Deployment method, device and computer equipment of all-vanadium liquid flow battery energy storage system

Abstract

The present application relates to the field of battery energy storage technology, and discloses a deployment method, device, and computer equipment for an all-vanadium liquid flow battery energy storage system. It includes obtaining the energy storage capacity gap data contained in multiple time periods in the target area and performing frequency amplitude statistics to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and then judging the uniform distribution of high-risk time periods and dividing multiple honeycomb units that can be used as candidate deployment locations for the all-vanadium liquid flow battery energy storage system. Taking into account the energy storage capacity gap amplitude, duration, and spatial correlation between units, the energy storage assessment demand data of each honeycomb unit is calculated, and the target deployment plan of the all-vanadium liquid flow battery energy storage system is further generated. At this point, a deployment method for an all-vanadium liquid flow battery energy storage system is realized that can accurately analyze various energy storage requirements and conduct a comprehensive evaluation to determine the best deployment plan.

Description

Technical Field

[0001] The present application relates to the field of battery energy storage technology, and in particular to a deployment method, device and computer equipment for an all-vanadium liquid flow battery energy storage system. Background Art

[0002] As people pay more and more attention to environmental protection and energy utilization, it has become a trend to use renewable energy to replace some traditional coal-fired power generation. However, due to the instability and unpredictability of renewable energy generation (such as solar and wind energy), the performance requirements for energy storage equipment are getting higher and higher. Especially in specific power grid areas, voltage instability may be encountered, which requires energy storage systems to adjust to ensure the stability of power supply. In this case, there is also a potential contradiction between the capacity demand of the energy storage system and the frequency of undervoltage events, that is, the reduction in the frequency of undervoltage events may reduce the system's sensitivity to the risk of battery capacity demand, resulting in an unexpected increase in battery capacity demand. Especially in the application of all-vanadium liquid flow battery energy storage systems, if the configuration is improper, it may interfere with the system's judgment of battery capacity demand, resulting in abnormal fluctuations in battery capacity demand. In the related art, the deployment method of all-vanadium liquid flow battery energy storage systems is not perfect enough, and it is impossible to accurately determine the optimal deployment plan for all-vanadium liquid flow battery energy storage systems. Summary of the invention

[0003] This application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, this application proposes a deployment method, device and computer equipment for an all-vanadium liquid flow battery energy storage system. The main technical solutions adopted in this application include:

[0004] In a first aspect, an embodiment of the present application provides a deployment method of an all-vanadium liquid flow battery energy storage system, the method comprising:

[0005] Obtain the energy storage capacity gap data of the target area; wherein the duration corresponding to the energy storage capacity gap data is divided into multiple time periods; perform frequency and amplitude statistics based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap situation in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics; if the uniform distribution indicates that the high-risk time period is unevenly distributed, divide the target area into multiple honeycomb units; wherein each honeycomb unit is regarded as a candidate deployment location for the all-vanadium liquid flow battery energy storage system; construct an energy storage demand feature matrix corresponding to the target area based on the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and perform correlation analysis based on the energy storage demand feature matrix to obtain spatial correlation data between candidate deployment locations; perform weighted processing based on the energy storage capacity gap amplitude, capacity gap duration and spatial correlation data of the candidate deployment location to obtain the energy storage assessment demand data of the candidate deployment location; generate a target deployment plan for the all-vanadium liquid flow battery energy storage system based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment location; wherein the deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery.

[0006] In a second aspect, an embodiment of the present application provides a deployment device for an all-vanadium liquid flow battery energy storage system, the device comprising: a gap data acquisition module, used to acquire energy storage capacity gap data of a target area; wherein the duration corresponding to the energy storage capacity gap data is divided into a plurality of time periods; a distribution determination module, used to perform frequency and amplitude statistics based on the energy storage capacity gap data, obtain the time distribution characteristics of the energy storage capacity gap in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics; a honeycomb unit division module, used to divide the target area into a plurality of honeycomb units when the uniform distribution indicates that the high-risk time period is unevenly distributed; wherein each honeycomb unit is regarded as a candidate deployment location of the all-vanadium liquid flow battery energy storage system; and related data An acquisition module is used to construct an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and perform correlation analysis based on the energy storage demand characteristic matrix to obtain spatial correlation data between candidate deployment locations; an energy storage evaluation module is used to perform weighted processing according to the energy storage capacity gap amplitude, capacity gap duration and spatial correlation data of the candidate deployment locations to obtain energy storage evaluation demand data of the candidate deployment locations; a deployment plan generation module is used to generate a target deployment plan for the all-vanadium liquid flow battery energy storage system according to the technical parameters of the all-vanadium liquid flow battery and the energy storage evaluation demand data of the candidate deployment locations; wherein the deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery.

[0007] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0008] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.

[0009] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the steps of any of the above methods when executed by a processor.

[0010] In the above embodiment, first, the energy storage capacity gap data contained in multiple time periods of the target area is obtained, and secondly, the frequency amplitude statistics are performed based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and the uniform distribution of the high-risk time period is judged based on the time distribution characteristics. If the uniform distribution indicates that the high-risk time period is unevenly distributed, multiple honeycomb units that can be used as candidate deployment locations for the all-vanadium liquid flow battery energy storage system are divided, and the energy storage assessment demand data of each honeycomb unit is calculated while comprehensively considering the energy storage capacity gap amplitude, duration, and spatial correlation between units. Finally, the target deployment plan of the all-vanadium liquid flow battery energy storage system is generated based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment locations. At this point, a deployment method for the all-vanadium liquid flow battery energy storage system is realized that can accurately analyze various energy storage requirements and conduct a comprehensive evaluation to determine the best deployment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 A flowchart of a deployment method of an all-vanadium liquid flow battery energy storage system provided according to an embodiment of the present application;

[0013] Figure 2 A flowchart generated for a target deployment solution of an all-vanadium liquid flow battery energy storage system provided according to an embodiment of the present application;

[0014] Figure 3 A flowchart of a method for constructing a multi-objective energy storage system deployment optimization model according to an embodiment of the present application;

[0015] Figure 4 A flowchart of a method for obtaining energy storage capacity gap data provided according to an embodiment of the present application;

[0016] Figure 5 A flowchart of a method for determining a uniform distribution of high-risk time periods according to an embodiment of the present application;

[0017] Figure 6 A structural block diagram of a deployment device for an all-vanadium liquid flow battery energy storage system provided according to an embodiment of the present application;

[0018] Figure 7 The figure is a diagram of the internal structure of a computer device provided according to one embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0020] As people pay more and more attention to environmental protection and energy utilization, it has become a trend to use renewable energy to replace some traditional coal-fired power generation. However, due to the instability and unpredictability of renewable energy generation (such as solar and wind power), the performance requirements for energy storage equipment are getting higher and higher. Especially in certain power grid areas, voltage instability may occur, which requires energy storage systems to adjust to ensure stable power supply.

[0021] To meet this challenge, people have adopted some energy storage strategies, such as releasing the stored energy in the energy storage system when the power demand peaks (peak shaving), charging the energy storage system when the demand is low (valley filling), or combining the energy storage system with distributed photovoltaic power generation systems to adjust the supply and demand balance of the power grid. However, the relevant energy storage equipment deployment methods are not perfect, and it is impossible to accurately determine the best deployment plan based on actual needs. This requires us to adopt more advanced technologies and methods to optimize the deployment of energy storage equipment to adapt to the volatility of renewable energy generation and ensure the stable operation of the power grid.

