S2G-V2G cooperative control method, device and equipment of energy storage type charging station and storage medium

Abstract

The invention discloses an S2G-V2G cooperative control method, device and equipment of an energy storage type charging station and a storage medium, and relates to the technical field of computers, and the method comprises the steps: determining a multi-source data set based on a cooperative control request issued by a power distribution network dispatching center or an energy management system; inputting the multi-source data set into a target model to obtain a charging and discharging state vector and an initial power distribution vector of the energy storage type charging station; judging whether the power interaction between the energy storage type charging station and the power distribution network meets a preset optimization condition or not; and if yes, constructing a multi-target optimization model by using a target constraint condition and a k-means clustering algorithm, carrying out distributed solution by using an alternating direction multiplier method to obtain a target power distribution scheme, converting the target power distribution scheme into a control instruction, and carrying out corresponding power cooperative execution operation by using the control instruction. Cooperative optimization control among the energy storage system, the vehicle and the power distribution network is realized, so that the operation pressure of the power distribution network is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a S2G-V2G collaborative control method, device and equipment of energy storage type charging station and storage medium. BACKGROUND

[0002] With the rapid growth of the number of electric vehicles and the wide access of distributed energy, the distribution network is facing problems such as power fluctuation aggravation, load peak-valley difference expansion and power quality decline. The traditional charging station is mainly one-way charging, which is difficult to effectively support the power grid. The energy storage type charging station has energy storage and bidirectional regulation capability, and becomes an important node to realize vehicle-to-grid interaction and peak load shifting. However, in the prior art, the control of the energy storage system and the vehicle-to-grid is independent operation, and lacks a unified energy management mechanism, making it difficult to realize collaborative optimization control of the station, the grid and the vehicle. At the same time, the traditional scheduling mode has slow response speed and insufficient consideration of power fluctuation and battery degradation, which limits the operation efficiency and economy of the energy storage device in the dynamic power grid environment.

[0003] From the above, how to realize the collaborative optimization control among the energy storage system, the vehicle and the distribution network to reduce the operation pressure of the distribution network is a problem to be solved at present. SUMMARY

[0004] Therefore, the present application aims to provide a S2G-V2G collaborative control method, device and equipment of energy storage type charging station, which can realize the collaborative optimization control among the energy storage system, the vehicle and the distribution network to reduce the operation pressure of the distribution network. The specific scheme is as follows:

[0005] In the first aspect, the present application provides a S2G-V2G collaborative control method of energy storage type charging station, comprising:

[0006] determining a corresponding multi-source data set based on a collaborative control request issued by a distribution network dispatching center or an energy management system; the multi-source data set includes energy storage side data corresponding to the energy storage type charging station, vehicle side data corresponding to a target vehicle accessing the energy storage type charging station, and grid side data corresponding to the distribution network;

[0007] inputting the multi-source data set into a target model to obtain a charge-discharge state vector and an initial power allocation vector of the energy storage type charging station; the target model includes a preset energy storage state estimation model, a preset power flow model and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation among the energy storage type charging station, the target vehicle and the distribution network;

[0008] judging whether the power interaction between the energy storage type charging station and the distribution network meets a preset optimization condition based on the charge-discharge state vector and the initial power allocation vector;

[0009] If the preset optimization conditions are met, a multi-objective optimization model is constructed using the target constraints and k-means clustering algorithm. Based on the multi-objective optimization model, a distributed solution is performed using the alternating direction multiplier method to obtain the target power allocation scheme. The target power allocation scheme is then converted into control commands to perform corresponding power coordination operations.

[0010] Optionally, determining the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system includes:

[0011] The system acquires a coordinated control request issued by the power distribution network dispatch center or energy management system, and determines the energy storage-side data corresponding to the energy storage charging station based on the coordinated control request. The energy storage-side data includes first data corresponding to the energy storage battery in the energy storage charging station and second data corresponding to the energy storage converter in the energy storage charging station. The first data includes the voltage, current, battery state of charge, health status, operating temperature, and total charging and discharging power of the target vehicle connected to the energy storage battery at the current moment. The second data includes the real-time output power of the energy storage converter. The battery state of charge represents the remaining capacity percentage of the energy storage battery.

