximum power supply capacity of the energy storage vehicle depends on the battery capacity of the energy storage vehicle; the set of critical loads includes critical nodes, which are not limited to, hospitals, communication base stations, and government facilities.

[0041] This approach, based on sub-regional data and preset penalty coefficients, constructs an objective function that minimizes the total planning cost, along with constraints on service integrity, resource coordination, and spatiotemporal coordination. This enables the path optimization model to adapt to complex scenarios. The service integrity constraint ensures that each user node receives power without omission or duplication, preventing reliability degradation due to service deficiencies. The resource coordination constraint matches the number of vehicles with power supply capacity, preventing power outages due to resource mismatches. The spatiotemporal coordination constraint adapts to traffic control and power supply timeliness, avoiding path failures caused by time conflicts or traffic restrictions. The combination of these three types of constraints and the cost objective ensures that the model solution always revolves around "feasibility and reliability," providing a model foundation for the feasibility of path planning schemes and the reliability of power supply under complex road conditions.

[0042] In some embodiments, the process of constructing the objective function specifically includes: calculating the vehicle fixed cost based on the unit vehicle cost and preset decision variables; calculating the vehicle travel cost based on the transportation distance, unit travel cost, and decision variables; calculating the overtime penalty cost based on the unit penalty cost, vehicle arrival time at the departure point, interval time, time period number, and the maximum service duration of a single mobile energy storage vehicle; calculating the power supply reliability penalty cost based on the important load set, actual power supply time, preset required power supply time, and the preset penalty coefficient; and obtaining the objective function based on the vehicle fixed cost, the vehicle travel cost, the overtime penalty cost, and the power supply reliability penalty cost. Specifically, the total cost consists of four parts: vehicle fixed cost, vehicle travel cost, overtime penalty cost, and power supply reliability penalty cost. The vehicle fixed cost is used to quantify the fixed activation cost generated by planning the mobile energy storage vehicle route; the vehicle travel cost is used to quantify the mileage cost generated by the vehicle during delivery; the overtime penalty cost is used to quantify the penalty cost incurred by the vehicle due to exceeding the maximum service time; and the power supply reliability penalty cost is used to quantify the power supply gap loss of important loads, and the preset penalty coefficient is used to force the continuous power supply of critical loads to be greater than or equal to a preset time (e.g., 2 hours).

[0043] In some embodiments, the relevant formulas for constructing the objective function specifically include: Objective function: ; The formula for vehicle fixed costs: ; The formula for vehicle operating costs: ; Formula for the cost of timeout penalty: ; Formula for power supply reliability penalty cost: ; In the formula, Total cost; Fixed costs for vehicles; For vehicle operating costs; The cost of penalties for exceeding the time limit; To ensure reliable power supply, costs are penalized. This represents the total number of available energy storage vehicles. This represents the total number of user nodes in the sub-region (excluding energy storage stations). Index for energy storage vehicles; and For node indexing; The preset decision variables are binary variables, representing the variables from the nodes. To the node Is it by the first Energy storage vehicle service, if the vehicle From node Drive to the node The value is 1 if it is 1, otherwise it is 0. Cost per unit vehicle; For nodes To node The transportation distance; Cost per unit of travel; The time it takes for the vehicle to return to its starting point; This refers to the interval time. For the first Each energy storage vehicle selects a time slot number from its starting point; Gather at the designated departure time; The maximum service duration for a single mobile energy storage vehicle; Penalty cost per unit; For important load sets; Indicates the required power supply time (e.g., 2 hours); Indicates the actual power supply time; This is a penalty coefficient (e.g., 1000 yuan / hour).

[0044] By calculating and integrating vehicle fixed costs, vehicle operating costs, overtime penalty costs, and power supply reliability penalty costs into an objective function, a quantitative balance between economic efficiency and power supply reliability is achieved. Among these, the power supply reliability penalty cost is directly related to the power supply time gap of critical loads through a preset penalty coefficient, which can force the optimization process to prioritize the needs of critical loads. Compared with general cost accounting, the refined modeling of multi-dimensional costs can avoid sacrificing power supply safety for cost reduction, ensuring that the solution can control operating costs under complex road conditions and force critical loads to meet power supply standards through the penalty mechanism, thus significantly improving the reliability of route planning.