[0022] In this case, a deployment strategy based on distributed energy storage devices can be adopted, but there is still a subtle and complex technical contradiction, the potential conflict between the frequency of undervoltage events and the battery capacity demand. The essence of this contradiction lies in the trade-off between system stability and flexibility. It requires us to reduce the frequency of undervoltage events to enhance system stability while avoiding excessive sacrifice of the system's ability to respond quickly to short-term power fluctuations, and vice versa. In other words, when the system strives to reduce the occurrence of undervoltage events, it may accidentally reduce the sensitivity to battery capacity demand, which in turn causes the battery capacity demand to rise unexpectedly. Therefore, in the pursuit of system stability, it is also necessary to carefully handle the delicate balance between flexibility. Especially when introducing new energy storage systems such as all-vanadium liquid flow batteries. In theory, these devices should enhance the system's regulation capabilities and flexibility, but if they are not configured properly, they may become a hidden danger to system stability, and even distort the system's true judgment of battery capacity demand, leading to abnormal fluctuations in demand. The special electrochemical characteristics and regulation capabilities of all-vanadium liquid flow batteries, although they bring potential advantages to the system, may also pose challenges to voltage stability if they lack effective management and optimization.

[0023] According to an embodiment of the present application, an embodiment of a deployment method of an all-vanadium liquid flow battery energy storage system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] In this embodiment, a deployment method of an all-vanadium liquid flow battery energy storage system is provided. Figure 1 As shown, the method comprises the following steps:

[0025] S110. Obtain energy storage capacity gap data of the target area.

[0026] Among them, the duration corresponding to the energy storage capacity gap data is divided into multiple time periods. The target area may refer to the relevant area where the all-vanadium liquid flow battery energy storage device needs to be deployed. Exemplarily, this area may be a city, a county, a community or the service scope of any power supply and monitoring system. The energy storage capacity gap data may refer to the difference data between the energy that the energy storage system needs to supplement and the actual available energy within a specific time period in a specific target area. Exemplarily, the energy storage capacity gap data may be feature vector data containing information such as the duration, voltage deviation amplitude and occurrence frequency of the undervoltage event that occurs in the target area. It can be understood that an undervoltage event refers to a situation where the voltage in the power system deviates from the normal range. Exemplarily, an undervoltage event refers to a voltage reduction event that may be caused by an increase in grid load, insufficient power supply capacity, line fault or other system problems; it may also be a voltage increase event caused by a line fault or other system problems; it may also be a voltage rapid fluctuation event caused by a rapid rise or fall in voltage in a short period of time.

[0027] Specifically, the voltage undervoltage event records and load change data of a specified time period in the target area can be extracted from the power monitoring system database, and the data can be processed to obtain the energy storage capacity gap data. Exemplarily, the voltage undervoltage event records and load change data in the target area from January to December 2023 can be obtained from the power monitoring system database, and outlier removal, smoothing cleaning and unified format processing can be performed. If the duration corresponding to the voltage undervoltage event record is divided into hours, a normalized voltage undervoltage event sequence data set containing all hourly data points corresponding to all voltage undervoltage events from January to December 2023 can be obtained. Furthermore, features are extracted from each segment of the normalized voltage undervoltage event sequence to obtain a voltage undervoltage feature vector, which includes the voltage undervoltage duration (minutes), voltage deviation amplitude (nominal voltage percentage) and occurrence frequency (times / day). Finally, the obtained voltage undervoltage feature vector is used as the energy storage capacity gap data. For example, the energy storage capacity gap data, i.e., the extracted voltage undervoltage feature vector, is in the form of [30, 15%, 2], indicating that during the period, the voltage undervoltage event lasted for 30 minutes at a time, the voltage dropped by 15%, and there were two voltage undervoltage events on the same day.

[0028] S120. Perform frequency and amplitude statistics based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics.

[0029] Among them, the time distribution feature can be characteristic data that describes the statistical characteristics of the capacity gap faced by the energy storage system in different time periods, including intraday volatility, peak-to-valley ratio and periodic indicators. For example, the energy storage capacity gap data can be time-divided by hour, and the frequency and average amplitude of the energy storage capacity gap in each hour are counted to generate a time series data set containing timestamps, frequencies and average amplitudes, and further extract the time series data describing the voltage shortage information as the time distribution feature. In the context of power system and energy storage management, high-risk time periods can refer to certain specific time periods in a day when the power grid or energy storage system faces higher operating risks due to the voltage deviation from the normal range in the power system. For example, by analyzing historical data and real-time monitoring of the power system, it is found that the load demand of the power grid reaches its peak from 4 to 6 pm and from 10 pm to midnight every day. If the energy storage system of the power grid cannot provide enough energy to make up for the supply and demand gap during these time periods, then these time periods can be marked as high-risk time periods.

[0030] Specifically, Python's Pandas library is used to process data based on the energy storage capacity gap data. The target time period for data processing is set, and the cross-day data is processed in a 24-hour cycle. The energy storage capacity gap data is divided according to the target time period, and the frequency and average amplitude of the energy storage capacity gap in each time period are statistically obtained to generate a time series data set containing timestamps, frequencies and average amplitudes. Further, the sliding window method is used to extract features in the time series data set to obtain time distribution features. Optionally, before generating the time series data set, the box plot method can also be used to identify outliers and remove abnormal data. Further, based on the time distribution features, the K-means algorithm in the Scikit-learn library is used for clustering processing to identify high-risk time periods. By calculating the distribution coefficient of variation of the high-risk time period in the target time period, it is determined whether the value of the coefficient of variation CV is greater than the preset threshold and then whether the high-risk time period is evenly distributed, and finally the uniform distribution of the high-risk time period is obtained. Optionally, a 5-fold cross validation can be performed on the identified high-risk time period to confirm the stability of the identification result.

[0031] S130: If the uniform distribution indicates that the high-risk time period is unevenly distributed, the target area is divided into a plurality of honeycomb units.

[0032] Among them, each honeycomb unit is regarded as a candidate deployment location for the all-vanadium liquid flow battery energy storage system. Specifically, according to the geographic information and power load distribution of the target area, the area data of each honeycomb unit is pre-set, and the target area is divided into several honeycombs using the H3 geospatial indexing system to obtain the honeycomb unit geographic information data set of the target area, i.e., the honeycomb unit map. At the same time, the grid topology information is integrated, and the substation location and the main transmission line are superimposed on the honeycomb unit geographic information data set containing all honeycombs to obtain multiple honeycombs.

[0033] S140. Construct an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and perform correlation analysis based on the energy storage demand characteristic matrix to obtain spatial correlation data between the candidate deployment locations.