[0012] Based on the collaborative control request, the vehicle-side data corresponding to the target vehicle accessing the energy storage charging station is determined; the vehicle-side data includes the target vehicle's battery capacity, initial vehicle state of charge, charging power threshold, discharging power threshold, vehicle charging and discharging efficiency, vehicle required state of charge, remaining time after leaving the station, access charging pile number, and user priority weight; the initial vehicle state of charge represents the remaining battery capacity of the target vehicle when it accesses the energy storage charging station;

[0013] Based on the coordinated control request, the grid-side data corresponding to the distribution network is determined, and a multi-source dataset is constructed using the energy storage-side data, the vehicle-side data, and the grid-side data; the grid-side data includes the preset interactive power, electricity price signal, frequency deviation, and bus voltage between the energy storage charging station and the distribution network.

[0014] Optionally, inputting the multi-source dataset into the target model to obtain the charge / discharge state vector and initial power allocation vector of the energy storage charging station includes:

[0015] The charging and discharging power of the energy storage battery is determined based on its voltage and current, and the charging efficiency, discharging efficiency, and rated capacity of the energy storage battery are obtained.

[0016] Based on the current state of charge of the energy storage battery, the battery charging and discharging power, the charging efficiency and the discharging efficiency, and using a preset energy storage state estimation model, the target state of charge of the battery at the next moment is determined.

[0017] Based on the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle connected to the grid, and the total power loss generated by the energy storage charging station during operation, the target interaction power between the energy storage charging station and the power distribution network is determined using a preset power flow model.

[0018] The load forecast value of the distribution network is determined based on historical distribution network load data and using the time series forecasting method in the preset load forecasting model.

[0019] The charge / discharge state vector of the energy storage battery is constructed using the target battery's state of charge, the energy storage battery's charging efficiency, and the energy storage battery's discharging efficiency.

[0020] An initial power allocation vector is constructed using the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle, and the target interactive power.

[0021] Optionally, determining whether the power interaction between the energy storage charging station and the power distribution network satisfies preset optimization conditions based on the charge / discharge state vector and the initial power allocation vector includes:

[0022] The power fluctuation index between the energy storage charging station and the power distribution network is determined based on the target interactive power in the initial power allocation vector and the preset interactive power.

[0023] Determine whether the power fluctuation index is greater than the target deviation threshold;

[0024] If the power fluctuation index is greater than the target deviation threshold, it indicates that the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions.

[0025] Optionally, the target constraint conditions include a first preset constraint condition, a second preset constraint condition, a third preset constraint condition, and a fourth preset constraint condition;

[0026] The first preset constraint is that the battery charging and discharging power of the energy storage battery is within a first target charging and discharging power range; the first target charging and discharging power range is determined based on the energy storage battery provider; the second preset constraint is that the vehicle charging and discharging power of the target vehicle is within a second target charging and discharging power range; the second target charging and discharging power range is determined based on the charging power threshold and discharging power threshold of the target vehicle; the third preset constraint is that the battery state of charge is within a first target safety range, and the initial vehicle state of charge is within a second target safety range; the fourth preset constraint is that the bus voltage is within a target voltage range, and the frequency deviation is within a target allowable deviation range.

[0027] Optionally, the step of constructing a multi-objective optimization model using objective constraints and k-means clustering algorithm, and then performing a distributed solution based on the multi-objective optimization model using the alternating direction multiplier method to obtain the objective power allocation scheme includes:

[0028] The vehicle feature vector is constructed based on the initial vehicle state of charge, the vehicle demand state of charge, the remaining time before departure, the charging power threshold, the discharging power threshold, the access charging pile number, and the user priority weight in the vehicle-side data.

[0029] The contour coefficient method in the k-means clustering algorithm is used to cluster the feature vectors of each vehicle corresponding to the target vehicle to obtain k vehicle clusters;

[0030] Based on the vehicle cluster, the preset interaction power, the target interaction power, the user priority weight, the load forecast value, and the current in the grid-side data, and using the target constraints, a multi-objective optimization model is constructed.