[0045] In some embodiments, before solving the problem under constraints using an improved adaptive genetic algorithm until preset conditions are met and the target planning scheme corresponding to each sub-region is obtained, the following steps are taken: defining individuals. Specifically, each individual represents a planning scheme. Individuals adopt a dual-track gene structure, including path gene segments and time period gene segments. The path gene segment uses integer permutation encoding to represent the service sequence of energy storage vehicles, constructing a complete delivery path with energy storage station nodes (e.g., represented by 0) as separators (e.g., [0,3,1,0,2,5,6,0] represents the paths of two vehicles: 0→3→1→0 and 0→2→5→6→0). At the same time, a traffic control constraint transformation mechanism is established to dynamically transform prohibited variables into a node connection taboo table, avoiding the generation of illegal paths from the gene level. The time period gene segment uses defined integer vectors to represent the departure time sequence (e.g., [9,11] represents the first vehicle departing at time period 9 and the second vehicle departing at time period 11). A dynamic feasible time window is set based on the power supply reliability target, and the timeliness of power supply for critical loads is ensured through the genetic evolution of time period numbers.

[0046] In some embodiments, the step of solving the problem by improving the adaptive genetic algorithm under constraints until a preset condition is met to obtain the target planning scheme corresponding to each sub-region specifically includes: based on the path optimization model, randomly generating a first set of individuals according to preset generation conditions; calculating the fitness of each individual in the first set of individuals; determining several selection probabilities based on each fitness; and filtering the first set of individuals by combining the selection probabilities to obtain a second set of individuals; determining several mutation probabilities based on the fitness of each individual in the second set of individuals; performing mutation processing on the second set of individuals according to the mutation probabilities to obtain a third set of individuals; and performing local optimization operations on the third set of individuals to obtain a fourth set of individuals, until the preset condition is met and the target planning scheme is output.