[0034] Among them, the energy storage capacity gap amplitude may refer to the data of the voltage deviation amplitude of the voltage shortage event in the target area included in the energy storage capacity gap data, and the capacity gap duration may refer to the data of the duration of the voltage shortage event in the target area included in the energy storage capacity gap data. The energy storage demand feature matrix may be a feature data matrix used to describe the energy storage capacity gap amplitude and capacity gap duration of each honeycomb unit in the target area during the high-risk time period, and may include information such as the duration of the voltage shortage event, the amplitude of the voltage deviation from the normal level, the number of voltage shortage events in a specific time period, and the load changes during the high-risk time period. Exemplarily, each row of the energy storage demand feature matrix may represent a honeycomb unit, and each column may represent a specific energy storage demand feature (such as the energy storage capacity gap amplitude or the capacity gap duration, etc.). The candidate deployment location may refer to a specific geographical location in the power grid that is considered for installing an energy storage system. The spatial correlation data between the candidate deployment locations may be data used to describe whether there is a certain correlation between the energy storage demand characteristics between honeycombs adjacent in geographical space.

[0035] Specifically, the energy storage demand characteristic matrix can be obtained to process and extract the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location of the all-vanadium liquid flow battery energy storage system, so as to determine how much energy storage capacity is needed to maintain the stability of the power grid during these time periods, thereby obtaining the energy storage demand characteristics and generating the energy storage demand characteristic matrix based on the extracted energy storage demand characteristics. Optionally, the energy storage demand characteristics can also be standardized. Furthermore, a correlation analysis is performed based on the standardized energy storage demand characteristic matrix, and the correlation of the energy storage demand characteristics between adjacent units is analyzed by calculating the Moran's I index to obtain the spatial correlation data between the candidate deployment locations.

[0036] S150: Perform weighted processing on the energy storage capacity gap amplitude, capacity gap duration and space-related data of the candidate deployment location to obtain energy storage assessment demand data of the candidate deployment location.

[0037] Among them, the energy storage assessment demand data of the candidate deployment location can be the assessment demand data used to describe the candidate deployment location of the all-vanadium liquid flow battery energy storage system in the target area, that is, the duration of the voltage undervoltage event of each honeycomb unit in the high-risk time period, the amplitude of the voltage deviation from the normal level, the number of occurrences of the voltage undervoltage event in a specific time period, and the load change in the high-risk time period. Exemplarily, each candidate deployment location of the all-vanadium liquid flow battery energy storage system can be evaluated and scored, and the energy storage assessment demand score obtained can be used as the energy storage assessment demand data of the candidate deployment location of the all-vanadium liquid flow battery energy storage system. Exemplarily, the NSGA-II multi-objective optimization algorithm can be used to comprehensively consider the energy storage capacity gap amplitude, duration and spatial correlation of the candidate deployment location, and weighted processing can be performed based on the energy storage capacity gap amplitude, capacity gap duration and spatial correlation data to calculate the energy storage demand score of each honeycomb unit, so as to obtain the energy storage assessment demand data of each candidate deployment location. Optionally, based on the energy storage demand score of each honeycomb unit, the K-means clustering algorithm can also be used to group the honeycomb units, and mark the honeycomb units with the highest scores as the priority candidate deployment locations for the all-vanadium liquid flow battery energy storage system. Furthermore, for each priority candidate deployment location, based on its energy storage demand score and the uniform distribution of high-risk time periods, a linear regression model is used to estimate its specific energy storage capacity demand, and finally a list of candidate all-vanadium liquid flow battery energy storage system deployment locations and corresponding energy storage demand assessment results are obtained, that is, the energy storage assessment demand data of the candidate deployment locations are obtained.

[0038] S160. Generate a target deployment plan for the all-vanadium liquid flow battery energy storage system based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment locations.

[0039] Among them, the deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery. The technical parameters of the all-vanadium liquid flow battery are used to describe the various physical and chemical properties that affect the performance and cost of the all-vanadium liquid flow battery energy storage system. Exemplarily, the technical parameters of the all-vanadium liquid flow battery may include the energy value that the battery can store per unit volume or weight, the concentration and composition of vanadium ions in the electrolyte, the membrane used to separate the positive and negative electrolytes in the battery, the energy conversion efficiency of the battery during charging and discharging, the number of charge and discharge cycles the battery can undergo, and the total energy storage capacity of the battery. The target deployment plan of the all-vanadium liquid flow battery energy storage system may refer to the optimal deployment plan of the all-vanadium liquid flow battery energy storage system obtained by comprehensively considering various information.

[0040] Specifically, the target deployment plan of the all-vanadium liquid flow battery energy storage system can be obtained by using a pre-established multi-objective energy storage system deployment optimization model. According to the technical parameters and energy storage requirements, based on the pre-established multi-objective energy storage system deployment optimization model, set parameters including objective functions (such as minimizing costs and maximizing efficiency) and constraints (such as geographical location, capacity scale, efficiency and life requirements). Furthermore, using the optimization algorithm, the optimal solution is searched through an iterative process to obtain the target deployment plan of the all-vanadium liquid flow battery energy storage system. For example, taking the deployment of a 100MWh all-vanadium liquid flow battery energy storage system as an example, when constructing the mathematical model, the decision variables is the energy density (range 20-40Wh / L), is the electrolyte concentration (1.6-2.0M), is the membrane material type (1-5 represents different materials). Objective function represents the capacity cost (ten thousand yuan), Represents the annual operating cost (10,000 yuan). Among the constraints, the geographical location is limited to latitude 30° to 35° and longitude 110° to 115°; capacity scale 80-120MWh; charging and discharging efficiency ≥ 75%; cycle life ≥ 10,000 times. Use the NSGA-II algorithm to solve, with a population size of 100, a crossover rate of 0.8, a mutation rate of 0.1, and 1,000 iterations. Randomly generate a preliminary deployment plan for the all-vanadium liquid flow battery energy storage system, such as [30,1.8,3]. After selection, crossover and mutation operations, 500 valid solutions are obtained. Constraint verification is performed and 80 solutions that do not meet the conditions are eliminated. Use the crowding distance sorting method to screen out 100 non-dominated solutions. Set weights =0.6, =0.4, and the comprehensive score is calculated. Finally, the optimal solution [35,1.9,4] with a corresponding system capacity cost of 2.67 billion yuan and an annual operating cost of 53.4 million yuan is obtained, indicating an energy density of 35Wh / L, an electrolyte concentration of 1.9M, and the selection of the fourth membrane material. The optimal solution [35,1.9,4] is used as the target deployment plan for the all-vanadium liquid flow battery energy storage system.

[0041] In the above implementation, first, the energy storage capacity gap data contained in multiple time periods in the target area is obtained, and secondly, the frequency and amplitude statistics are performed based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and the uniform distribution of the high-risk time period is judged based on the time distribution characteristics. If the uniform distribution indicates that the high-risk time period is unevenly distributed, a plurality of honeycomb units that can be used as candidate deployment locations for the all-vanadium liquid flow battery energy storage system are divided, and the energy storage assessment demand data of each honeycomb unit is calculated while comprehensively considering the energy storage capacity gap amplitude, duration and spatial correlation between units. Finally, the target deployment plan of the all-vanadium liquid flow battery energy storage system is generated based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment locations. At this point, a deployment method for the all-vanadium liquid flow battery energy storage system is realized that can accurately analyze various energy storage requirements and conduct a comprehensive evaluation to determine the best deployment plan.

[0042] In some embodiments, the technical parameters include energy density, electrolyte type, and membrane material. The target deployment plan of the all-vanadium liquid flow battery energy storage system is generated based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment location. Please refer to the attached Figure 2 ,include:

[0043] S210. Construct a multi-objective energy storage system deployment optimization model based on the energy density, electrolyte type and membrane material of the all-vanadium liquid flow battery.