[0031] Based on the multi-objective optimization model and using the alternating direction multiplier method for distributed solution, the target power vector is obtained; the target power vector includes the first target charge and discharge power vector corresponding to the energy storage battery, the second target charge and discharge power vector corresponding to the target vehicle, and the third target charge and discharge power vector corresponding to the energy storage converter.

[0032] Optionally, converting the target power allocation scheme into control commands to perform corresponding power coordination operations using the control commands includes:

[0033] The first target charge / discharge power vector is converted into a first control command corresponding to the energy storage battery;

[0034] Power allocation and adjustment are performed based on the second target charging and discharging power vector and the capability coefficient and demand weight corresponding to the target vehicle in each vehicle cluster to obtain the total power command of the vehicle cluster; the capability coefficient is determined based on the charging power threshold and the discharging power threshold corresponding to the target vehicle; the demand weight is determined based on the initial vehicle state of charge, the vehicle demand state of charge, and the user priority weight corresponding to the target vehicle.

[0035] The total power command is converted into a second control command corresponding to the target vehicle, and the third target charging and discharging power vector is converted into a third control command corresponding to the energy storage converter;

[0036] Based on the first control command, the second control command, and the third control command, perform corresponding power coordination operations.

[0037] Secondly, this application provides an S2G–V2G cooperative control device for an energy storage charging station, comprising:

[0038] The dataset determination module is used to determine the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system; the multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the distribution network.

[0039] The dataset input module is used to input the multi-source dataset into the target model to obtain the charging and discharging state vector and the initial power allocation vector of the energy storage charging station; the target model includes a preset energy storage state estimation model, a preset power flow model and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle and the power distribution network;

[0040] The power interaction judgment module is used to determine whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions based on the charging and discharging state vector and the initial power allocation vector.

[0041] The collaborative execution module is used to construct a multi-objective optimization model using the target constraints and k-means clustering algorithm if the preset optimization conditions are met, perform distributed solution based on the multi-objective optimization model and using the alternating direction multiplier method to obtain the target power allocation scheme, and convert the target power allocation scheme into control commands to perform corresponding power collaborative execution operations using the control commands.

[0042] Thirdly, this application provides an electronic device, comprising:

[0043] Memory, used to store computer programs;

[0044] A processor is used to execute the computer program to implement the aforementioned S2G–V2G collaborative control method for energy storage charging stations.

[0045] Fourthly, this application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned S2G–V2G cooperative control method for an energy storage charging station.

[0046] This application determines the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system. The multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the distribution network. The multi-source dataset is input into the target model to obtain the charging and discharging state vector and the initial power allocation vector of the energy storage charging station. The target model includes a preset energy storage state estimation model, a preset power flow model, and a preset load prediction model. The initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle, and the distribution network. Based on the charging and discharging state vector and the initial power allocation vector, it is determined whether the power interaction between the energy storage charging station and the distribution network meets the preset optimization conditions. If the preset optimization conditions are met, a multi-objective optimization model is constructed using the target constraint conditions and the k-means clustering algorithm. Based on the multi-objective optimization model, a distributed solution is performed using the alternating direction multiplier method to obtain the target power allocation scheme. The target power allocation scheme is then converted into control commands to perform corresponding power collaborative execution operations.

[0047] As can be seen from the above, this application constructs a multi-dimensional dataset including the energy storage side, vehicle side, and grid side based on the collaborative control request. Based on this multi-dimensional dataset, and utilizing a preset energy storage state estimation model, a preset power flow model, and a preset load prediction model, the initial power allocation relationship between energy storage, vehicles, and the grid is quantified to further determine whether the current power allocation relationship needs optimization. If optimization is required, a multi-objective optimization model is constructed based on objective constraints and the k-means clustering algorithm, and a distributed solution is performed using the alternating direction multiplier method to obtain the globally optimal target power allocation scheme. In this way, the target power allocation scheme enables intelligent scheduling of energy storage charging stations and adaptive energy management of the distribution network, thereby significantly improving the overall operating efficiency of the charging station and the grid. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0049] Figure 1 This is a flowchart of an S2G–V2G collaborative control method for an energy storage charging station disclosed in this application;

[0050] Figure 2 This application discloses a flowchart of an S2G–V2G collaborative control method for a specific energy storage charging station.