[0047] Specifically, firstly, a constraint-guided population initialization mechanism is established, based on preset generation conditions (e.g., path gene segments are arranged according to the principle of uniform node distribution, and time-segment gene segments are within the feasible region). An initial set of individuals (e.g., 200 individuals) is randomly generated by uniformly sampling within the "departure time slot set". This set can be considered as a population. After generation, individuals within the initial set undergo a triple pre-screening process, including deleting those that violate the prohibition constraints. Remove power supply time for critical load nodes Individuals whose arrival time is less than a preset time (e.g., 1.5 hours) are prioritized for path resource allocation to key nodes such as hospitals and base stations to ensure the feasibility of the initial population. During the population initialization phase, the system uses preset decision variables. Perform hard constraint assignment, and prioritize generating those containing The path connecting the nodes, and it is mandatory that all critical nodes must be covered, i.e. The set of individuals selected is the first set; Then, guided by power supply reliability, the fitness function is defined as the reciprocal of the total cost and the reliability penalty. By using a preset high-coefficient penalty term (such as 1000 yuan / hour), any solution that does not meet the power supply requirements of important loads is strongly penalized to ensure that the algorithm achieves a balance between cost minimization and power supply guarantee, so that the evolutionary process converges towards ensuring the continuous power supply of important loads. Then, the fitness is calculated for each individual in the first set of volumes. Next, the power supply compliance rate of each individual in the first set is calculated, which is the proportion of important load nodes that meet the condition that the actual power supply time is greater than the required power supply time to the total number of nodes of that type. If the power supply compliance rate of an individual exceeds a preset percentage (such as 90%), its fitness value is increased (such as by 50%). Based on this weighted fitness value, the selection probability of each individual is calculated. Finally, by repeatedly executing the roulette wheel rotation operation, individuals are selected from the current set to form a mating pool, which is the selected individual set. This ensures that the high fitness scheme has more genetic opportunities in terms of probability, driving the population to evolve towards a low-cost and high-reliability direction. Then, the sequential crossover operator (OX) is applied to the selected individual set to perform recombination path gene operations, first setting the crossover probability (e.g., fixed at 0.5%). Then, two parent individuals are randomly selected from the selected individual set, and a consecutive node subsequence from the path sequence of parent 1 is randomly selected and directly copied to the corresponding position in the child generation; the remaining empty slots in the child generation sequence are filled according to the order of nodes in parent 2; to ensure that the newly generated child generation path does not violate traffic control constraints, the algorithm introduces a dynamic taboo repair mechanism, which is based on a no-entry sign matrix generated from real-time traffic data. A node connection taboo table is dynamically constructed. During or after the crossover process, the system continuously monitors each connection (i→j) in the child path. If a taboo table is found... If the connection is invalid, the connection is determined to be illegal. At this time, the system will automatically trigger the repair program, which will forcibly split the path by inserting the energy storage station separator "0" at the illegal connection point (e.g., after node i) to avoid the prohibited road section. After the selected individual set is recombined with the path gene operation, a second set is obtained. Next, based on the evolutionary state of the second set, a dynamic mutation probability mechanism is established to handle different convergence states. When premature maturity is detected (e.g., the ratio of the average fitness value of the current population to the optimal fitness value of the current population is less than 0.5), the mutation probability is increased (e.g., by 0.2) to enhance population diversity. In other cases, the mutation probability is maintained within a preset value (e.g., 0.05) to protect superior genes. After determining the number of individuals that need to be mutated in the current generation, three types of targeted mutation operations are performed on the selected individuals in priority order. These three types of targeted mutation operations include: emergency splitting mutation, time period reset mutation, and node exchange mutation. Emergency splitting mutation inserts a separator 0 after nodes whose actual power supply time is less than a preset time (e.g., 1.8h) to split the path and prioritize the power supply time of that node. Time period reset mutation resamples the departure time within the departure time set for vehicles whose total path time exceeds the maximum service time. Node exchange mutation only allows the exchange of nodes without... Constraint nodes; after mutation processing, a third volume set is obtained; Then, local optimization is performed on the third set. This application introduces a dual-track elite optimization strategy in the local optimization operation, which is executed after each generation iteration. In each generation, the individuals with the best fitness (e.g., the top 10%) are directly promoted to the next generation, and dual-track optimization is implemented. The dual-track optimization includes: the first is control-aware 2-opt local optimization, which, when traversing path nodes, only performs local optimization on nodes without prohibition constraints (i.e., ... The first optimization involves swapping the positions of nodes to ensure that the route adjustment does not violate traffic dynamic control rules; the second optimization involves rebalancing the power supply time, transferring the redundant time of nodes whose actual power supply time is longer than the preset time (e.g., 2.2 hours) to the critical node, thereby systematically improving the overall power supply reliability without significantly increasing the total cost; the fourth set is obtained after local optimization operations. In each iteration of the above steps, after each fitness calculation, a termination determination is required based on preset conditions, and the target planning scheme is output. This application adopts a triple termination determination mechanism, including: a maximum iteration limit, an optimal solution stability condition, and a population diversity threshold. In the maximum iteration limit, an upper limit is set for the maximum number of iterations of the improved adaptive genetic algorithm. When the number of iterations reaches this threshold, the algorithm is forcibly terminated to avoid unnecessary computational resource consumption, and the target planning scheme is output. In the optimal solution stability condition, the sliding window formula is used to determine whether the fluctuation range of the objective function value (total cost C) of the global optimal solution within a preset number of consecutive iterations (e.g., 50 generations) is less than a preset range value (e.g., 0.1%). This ensures that the solution quality reaches a stable state, and the target planning scheme is output. In the population diversity threshold, when the population diversity is extremely scarce, the premature convergence determination formula is used to determine premature convergence, and the target planning scheme is output.

[0048] For example, the maximum number of iterations for the improved adaptive genetic algorithm can be set to 500 generations. This parameter is set based on the convergence characteristics of the test data and can cover the solution requirements of more than 95% of scenarios.

[0049] In some embodiments, the step of solving the problem under constraints by improving the adaptive genetic algorithm until preset conditions are met, and obtaining the relevant formulas for the target planning schemes corresponding to each sub-region, specifically includes: The fitness function is: ; In the formula, Total cost; For important load sets; Indicates the required power supply time (e.g., 2 hours); Indicates the actual power supply time; This is a penalty coefficient (e.g., 1000 yuan / hour). For fitness.