[0044] Among them, the objective function includes minimizing the capacity and operating cost of the all-vanadium liquid flow battery energy storage system, and the constraints include the upper and lower limits of the geographical location, capacity scale, energy density, charge and discharge efficiency and cycle life of the all-vanadium liquid flow battery energy storage system. The energy density of the all-vanadium liquid flow battery can refer to the energy value that can be stored in the battery per unit volume or weight. The electrolyte type of the all-vanadium liquid flow battery can refer to the concentration and composition of vanadium ions in the electrolyte. The membrane material of the all-vanadium liquid flow battery can refer to the membrane used to separate the positive and negative electrolytes in the battery. The multi-objective energy storage system deployment optimization model can be a pre-established model for solving the target deployment plan of the all-vanadium liquid flow battery energy storage system. Exemplarily, a multi-objective optimization model including objective functions (such as minimizing costs and maximizing efficiency) and constraints (such as geographical location, capacity scale, efficiency and life requirements) can be regarded as a multi-objective energy storage system deployment optimization model.

[0045] Specifically, a multi-objective energy storage system deployment optimization model is constructed. A mathematical model can be established based on the technical parameters of the all-vanadium liquid flow battery and the training energy storage evaluation demand data of the candidate deployment locations. The energy density, electrolyte type and membrane material are used as decision variables to construct the objective function and ,in represents the capacity cost, represents the operating cost, represents the decision variable. Constraints include geographical location restrictions , the upper and lower limits of capacity scale , energy density range , charge and discharge efficiency threshold , cycle life requirements The constraint parameters can be obtained from the historical operation data of the target area and the equipment specifications of the all-vanadium liquid flow battery energy storage equipment. So far, a multi-objective energy storage system deployment optimization model has been constructed based on the energy density, electrolyte type and membrane material of the all-vanadium liquid flow battery.

[0046] Optionally, after constructing the multi-objective energy storage system deployment optimization model, further, real number coding can be used to represent decision variables and the NSGA-II algorithm can be used to generate a preliminary deployment plan for the all-vanadium liquid flow battery energy storage system and perform fitness evaluation, selection, crossover and mutation operations. Constraint verification is performed on the optimization results to eliminate solutions that do not meet the constraints. Pareto frontier analysis is performed on the verified results, and the crowding distance sorting method is used to screen out the non-dominated solution set. The comprehensive score of each solution is calculated. ,in and is the weight coefficient. The solution with the highest comprehensive score is selected as the optimal deployment solution, and the optimal configuration parameters of the all-vanadium liquid flow battery energy storage system are output, including energy density, electrolyte concentration and membrane material type.

[0047] S220. Use a particle swarm optimization algorithm to solve a multi-objective energy storage system deployment optimization model and obtain a target deployment plan.

[0048] Among them, the particle swarm optimization algorithm (PSO) is an optimization algorithm based on swarm intelligence. Specifically, the particle swarm optimization algorithm can be used to search for the optimal deployment plan of the all-vanadium liquid flow battery energy storage system for constraint verification, and the verified solution can be analyzed by Pareto frontier, and the crowding distance sorting method or other methods can be used to screen out the non-dominated solution set, calculate the comprehensive score of each solution, consider different weight coefficients, and finally select the solution with the highest comprehensive score as the target deployment plan of the all-vanadium liquid flow battery energy storage system.

[0049] For example, taking the deployment of a distributed all-vanadium liquid flow battery energy storage system in a certain city as an example, each particle is represented as a deployment plan for 10 subsystems, and each subsystem is represented by [x, y, c, s], where x and y are longitude and latitude coordinates (accurate to 0.0001 degrees), c is the capacity (0-10MWh), and s is the charging and discharging strategy parameter (a floating point number between 0 and 1). Set the particle swarm size to 100, the maximum number of iterations to 1000, and the learning factor , the initial value of the inertia weight w is 0.9, and it decreases by 0.0005 each iteration. Initialize the particle swarm and randomly generate particles that meet the constraints, including geographical boundaries (longitude 118.5°-119.5°, latitude 31.5°-32.5°), total capacity limit (50MWh), and minimum spacing requirement (2 kilometers). Calculate the fitness value of each particle, the fitness function ,in is the total cost per unit in millions of dollars, is the system efficiency between 0 and 1, is a reliability index between 0 and 1. When updating the particle position, the V-max method is used to limit the speed to the range of [-0.1, 0.1]. For positions beyond the search space, periodic boundary conditions are used for mapping. For example, longitude 119.6° will be mapped to 118.6°. In each iteration, non-dominated sorting and congestion calculations are performed to retain the solutions on the Pareto front. The algorithm terminates when 1000 iterations are reached or the improvement of the optimal solution is less than 0.1% for 50 consecutive iterations. The optimal deployment plan for the all-vanadium liquid flow battery energy storage system finally output includes the specific geographical location, capacity scale and charging and discharging strategy parameters of the 10 sub-all-vanadium liquid flow battery energy storage systems.

[0050] In the above implementation, a target deployment plan for the all-vanadium liquid flow battery energy storage system is generated based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment locations. The particle swarm optimization algorithm is used to solve the multi-objective energy storage system deployment optimization model. The solution with the highest comprehensive score is used as the optimal deployment plan to ultimately obtain a target deployment plan for the all-vanadium liquid flow battery energy storage system that comprehensively considers factors such as cost, efficiency, reliability and geographical location.

[0051] In some embodiments, the objective function includes a capacity cost objective function and an operating cost objective function. According to the energy density, electrolyte type and membrane material of the all-vanadium liquid flow battery, a multi-objective energy storage system deployment optimization model is constructed. Please refer to the attached Figure 3 ,include:

[0052] S310. Taking energy density, electrolyte type and membrane material as decision variables, construct a capacity cost objective function and an operation cost objective function.

[0053] Among them, the electrolyte type and membrane material indirectly affect the objective function by affecting the system efficiency and life. In the multi-objective energy storage system deployment optimization model for the deployment of the all-vanadium liquid flow battery energy storage system, the decision variables can be parameters used to describe the system configuration, that is, the values ​​that need to be determined during the optimization process. Exemplarily, energy density, electrolyte type and membrane material can be used as decision variables. The capacity cost objective function can be a function used to calculate all costs including materials, manufacturing and installation during the initial construction of the all-vanadium liquid flow battery energy storage system. Exemplarily, As the capacity cost objective function, Representation and decision variables The operating cost objective function can be a function used to calculate all costs of the all-vanadium liquid flow battery energy storage system during operation, including maintenance, replacement of components, and energy loss. For example, As the capacity cost objective function, Representation and decision variables Relevant unit operating costs.

[0054] S320. Set constraint conditions using historical operation data and equipment specification data.

[0055] Among them, the historical operation data may be data that reflects the performance and behavior of the all-vanadium liquid flow battery energy storage system during actual operation. Exemplarily, the historical operation data may include performance parameters, fault records, maintenance records, and efficiency changes of the all-vanadium liquid flow battery energy storage system. Equipment specification data may refer to data provided by the manufacturer on the technical parameters and performance indicators of the all-vanadium liquid flow battery energy storage equipment. Constraints may be a series of rules or restrictions used to limit the range of values ​​of decision variables. Exemplarily, constraints may include geographic location constraints that reflect the geographical range in which the system is deployed; they may also include capacity scale conditions that reflect system capacity limitations; they may also include energy density conditions that reflect the technical specification limitations of the all-vanadium liquid flow battery; they may also include conditions on charge and discharge efficiency and constraints on the expected cycle life of the battery.