[0051] Figure 3 A schematic diagram of a k-means clustering algorithm provided in this application;

[0052] Figure 4 This is a schematic diagram of the S2G–V2G collaborative control device for an energy storage charging station disclosed in this application.

[0053] Figure 5 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Currently, energy storage systems and vehicle-to-grid (V2G) control are mostly independent, lacking a unified energy management mechanism, making it difficult to achieve coordinated and optimized control between the charging station and the V2G network. Furthermore, traditional scheduling methods suffer from slow response times and insufficient consideration of factors such as power fluctuations and battery degradation, limiting the operational efficiency and economy of energy storage devices in dynamic grid environments. To address this, this application provides an S2G–V2G coordinated control method for energy storage charging stations. Through a target power allocation scheme, it enables intelligent scheduling of energy storage charging stations and adaptive energy management of the distribution network, thereby significantly improving the overall operational efficiency of both the charging station and the power grid.

[0056] See Figure 1 As shown, this embodiment of the invention discloses an S2G–V2G cooperative control method for an energy storage charging station, including:

[0057] Step S11: Determine the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system; the multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the distribution network.

[0058] In this embodiment, energy storage-side data, vehicle-side data, and grid-side data are determined based on a collaborative control request issued by the distribution network dispatch center or energy management system. The collaborative control request includes a preset interaction power between the energy storage charging station and the distribution network; the preset interaction power is the desired interaction power between the energy storage charging station and the distribution network by the grid. The vehicle-side data includes the vehicle's demand state of charge, remaining time before departure, and user priority weight. The vehicle's demand state of charge is set based on the user's charging demand. The remaining time before departure is the interval between the vehicle's expected departure time and the current time. A higher user priority weight indicates a higher user priority.

[0059] Specifically, determining the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system includes: acquiring the collaborative control request issued by the distribution network dispatch center or energy management system, and determining the energy storage-side data corresponding to the energy storage charging station based on the collaborative control request; the energy storage-side data includes first data corresponding to the energy storage battery in the energy storage charging station and second data corresponding to the energy storage converter in the energy storage charging station; the first data includes the voltage, current, battery state of charge, health status, operating temperature of the energy storage battery at the current moment, and the total charging and discharging power of the target vehicle connected; the second data includes the real-time output power of the energy storage converter; the battery state of charge represents the remaining capacity ratio of the energy storage battery; The collaborative control request determines the vehicle-side data corresponding to the target vehicle accessing the energy storage charging station. This vehicle-side data includes the target vehicle's battery capacity, initial state of charge (SBC), charging power threshold, discharging power threshold, vehicle charging / discharging efficiency, required SBC, remaining time before departure, access charging pile number, and user priority weight. The initial SBC represents the remaining battery capacity of the target vehicle when it accesses the energy storage charging station. Based on the collaborative control request, the grid-side data corresponding to the distribution network is determined, and a multi-source dataset is constructed using the energy storage-side data, the vehicle-side data, and the grid-side data. The grid-side data includes the preset interaction power, electricity price signal, frequency deviation, and bus voltage between the energy storage charging station and the distribution network.

[0060] Step S12: Input the multi-source dataset into the target model to obtain the charging and discharging state vector and initial power allocation vector of the energy storage charging station; the target model includes a preset energy storage state estimation model, a preset power flow model and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle and the power distribution network.

[0061] In this embodiment, the target battery state of charge at the next moment is determined using a preset energy storage state estimation model, and the corresponding formula is as follows:

[0062] ;

[0063] in, The target battery state of charge for the next moment or the next scheduling cycle; This refers to the current state of battery charge, i.e., the battery charge state in the energy storage side data. The charging efficiency of the energy storage battery is determined based on the supplier of the energy storage battery. The discharge efficiency of the energy storage battery; The charging power of the energy storage battery at the current moment is determined based on the voltage and current of the energy storage battery. This represents the discharge power of the energy storage battery at the current moment. The rated capacity of the energy storage battery; For time or scheduling cycle.