[0050] The formula for calculating the probability of selection is: ; In the formula, The probability of an individual's choice; F represents the fitness value of each individual in the population. j For any individual (the first) j The fitness of (n) individuals is represented in the summation formula, which represents all individuals.

[0051] The dynamic mutation probability mechanism is as follows: ; ; ; In the formula, This represents the current mutation probability; This represents the average fitness value of the current population. This represents the optimal fitness value for the current population. The number of individuals in the second set; For individual indexes; The formula for calculating the number of individuals that need to mutate in the current generation is: ; In the formula, The number of mutated individuals; This represents the current mutation probability; The number of individuals in the set of individuals to be mutated; The formula for the sliding window is: ; In the formula, For the current algebra; This represents the objective function value corresponding to the current algebra. The preset amplitude value; The preset number of consecutive iterations; The formula for determining precocity is: ; In the formula, This represents the average fitness value of the current population. This represents the optimal fitness value for the current population.

[0052] For easier understanding, please refer to Figure 2 , Figure 2 This is a schematic diagram of the solution process of the improved adaptive genetic algorithm provided in this application. The population representation is initialized by triple hard constraints to generate an initial set of individuals and undergo triple pre-screening. Then, the fitness is calculated and a triple termination decision mechanism is implemented. If the preset conditions are met, the optimal target planning scheme is directly output. If not, a roulette wheel rotation operation is performed to further screen the set of individuals. The screened set of individuals then undergoes sequential crossover, three types of directional mutation operations, and dual-track elite optimization to generate a new set of individuals, i.e., a new population. The new population is then iteratively processed using the above steps.

[0053] It should be noted that after a complete generation of population iteration is completed, a multi-dimensional weighted clustering algorithm will be used to improve the efficiency of path planning. It will comprehensively consider three core elements: the geographical distribution of nodes, traffic control policy constraints, and the urgency of power supply demand, and scientifically divide the service area into multiple collaborative sub-regions.

[0054] Based on the path optimization model, a first set is generated under preset conditions. A second set is obtained by combining fitness and selection probability. This prioritizes high-quality individuals that fit the traffic, demand, and energy storage vehicle data of the sub-regions, while eliminating invalid solutions. The mutation probability is dynamically determined based on the fitness of individuals in the second set, and mutation is performed to obtain a third set. The mutation intensity can be adjusted as needed to explore new solutions or protect high-quality individuals, enhancing adaptability to dynamic constraints under complex road conditions. Local optimization of the third set yields a fourth set, which can further optimize the defects of the individual set, allowing individuals to iterate towards traffic adaptation, power supply reliability, and cost optimization. Through iterative operations until the preset conditions are met, the final target planning scheme adapted to each sub-region is output, effectively reducing the risk of path failure and power outage, and improving the reliability of energy storage vehicle power supply path planning under complex road conditions.

[0055] In some embodiments, planning the power supply path for the energy storage vehicle based on each of the target planning schemes specifically includes: issuing a path navigation instruction to the energy storage vehicle based on the target planning scheme; planning the energy storage vehicle to reach the corresponding sub-area according to the path navigation instruction, and executing a preset standardized grid connection operation procedure to supply power. Specifically, based on the target planning scheme, the central planning platform sends path navigation instructions to the mobile energy storage vehicle through a dedicated communication network. After receiving the path navigation instructions, the energy storage vehicle arrives at the corresponding sub-area and executes the standardized grid connection operation process. The standardized grid connection operation process includes: achieving automatic matching of the grid phase angle through a high-precision phase-locked loop circuit, with the phase error strictly controlled within a preset range (e.g., ±0.5°); adopting gradient power ramp control technology within preset values ​​(e.g., 10-100kW / s) to eliminate grid connection inrush current; real-time monitoring of total harmonic distortion (THD) during operation, maintaining THD within safe limits (e.g., THD < 3%) through a dynamic filtering module; and for critical load nodes such as hospitals and communication base stations, deploying dual-channel metering devices to continuously monitor the actual power supply duration. When the predicted remaining power cannot meet the continuous power supply demand for a preset time (e.g., 2 hours), the "dual-vehicle relay" emergency protocol is automatically triggered, that is, the first vehicle maintains the basic power supply, and the backup vehicle carries a fully charged battery pack to take over, ensuring uninterrupted operation of important loads.