[0056] S330, real number encoding is performed on the decision variables, and a fitness function is constructed based on the capacity cost objective function and the operation cost objective function to perform fitness evaluation, selection, crossover and mutation operations, and a crowding distance sorting method is used to screen out a non-dominated solution set.

[0057] Among them, real number coding can refer to the data representation of measuring decision variables in the form of actual numerical coding. For example, the decision variables can include energy density (Range 20-40Wh / L), electrolyte concentration (1.6-2.0M) and membrane material type (1-5 each represent a different type of membrane material). Furthermore, a fitness function is constructed based on the capacity cost objective function and the operating cost objective function, and is used as a standard for evaluating each individual in the multi-objective energy storage system deployment optimization model, that is, each candidate deployment location. The NSGA-II algorithm is used to generate a preliminary deployment plan for the all-vanadium liquid flow battery energy storage system. Furthermore, a genetic algorithm operation is used to perform fitness evaluation, selection, crossover and mutation operations on the preliminary deployment plan of the all-vanadium liquid flow battery energy storage system, and constraint verification is performed on the optimization results. Furthermore, a Pareto frontier analysis is performed on the verified results, that is, the crowding distance sorting method is used to screen out the non-dominated solution set, the solutions are sorted according to the crowding distance, and a certain number of solutions with the largest distance are selected as the final optimal solution set, and as the non-dominated solution set.

[0058] S340. According to the comprehensive score of each solution in the non-dominated solution set, determine the deployment solution with the highest score as the target deployment solution.

[0059] Specifically, the weight coefficient is used to calculate the comprehensive score of each solution, and the deployment scheme with the highest score is determined to be the optimal deployment scheme for the all-vanadium liquid flow battery energy storage system.

[0060] In the above implementation, a better solution is found through selection, crossover and mutation operations, and constraint verification is performed and solutions that do not meet the problem constraints are eliminated. This step ensures that all considered solutions are feasible. Furthermore, using techniques such as the crowding distance sorting method, a non-dominated solution set is screened out from the current population, considering not only the non-dominance of the solution, but also the distribution density of the solution in the objective function space to maintain the diversity of solutions. Finally, in the non-dominated solution set, the solution with the highest comprehensive score is selected as the optimal deployment plan, which provides the best trade-off and minimizes capacity cost and operating cost. Through the above series of steps, the optimal solution can be effectively found from the multi-objective optimization problem to ensure that cost-effectiveness is maximized while meeting all technical, economic and operational constraints, thereby determining the optimal deployment plan for the all-vanadium liquid flow battery energy storage system.

[0061] In some embodiments, the target area is divided into a plurality of cellular units, including: dividing the target area using an H3 geospatial indexing system according to geographic information and power load distribution of the target area to obtain a cellular unit map. According to the power grid topology information of the target area, the substation location and the designated transmission line are superimposed on the cellular unit map to obtain a plurality of cellular units.

[0062] Among them, the H3 geospatial indexing system is a system for efficient geospatial data indexing and querying. By adopting the H3 geospatial indexing system, the geographical location surface of the target area can be divided into a polygonal honeycomb structure, namely a honeycomb unit map, which contains the geographic information data of each honeycomb unit. Exemplarily, the honeycomb unit map generated by the H3 system records and stores the geographic coordinates and boundaries of each unit in detail, and is represented in the form of a data set. The power grid topology information of the target area may refer to information containing the geographic coordinate features of the substation location and the main transmission lines. Specifically, based on the power grid topology information of the target area, the geographic coordinates of the substation and the transmission line can be added to the honeycomb unit map as a data layer. On the map, the locations of the substation and the transmission line will be aligned with the boundaries of the honeycomb unit to show their relative geographical positions. That is, comprehensive honeycomb unit map information containing substations and transmission lines is obtained, from which multiple honeycombs can be obtained.

[0063] In the above implementation, by effectively dividing the target area into multiple honeycomb units and combining the grid topology information and historical power data, the power demand and risk of each unit are analyzed in detail, thereby providing a scientific basis for the deployment of the all-vanadium liquid flow battery energy storage system.

[0064] In some embodiments, before constructing the energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, the method further includes: extracting the historical voltage and load data of each candidate deployment location from the power monitoring system database. Determine the energy storage capacity gap amplitude and capacity gap duration of the candidate deployment location according to the historical voltage and load data of the candidate deployment location.

[0065] Specifically, the voltage undervoltage event records and load change data of each candidate deployment location in a specified time period in the target area can be extracted from the power monitoring system database and used as historical voltage and load data. Further identify high-risk time periods and process and analyze the data, calculate the additional energy storage capacity required for grid operation in a specific time period, identify high-load periods and voltage fluctuations, and simulate and predict in combination with the capabilities of the energy storage system to obtain the magnitude of the energy storage capacity gap at the candidate deployment location. Similarly, determine the length of time the grid needs additional energy storage capacity based on the historical voltage and load data of the candidate deployment location, and obtain the capacity gap duration of the candidate deployment location.

[0066] In the above implementation, the energy storage demand of each candidate deployment location is systematically evaluated to provide a scientific basis for the rational deployment of the energy storage system. This method helps to optimize the operating efficiency of the power grid, improve the economic benefits of energy utilization, and enhance the reliability and stability of the power grid.

[0067] In some embodiments, constructing an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location includes: constructing an energy storage demand matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location. Standardizing the energy storage demand matrix, converting the elements in the energy storage demand matrix into the same dimension, and obtaining the energy storage demand characteristic matrix.

[0068] Specifically, the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location of the all-vanadium liquid flow battery energy storage system are processed and extracted to determine how much energy storage capacity is needed to maintain the stability of the power grid during these time periods, thereby obtaining energy storage demand characteristics and generating an energy storage demand matrix based on the extracted energy storage demand characteristics. Furthermore, the energy storage demand matrix is ​​feature standardized to convert the elements in the energy storage demand matrix into the same dimension. Exemplarily, the Z-score method is used to standardize the energy storage demand matrix, converting the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1, and finally obtaining the energy storage demand feature matrix.

[0069] In the above implementation, the dimensional effects of the various features in the energy storage demand feature matrix (such as the energy storage capacity gap amplitude and duration, etc.) due to different units and magnitudes are eliminated through standardization, so that they can be compared and processed on the same scale. Furthermore, it is ensured that in the subsequent multi-objective optimization and clustering analysis, the energy storage demand characteristics of each honeycomb unit can be processed fairly and accurately, thereby improving the effect and accuracy of clustering.

[0070] In some embodiments, please refer to the attached Figure 4 , obtain the energy storage capacity gap data of the target area, including:

[0071] S410: Acquire time series data of historical undervoltage events and historical load changes in a target area to construct an undervoltage feature vector.

[0072] Among them, historical voltage shortage events may refer to voltage increases, decreases, or fluctuations in the power system where the voltage deviates from the normal range. Specifically, the voltage shortage event records and time series data of historical load changes in a specified time period in the target area can be extracted from the power monitoring system database, and the original data can be cleaned and standardized. The moving average method is used to smooth the data and the linear interpolation method is used to fill the missing values. The timestamp format is unified to generate a standardized voltage shortage event sequence set and load change time series set. Furthermore, feature extraction is performed to obtain a voltage shortage feature vector.