[0056] This approach, by issuing path navigation instructions based on the target planning scheme and controlling the energy storage vehicle to execute standardized grid connection procedures, achieves a closed loop from path planning decision-making to power supply execution. The path navigation instructions ensure that the energy storage vehicle travels along the optimized and reliable path, avoiding blind detours in complex road conditions. The standardized grid connection operation strictly controls power supply parameters to avoid power outages caused by grid connection impacts. This instruction guidance and standardized execution can effectively reduce human error and equipment failure risks during the implementation of the planning scheme, ensure the stable execution of energy storage vehicle power supply in complex road conditions, and improve the reliability of path planning.

[0057] In some embodiments, after planning the power supply path of the energy storage vehicle based on each of the target planning schemes, the method further includes: acquiring traffic congestion data in real time, judging the traffic status based on the traffic congestion data, and obtaining a judgment result; activating a three-level response mechanism according to the judgment result to ensure normal power supply to the energy storage vehicle, wherein the three-level response mechanism includes a primary response stage, an intermediate response stage, and a high-level response stage. The primary response stage controls the energy storage vehicle to automatically switch to a preset parallel branch detour scheme. The intermediate response stage plans for idle energy storage vehicles within a preset range to jointly undertake a preset ratio of load tasks. The high-level response stage controls the energy storage vehicle to complete power transmission in a designated safety island. Specifically, the onboard terminal transmits the energy storage vehicle's location information and battery status parameters in real time, and establishes a data channel with the traffic monitoring center to periodically (e.g., every 2 minutes) acquire traffic congestion data from the entire road network. When the system detects that the increase in travel time on a specific road segment exceeds a preset threshold (e.g., 30%), it immediately activates a three-level response mechanism. In the initial response stage, it automatically switches to a preset parallel branch road detour plan. In the intermediate response stage, it plans standby vehicles within a preset range (e.g., within a 5-kilometer radius) to collaboratively undertake a preset ratio (e.g., 50%) of the load task. In the advanced response stage, it activates mobile charging vehicles to complete power transfer at designated safety islands. In addition, in extreme weather scenarios such as typhoons and heavy rain, the system forcibly activates a safety operation protocol, limiting the maximum vehicle speed to a preset speed (e.g., 30 km / h) and reducing the output power to a preset ratio of the rated value (e.g., 60%), while preheating the grid-connected interface equipment in the target area.

[0058] In this way, by monitoring traffic congestion data in real time and activating a three-level response mechanism during the power supply process, dynamic adaptation to sudden situations in complex road conditions is achieved. When an anomaly is detected, the graded response of primary detour, intermediate coordination, and advanced power transfer can quickly resolve sudden traffic risks and avoid power supply delays or interruptions caused by sudden changes in road conditions. This monitoring and response mechanism makes up for the limitations of static planning schemes, enabling energy storage vehicles to maintain power supply continuity even in complex road condition fluctuations, and significantly improving the planning reliability in emergency scenarios.

[0059] By acquiring real-time traffic data, user electricity demand data, and available energy storage vehicle data for the power outage area, comprehensive and dynamic basic data support is provided for route planning decisions, improving the reliability of route planning decisions from the data source. An improved clustering algorithm is used to divide sub-regions based on traffic data and electricity demand data, achieving deep integration of traffic control characteristics and user distribution characteristics. This makes traffic constraints and user needs in each sub-region more homogeneous and reduces interference from complex road conditions across regions. With the goal of minimizing the total planning cost of sub-regions, an improved adaptive genetic algorithm is used to solve the route optimization model. By introducing traffic control constraints and power supply time gaps, a dual-track evolution of power and traffic is constructed to obtain the target planning scheme for energy storage vehicles to supply power along the power supply path. This can accurately control economic indicators such as vehicle fixed costs and operating costs, and can also force the power supply needs of important loads through the power supply time gap related mechanism, achieving the goals of optimal cost and reliable power supply. This significantly improves the reliability of planning energy storage vehicle power supply paths under complex road traffic conditions.