[0073] Exemplarily, the voltage undervoltage event records and load change data in the target area from January to December 2023 can be obtained from the power monitoring system database. If there are abnormal values ​​in the original data, such as the voltage suddenly drops to 0 or the load surges to 10 times the normal value, they are eliminated by setting a threshold. And smoothing and cleaning are performed, and the moving average method of a 5-minute window is applied to the smoothed data to reduce the impact of short-term fluctuations. Optionally, if there is a lack of load data, linear interpolation can be used for filling. Further, unified format processing is performed to unify all timestamps into the format of "2023-01-01 00:00:00". If the duration corresponding to the voltage undervoltage event record is divided into every hour, a normalized voltage undervoltage event sequence data set containing all hourly data points corresponding to all voltage undervoltage events from January to December 2023 can be obtained. Further, features are extracted from each segment of the normalized voltage undervoltage event sequence to obtain a voltage undervoltage feature vector, which includes the voltage undervoltage duration (minutes), voltage deviation amplitude (nominal voltage percentage) and occurrence frequency (times / day). It can be understood that the undervoltage feature vector can also reflect information such as charging and discharging power, state of charge, voltage and current values ​​extracted from the real-time operation data of the all-vanadium liquid flow battery energy storage system.

[0074] S420: Analyze the correlation between the voltage shortage feature vector and the load change time series to obtain the influence rule of the voltage shortage frequency on the historical load change.

[0075] Specifically, further feature extraction is performed based on the undervoltage feature vector to obtain a multidimensional undervoltage feature vector containing key indicators such as undervoltage duration, voltage deviation amplitude, and frequency of occurrence. For example, the multidimensional undervoltage feature vector can be in the form of [30,15%,2], indicating an undervoltage event that lasts for 30 minutes, reduces the voltage by 15%, and occurs twice on the same day. At the same time, based on the load change time series set, the fixed time interval method is used for segmentation, with each hour as a time window, and the average load, maximum load, minimum load, and load change rate within the window are calculated to obtain the load change feature sequence. For example, the load change feature sequence can be in the form of [100,110,90,5%], representing an average load of 100MW, a maximum of 110MW, a minimum of 90MW, and a load increase of 5% within the hour.

[0076] Furthermore, data alignment is performed based on the timestamps of the multidimensional voltage shortage feature vector and the load change feature sequence to ensure that the two sets of data correspond one-to-one in the time dimension. The Pearson correlation coefficient is used to calculate the correlation between the voltage shortage feature vector and the load change feature sequence at different time scales, generate a correlation coefficient matrix, and identify feature combinations and time delay parameters with significant correlation. Based on the results of the correlation analysis, a relationship model between the voltage shortage frequency and load changes is constructed, and a linear regression algorithm is used to quantify the degree of influence of the voltage shortage frequency change on the load curve. The results of the regression model are input into the decision tree algorithm to generate an interpretable rule set, and the rules for the influence of the voltage shortage frequency reduction on the load change are obtained. Exemplarily, a linear regression algorithm is used to establish a relationship model between the voltage shortage frequency and load changes, and the regression equation can be obtained. ,in is the load change rate (% / hour), is the frequency of voltage shortage (times / day). Further, the regression model results are input into the decision tree algorithm to generate an interpretable rule set, and a specific rule of the impact of voltage shortage frequency reduction on load change is obtained, such as "if the voltage shortage frequency is less than 1 time / day, the load change rate increases by 2.5% / hour".

[0077] S430: Evaluate the energy storage capacity gap according to the voltage deficiency feature vector and the impact rule to obtain energy storage capacity gap data of the target area.

[0078] Among them, the energy storage capacity gap data can refer to the difference data between the energy that the energy storage system needs to supplement and the actual available energy within a specific time period in a specific target area. Specifically, the real-time operation data of the all-vanadium liquid flow battery energy storage system, including charging and discharging power, state of charge, voltage and current value information, is extracted from the power management system database through SQL query. At the same time, anomaly detection is performed on it and the triple standard deviation method is used to identify and eliminate outliers. According to the voltage deviation amplitude and duration in the voltage deficiency feature vector, the actual output power and energy of the energy storage system during the voltage deficiency period are calculated. Based on the load change prediction in the impact rule and the charge and discharge efficiency curve of the energy storage system, the theoretical maximum output power and energy of the energy storage system during the voltage deficiency period are calculated. The charge and discharge efficiency curve is obtained by table lookup method, and the corresponding efficiency value is interpolated according to the current state of charge and charge and discharge power. By comparing the difference between the actual output and the theoretical maximum output, the preliminary estimate of the energy storage capacity gap is obtained. Further, the preliminary estimated energy storage capacity gap data is normalized, and the maximum and minimum value normalization method is used to ensure that the capacity gap data of different time periods are comparable. Optionally, the exponential smoothing algorithm can be used to dynamically correct the normalized energy storage capacity gap. Set the smoothing coefficient α to 0.3, give a higher weight to the recent gap data, and give a lower weight to the long-term data, and obtain the corrected energy storage capacity gap amplitude. Finally, the STL (Seasonal and Trend decomposition using Loess) algorithm is used to decompose the corrected energy storage capacity gap amplitude into trend terms, seasonal terms, and residual terms. The characteristic parameters of the trend terms and seasonal terms are extracted to establish a prediction model for the duration of the energy storage capacity gap. The sliding window method is used to update the evaluation results in real time. The window size is set to 24 hours and updated every hour. Output the dynamic evaluation results, that is, the energy storage capacity gap data including the current energy storage capacity gap amplitude and the expected duration.

[0079] In the above implementation, by dynamically evaluating the energy storage capacity gap, the energy storage capacity gap data of the target area is obtained, which can more effectively manage and optimize the energy storage system, improve the stability and economy of the power system, and thus provide a scientific basis for the deployment of the all-vanadium liquid flow battery energy storage system.

[0080] In some implementations, frequency and amplitude statistics are performed based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and the uniform distribution of high-risk time periods is determined based on the time distribution characteristics. Please refer to the attached Figure 5 ,include:

[0081] S510, dividing the energy storage capacity gap data into time segments, counting the frequency and average amplitude of the energy storage capacity gap within a unit time, and generating a gap data time series including a timestamp, frequency, and average amplitude.

[0082] Among them, the gap data time series can be time series data used to describe the insufficient performance of the energy storage system capacity gap in meeting electricity demand at continuous time points. Specifically, Python's Pandas library is used to process data based on the energy storage capacity gap data. The target time period for data processing is set, and the cross-day data is processed in a 24-hour cycle. The energy storage capacity gap data is divided into target time periods, and the frequency and average amplitude of the energy storage capacity gap in each time period are statistically obtained to generate a gap data time series containing timestamps, frequencies, and average amplitudes.

[0083] S520: Apply a sliding window to the gap data time series to obtain the cumulative frequency and average amplitude of the energy storage capacity gap in each window.

[0084] Specifically, the gap data time series is cleaned, and the box plot method is used to identify and remove outliers to ensure data quality. Furthermore, the sliding window method is applied to obtain the cumulative frequency and average amplitude of the energy storage capacity gap in each window. Exemplarily, the window size can be set to 24 hours, with a step size of 1 hour, and the cumulative frequency and average amplitude of the energy storage capacity gap in each window are calculated. Optionally, for the window boundary data, the cyclic filling method is used, that is, the insufficient part is filled with data from adjacent cycles.