[0060] See Figure 3 Based on the above method embodiments, corresponding device embodiments are provided; An embodiment of the present invention provides an emergency power supply planning device for a mobile energy storage vehicle, characterized in that it includes a data acquisition module 100, a division module 200, and a planning module 300; The acquisition module 100 is used to acquire in real time traffic data of the power outage area, user electricity demand data, and energy storage vehicle data of currently available energy storage vehicles; The partitioning module 200 is used to perform cluster analysis on the traffic data and the electricity demand data through an improved clustering algorithm, so as to divide the power outage area into several sub-regions. The planning module 300 is used to input the traffic data, electricity demand data, and energy storage vehicle data corresponding to each sub-region into a preset path optimization model. The model aims to minimize the total planning cost of each sub-region and solves the problem under constraints using an improved adaptive genetic algorithm until the preset conditions are met, thereby obtaining the target planning scheme for each sub-region. Based on the target planning scheme, the power supply path for the energy storage vehicle is planned. The improved adaptive genetic algorithm is obtained by introducing traffic control constraints and power supply time gaps into the traditional genetic algorithm to construct a dual-track evolution of electric and transportation systems.

[0061] This approach, through the acquisition module, acquires real-time traffic data, user electricity demand data, and available energy storage vehicle data for the power outage area, providing comprehensive and dynamic basic data support for route planning decisions and improving the reliability of these decisions from the data source. The partitioning module uses an improved clustering algorithm to perform cluster analysis based on traffic data and electricity demand data to divide the area into sub-regions, achieving deep integration of traffic control characteristics and user distribution characteristics. This makes the traffic constraints and user needs within each sub-region more homogeneous, reducing interference from complex cross-regional road conditions. The planning module aims to minimize the total planning cost of the sub-regions. It combines an improved adaptive genetic algorithm to solve the route optimization model and constructs a dual-track evolution of power and traffic by introducing traffic control constraints and power supply time gaps. This yields a target planning scheme for energy storage vehicles to supply power along the power supply path. This approach can accurately control economic indicators such as vehicle fixed costs and operating costs, and can also forcibly guarantee the power supply needs of important loads through the power supply time gap mechanism, achieving the goals of optimal cost and reliable power supply. This significantly improves the reliability of planning energy storage vehicle power supply paths under complex road traffic conditions.

[0062] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the emergency power supply planning method for a mobile energy storage vehicle provided by any of the above-described method embodiments of the present invention.

[0063] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0064] Based on the above-described embodiment of an emergency power supply planning method for a mobile energy storage vehicle, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements an emergency power supply planning method for a mobile energy storage vehicle according to any embodiment of the present invention.

[0065] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0066] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0067] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0068] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the emergency power supply planning method for a mobile energy storage vehicle as described in any of the above-described method embodiments of the present invention.

[0069] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0070] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An emergency power supply planning method for a mobile energy storage vehicle, characterized by, The application relates to a power supply path planning method for a mobile energy storage vehicle. Real-time traffic data of a power outage area, user power demand data and mobile energy storage vehicle data are acquired; The traffic data and the power demand data are analyzed by using an improved clustering algorithm to divide the power outage area into a plurality of subareas; The traffic data, the power demand data and the mobile energy storage vehicle data corresponding to each subarea are input into a preset path optimization model, and a target planning scheme corresponding to each subarea is obtained by minimizing the total planning cost of each subarea and solving the model under constraint conditions by using an improved adaptive genetic algorithm until a preset condition is met, and the power supply path of the mobile energy storage vehicle is planned based on the target planning scheme.

2. The emergency power supply planning method of the mobile energy storage vehicle according to claim 1, characterized in that, The traffic data includes traffic restriction time period data and traffic restriction vehicle data, the power demand data includes address data, and the traffic data and the power demand data are analyzed by using an improved clustering algorithm to divide the power outage area into a plurality of subareas, specifically including: The traffic restriction time period data, the traffic restriction vehicle data and the address data are weighted and distributed according to a preset proportion to obtain a weighted feature vector; The power outage area is analyzed by using a clustering algorithm according to the weighted feature vector until a preset condition is met to obtain a plurality of subareas, wherein the clustering algorithm is a k-means clustering algorithm.

3. The emergency power supply planning method of the mobile energy storage vehicle according to claim 1, characterized in that, Before the traffic data, the power demand data and the mobile energy storage vehicle data corresponding to each subarea are input into a preset path optimization model, a target function with a lowest total cost and constraint conditions are established according to the traffic data, the power demand data, the mobile energy storage vehicle data and a preset penalty coefficient corresponding to each subarea, wherein the constraint conditions include service completeness constraint, resource coordination constraint and space-time coordination constraint.