[0085] S530: Based on the cumulative frequency and average amplitude of the energy storage capacity gap in each window, generate a time distribution characteristic of the energy storage capacity gap in each time period.

[0086] Among them, the time distribution characteristics can be characteristic data that describe the statistical characteristics of the capacity gap faced by the energy storage system in different time periods, including intraday volatility, peak-to-valley ratio and periodic indicators. Exemplarily, a 24-hour sliding window with a step size of 1 hour can be used to calculate the cumulative frequency and average amplitude within the window to obtain 697 window statistical results. The window boundary data is processed using a cyclic filling method. If the data in the first hour is insufficient, it is supplemented with data from the 25th to 48th hours. Furthermore, time distribution characteristics are extracted, including intraday volatility, peak-to-valley ratio and periodic indicators.

[0087] S540: Classify the time periods according to the time distribution characteristics, generate a list of high-risk time periods, and determine the uniform distribution of the high-risk time periods.

[0088] Specifically, based on the statistical results of the sliding window, the K-means clustering algorithm is used to classify the time periods and generate a list of high-risk time periods. Furthermore, the stability of the identification results of high-risk time periods is ensured by cross-validation. For the identified high-risk time periods, the distribution dispersion coefficient within the cycle is calculated, and the coefficient of variation (CV) is used as a metric for the dispersion coefficient and the uniform distribution of the high-risk time periods is judged. For example, the K-means algorithm in the Scikit-learn library is used for clustering, and the number of cluster centers is set to 3, and convergence is achieved after 50 iterations. The time periods with cumulative frequencies exceeding the 90% quantile (value is 28 times) and average amplitudes exceeding the 90% quantile (value is 15kWh) are marked as high risk, and 78 high-risk time periods are identified. Through 5-fold cross-validation, it is confirmed that the stability of the identification results reaches 95%. The distribution coefficient of variation of the high-risk time period within the 24-hour cycle is calculated, and the CV value is 0.62. Since the CV value is greater than the preset threshold of 0.5, it is determined that the high-risk time periods are unevenly distributed, mainly concentrated in the two time periods of 14:00-18:00 and 22:00-02:00.

[0089] In the above implementation, the energy storage capacity gap data is divided into hours and a time series is generated, which can accurately identify and analyze the energy storage capacity gap situation every hour, including the frequency and average amplitude. This provides data support for a deep understanding of the performance of the energy storage system in different time periods. And the uniform distribution of high-risk time periods is evaluated, which provides an important reference for grid planning and energy storage system design, thereby providing strong data support and decision-making basis for the deployment of all-vanadium liquid flow battery energy storage systems.

[0090] It should be understood that, although the various steps in the above flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowchart may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0091] The present specification also provides a deployment device 600 of an all-vanadium liquid flow battery energy storage system. Figure 6 As shown, it includes: a gap data acquisition module 610, a distribution status determination module 620, a honeycomb unit division module 630, a related data acquisition module 640, an energy storage evaluation module 650 and a deployment plan generation module 660, wherein:

[0092] The gap data acquisition module 610 is used to acquire the energy storage capacity gap data of the target area. The duration corresponding to the energy storage capacity gap data is divided into multiple time periods.

[0093] The distribution determination module 620 is used to perform frequency and amplitude statistics based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics.

[0094] The honeycomb unit division module 630 is used to divide the target area into multiple honeycomb units, where each honeycomb unit is regarded as a candidate deployment location of the all-vanadium liquid flow battery energy storage system.

[0095] The relevant data acquisition module 640 is used to construct an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and perform correlation analysis based on the energy storage demand characteristic matrix to obtain spatial correlation data between candidate deployment locations.

[0096] The energy storage assessment module 650 is used to perform weighted processing according to the energy storage capacity gap amplitude, capacity gap duration and space-related data of the candidate deployment location to obtain energy storage assessment demand data of the candidate deployment location.

[0097] The deployment plan generation module 660 is used to generate a target deployment plan for the all-vanadium liquid flow battery energy storage system based on the technical parameters of the all-vanadium liquid flow battery and the energy storage evaluation demand data of the candidate deployment locations. The deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery.

[0098] In some embodiments, the technical parameters include energy density, electrolyte type and membrane material. The deployment plan generation module 660 is also used to construct a multi-objective energy storage system deployment optimization model based on the energy density, electrolyte type and membrane material of the all-vanadium liquid flow battery. The particle swarm optimization algorithm is used to solve the multi-objective energy storage system deployment optimization model to obtain a target deployment plan.

[0099] In some embodiments, the objective function includes a capacity cost objective function and an operating cost objective function. The deployment plan generation module 660 is also used to construct a capacity cost objective function and an operating cost objective function using energy density, electrolyte type and membrane material as decision variables. Constraints are set using historical operating data and equipment specification data. The decision variables are encoded with real numbers, and a fitness function is constructed based on the capacity cost objective function and the operating cost objective function to perform fitness evaluation, selection, crossover and mutation operations, and a non-dominated solution set is screened out using a crowding distance sorting method. According to the comprehensive score of each solution in the non-dominated solution set, the deployment plan with the highest score is determined as the target deployment plan.

[0100] In some embodiments, the cell division module 630 is further used to divide the target area into a cell map using the H3 geospatial indexing system according to the geographic information and power load distribution of the target area. According to the power grid topology information of the target area, the substation location and the designated transmission line are superimposed on the cell map to obtain multiple cells.

[0101] In some embodiments, a deployment device 600 of an all-vanadium liquid flow battery energy storage system further includes an energy storage demand characteristic matrix determination module, which is used to construct an energy storage demand matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location. The energy storage demand matrix is ​​standardized, and the elements in the energy storage demand matrix are converted into the same dimension to obtain the energy storage demand characteristic matrix.

[0102] In some embodiments, the energy storage demand characteristic matrix determination module is further used to extract historical voltage and load data of each candidate deployment location from the power monitoring system database, and determine the energy storage capacity gap amplitude and capacity gap duration of the candidate deployment location based on the historical voltage and load data of the candidate deployment location.

[0103] In some embodiments, the gap data acquisition module 610 is also used to obtain the time series data of historical voltage shortage events and historical load changes in the target area to construct a voltage shortage feature vector. The correlation between the voltage shortage feature vector and the load change time series is analyzed to obtain the influence rule of the voltage shortage frequency on the historical load change. The energy storage capacity gap is evaluated according to the voltage shortage feature vector and the influence rule to obtain the energy storage capacity gap data of the target area.

[0104] In some embodiments, the gap data acquisition module 610 is also used to divide the energy storage capacity gap data into time segments, count the frequency and average amplitude of the energy storage capacity gap in a unit time, and generate a gap data time series containing timestamps, frequencies, and average amplitudes. A sliding window is applied to the gap data time series to obtain the cumulative frequency and average amplitude of the energy storage capacity gap in each window. Based on the cumulative frequency and average amplitude of the energy storage capacity gap in each window, the time distribution characteristics of the energy storage capacity gap in each time period are generated. The time periods are classified according to the time distribution characteristics, a list of high-risk time periods is generated, and the uniform distribution of the high-risk time periods is determined.