4. The emergency power supply planning method of the mobile energy storage vehicle according to claim 3, characterized in that, The target function is constructed by specifically including: A vehicle fixed cost is calculated according to a unit vehicle cost and a preset decision variable, a vehicle driving cost is calculated according to a transportation distance, a unit driving cost and the decision variable, an overtime penalty cost is calculated according to a unit penalty cost, a vehicle arrival time at a departure point, an interval time, a time period number and a maximum service time of a single mobile energy storage vehicle, and a power supply reliability penalty cost is calculated according to an important load set, an actual power supply time, a preset required power supply time and the preset penalty coefficient; The target function is obtained according to the vehicle fixed cost, the vehicle driving cost, the overtime penalty cost and the power supply reliability penalty cost.

5. The emergency power supply planning method of the mobile energy storage vehicle according to claim 1, characterized in that, The target planning scheme corresponding to each subarea is obtained by solving the model under constraint conditions by using an improved adaptive genetic algorithm until a preset condition is met, specifically including: Based on the path optimization model, a first individual set is randomly generated according to a preset generation condition, the fitness of each individual in the first individual set is calculated respectively, a plurality of selection probabilities are determined based on the fitness, and the first individual set is screened based on the selection probabilities to obtain a second individual set; Based on the fitness corresponding to each individual in the second individual set, a plurality of mutation probabilities are determined, the second individual set is processed by mutation according to the mutation probabilities to obtain a third individual set, and the third individual set is subjected to a local optimization operation to obtain a fourth individual set, and the target planning scheme is output after the preset condition is met.

6. The emergency power supply planning method of the mobile energy storage vehicle according to claim 1, characterized in that, The path of the energy storage vehicle is planned based on the target planning scheme, specifically including: The path navigation instruction is sent to the energy storage vehicle based on the target planning scheme; The energy storage vehicle reaches the corresponding sub-area according to the path navigation instruction, and performs a preset standardized grid connection operation process to supply power.

7. The method of claim 1, wherein the method further comprises: After the path of the energy storage vehicle is planned based on the target planning scheme, the following steps are further included: Real-time traffic congestion data is obtained, and the traffic state is determined based on the traffic congestion data to obtain a determination result; According to the determination result, a three-level response mechanism is activated to ensure normal power supply of the energy storage vehicle, wherein the three-level response mechanism includes a primary response stage, an intermediate response stage and a high-level response stage, the primary response stage controls the energy storage vehicle to automatically switch to a preset parallel branch bypass scheme, the intermediate response stage plans idle energy storage vehicles in a preset range to cooperatively bear a preset proportion of load tasks, and the high-level response stage controls the energy storage vehicle to complete power transmission at a designated safety island.

8. An emergency power supply planning device for a mobile energy storage vehicle, characterized by, It includes a collection module, a division module and a planning module; The collection module is used to acquire traffic data of a power outage area, user power demand data and energy storage vehicle data of currently available energy storage vehicles in real time; The division module is used to perform clustering analysis on the traffic data and the power demand data by improving a clustering algorithm, so as to divide the power outage area into a plurality of sub-areas; The planning module is used to input the traffic data, the power demand data and the energy storage vehicle data corresponding to each sub-area into a preset path optimization model, to minimize the planning total cost of each sub-area as an objective, and to solve under constraint conditions by improving an adaptive genetic algorithm until a preset condition is met, to obtain a target planning scheme corresponding to each sub-area, and to plan the power supply path of the energy storage vehicle based on the target planning scheme, wherein the adaptive genetic algorithm is obtained by introducing traffic control constraints and power supply time gaps into a traditional genetic algorithm to construct an electric power and traffic double-track evolution.

9. A terminal device, comprising: It includes: a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operation of the emergency power supply planning method of the mobile energy storage vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored computer program, wherein the computer readable storage medium controls a device or apparatus where the computer readable storage medium is located to perform the emergency power supply planning method of the mobile energy storage vehicle according to any one of claims 1 to 7 when the computer program is running.

Images