[0105] For the specific definition of a deployment device of an all-vanadium liquid flow battery energy storage system, please refer to the definition of a deployment method of an all-vanadium liquid flow battery energy storage system in the above text, which will not be repeated here. Each module in the deployment device of the above-mentioned all-vanadium liquid flow battery energy storage system can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0106] In this embodiment, a deployment device of an all-vanadium liquid flow battery energy storage system is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0107] The embodiment of the present application also provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a deployment method of an all-vanadium liquid flow battery energy storage system is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0108] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0109] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0110] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0111] The above embodiments illustrate a deployment method, device, equipment and storage medium of an all-vanadium liquid flow battery energy storage system, which can be implemented by a computer chip or entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices. For the convenience of description, the above devices are described in various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same one or more software and / or hardware.

[0112] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0113] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", 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 application. 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.

[0115] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0117] 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, and each embodiment focuses on the differences from other embodiments. Since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0118] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

[0119] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A deployment method of an all-vanadium liquid flow battery energy storage system, characterized in that: The method comprises: Acquire energy storage capacity gap data of the target area; wherein the duration corresponding to the energy storage capacity gap data is divided into multiple time periods; Perform frequency and amplitude statistics based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics; If the uniform distribution indicates that the high-risk time period is unevenly distributed, the target area is divided into a plurality of honeycomb units; wherein each honeycomb unit is regarded as a candidate deployment location of the all-vanadium liquid flow battery energy storage system; Constructing an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and performing correlation analysis based on the energy storage demand characteristic matrix to obtain spatial correlation data between the candidate deployment locations; Performing weighted processing according to the energy storage capacity gap amplitude, capacity gap duration and space-related data of the candidate deployment location to obtain energy storage assessment demand data of the candidate deployment location; A target deployment plan for the all-vanadium liquid flow battery energy storage system is generated based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment locations; wherein the deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery.

2. The method according to claim 1, characterized in that The technical parameters include energy density, electrolyte type and membrane material; the target deployment plan of the all-vanadium liquid flow battery energy storage system is generated according to the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment location, including: According to the energy density, electrolyte type and membrane material of the all-vanadium flow battery, a multi-objective energy storage system deployment optimization model is constructed; wherein the objective function includes minimizing the capacity and operating cost of the all-vanadium flow battery energy storage system, and the constraints include the geographical location, capacity scale, energy density, charge and discharge efficiency and upper and lower limits of the cycle life of the all-vanadium flow battery energy storage system; A particle swarm optimization algorithm is used to solve the multi-objective energy storage system deployment optimization model to obtain the target deployment plan.

3. The method according to claim 2, characterized in that The objective function includes a capacity cost objective function and an operation cost objective function; the multi-objective energy storage system deployment optimization model is constructed according to the energy density, electrolyte type and membrane material of the all-vanadium liquid flow battery, including: The energy density, electrolyte type and membrane material are used as decision variables to construct the capacity cost objective function and the operation cost objective function; wherein the electrolyte type and membrane material indirectly act on the objective function by affecting the system efficiency and lifespan; Using historical operating data and equipment specification data to set the constraints; The decision variables are encoded with real numbers, and a fitness function is constructed based on the capacity cost objective function and the operation cost objective function to perform fitness evaluation, selection, crossover and mutation operations, and a crowding distance sorting method is used to screen out a non-dominated solution set; According to the comprehensive score of each solution in the non-dominated solution set, a deployment solution with the highest score is determined as the target deployment solution.

4. The method according to claim 1, characterized in that: The step of dividing the target area into a plurality of honeycomb units comprises: According to the geographic information and power load distribution of the target area, the target area is divided using the H3 geographic spatial indexing system to obtain a cellular unit map; According to the power grid topology information of the target area, the substation location and the designated transmission line are superimposed on the cellular unit map to obtain the multiple cellular units.

5. The method according to claim 4, characterized in that Before constructing the energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, the method further includes: Extracting historical voltage and load data of each candidate deployment location from a power monitoring system database; The energy storage capacity gap amplitude and capacity gap duration of the candidate deployment location are determined based on the historical voltage and load data of the candidate deployment location.

6. The method according to claim 1, characterized in that The step of constructing the energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location includes: Constructing an energy storage demand matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location; The energy storage demand matrix is ​​standardized, and the elements in the energy storage demand matrix are converted into the same dimension to obtain the energy storage demand characteristic matrix.

7. The method according to any one of claims 1 to 6, characterized in that: The obtaining of energy storage capacity gap data of the target area includes: Acquire time series data of historical undervoltage events and historical load changes in the target area to construct an undervoltage feature vector; Analyze the correlation between the voltage undervoltage characteristic vector and the load change time series to obtain the influence rule of the voltage undervoltage frequency on the historical load change; An energy storage capacity gap assessment is performed according to the voltage deficiency characteristic vector and the impact rule to obtain energy storage capacity gap data of the target area.

8. The method according to claim 7, characterized in that The frequency and amplitude statistics are performed according to the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and the uniform distribution of the high-risk time period is determined according to the time distribution characteristics, including: The energy storage capacity gap data is divided into time segments, and the frequency and average amplitude of the energy storage capacity gap within a unit time are counted to generate a gap data time series including a timestamp, frequency and average amplitude; Applying a sliding window to the gap data time series to obtain the cumulative frequency and average amplitude of the energy storage capacity gap in each window; Based on the cumulative frequency and average amplitude of the energy storage capacity gap in each window, generating a time distribution characteristic of the energy storage capacity gap in each time period; The time periods are classified according to the time distribution characteristics, a list of high-risk time periods is generated, and a uniform distribution of the high-risk time periods is determined.

9. A deployment device for an all-vanadium liquid flow battery energy storage system, characterized in that: The device comprises: A gap data acquisition module is used to acquire energy storage capacity gap data of a target area; wherein the duration corresponding to the energy storage capacity gap data is divided into a plurality of time periods; A distribution determination module is used to perform frequency and amplitude statistics based on the energy storage capacity gap data to obtain the time distribution characteristics of the energy storage capacity gap in each time period, and determine the uniform distribution of the high-risk time period based on the time distribution characteristics; A honeycomb unit division module is used for dividing the target area into a plurality of honeycomb units when the uniform distribution indicates that the high-risk time period is unevenly distributed; wherein each honeycomb unit is regarded as a candidate deployment location of the all-vanadium liquid flow battery energy storage system; A related data acquisition module is used to construct an energy storage demand characteristic matrix corresponding to the target area according to the energy storage capacity gap amplitude and capacity gap duration of each candidate deployment location, and perform correlation analysis based on the energy storage demand characteristic matrix to obtain spatial correlation data between the candidate deployment locations; An energy storage assessment module, configured to perform weighted processing according to the energy storage capacity gap amplitude, capacity gap duration and space-related data of the candidate deployment location to obtain energy storage assessment demand data of the candidate deployment location; A deployment plan generation module is used to generate a target deployment plan for the all-vanadium liquid flow battery energy storage system based on the technical parameters of the all-vanadium liquid flow battery and the energy storage assessment demand data of the candidate deployment location; wherein the deployment plan is used to describe the deployment location, capacity and charging and discharging strategy parameters of the all-vanadium liquid flow battery.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 8 by executing the computer instructions.

Images