[0064] It is understandable that, after obtaining the target battery state of charge, the target interactive power between the energy storage charging station and the distribution network is determined using a preset power flow model, and the corresponding formula is as follows:

[0065] ;

[0066] in, The target interaction power between the energy storage charging station and the distribution network at the current moment is defined as follows: if the target interaction power is positive, it indicates that the energy storage charging station is discharging to the distribution network; if the target interaction power is negative, it indicates that the distribution network is charging the energy storage charging station. This represents the charging and discharging power of the energy storage battery at the current moment. The total charging and discharging power of the target vehicle connected to the energy storage charging station in the energy storage side data; The total power loss generated by the energy storage charging station during operation includes the losses of the energy storage converter and the line losses.

[0067] Furthermore, after obtaining the target interactive power, the load forecast value of the distribution network is determined based on historical distribution network load data and using the time series forecasting method in the preset load forecasting model. The corresponding formula is as follows:

[0068] ;

[0069] in, The load forecast value for the aforementioned distribution network; This is a fuzzy time series forecasting method (FTS). The actual load data for the past k time points can be obtained from the database in the distribution network dispatch center. After obtaining the load forecast value, the charge / discharge state vector of the energy storage battery is constructed using the target battery's state of charge, the charging efficiency, and the discharging efficiency. The formula corresponding to the charge / discharge state vector is as follows:

[0070] ;

[0071] in, The target battery's state of charge; The charging efficiency of the energy storage battery; Let be the discharge efficiency of the energy storage battery. After obtaining the charge / discharge state vector, an initial power allocation vector is constructed using the charging efficiency and discharge efficiency of the energy storage battery, the total charge / discharge power of the target vehicle, and the target interactive power. The corresponding formula is as follows:

[0072] ;

[0073] in, The charge / discharge efficiency of the energy storage battery; The total charging and discharging power of the target vehicle connected to the energy storage charging station; The target interaction power is denoted as .

[0074] Specifically, inputting the multi-source dataset into the target model to obtain the charge / discharge state vector and initial power allocation vector of the energy storage charging station includes: determining the battery charge / discharge power based on the voltage and current of the energy storage battery, and obtaining the charging efficiency, discharging efficiency, and rated capacity of the energy storage battery; determining the target battery state of charge corresponding to the next moment based on the battery state of charge, the battery charge / discharge power, the charging efficiency, and the discharging efficiency of the energy storage battery at the current moment, and using a preset energy storage state estimation model; and determining the target battery state of charge corresponding to the next moment based on the charging efficiency, discharging efficiency, and total charging capacity of the target vehicles connected to the energy storage battery. The system calculates the discharge power and the total power loss generated by the energy storage charging station during operation, and uses a preset power flow model to determine the target interaction power between the energy storage charging station and the distribution network. Based on historical distribution network load data and using the time series prediction method in the preset load prediction model, the system determines the load prediction value of the distribution network. The system constructs the charge / discharge state vector of the energy storage battery using the target battery state of charge, the charging efficiency, and the discharging efficiency. The system constructs an initial power allocation vector using the charging efficiency, discharging efficiency, the total charge / discharge power of the target vehicle connected to the system, and the target interaction power.

[0075] Step S13: Based on the charging and discharging state vector and the initial power allocation vector, determine whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions.

[0076] In this embodiment, the power fluctuation index between the energy storage charging station and the distribution network is determined based on the target interactive power in the initial power allocation vector and the preset interactive power. The corresponding formula is as follows:

[0077] ;

[0078] in, This refers to the power fluctuation index; The target interaction power; The preset interaction power between the energy storage charging station and the distribution network in the grid-side data; To minimize the value, the denominator should be kept to a minimum. After obtaining the power fluctuation index, it is determined whether the power fluctuation index is greater than the target deviation threshold; the target deviation threshold is set according to the grid requirements; if the power fluctuation index is greater than the target deviation threshold, it indicates that the power interaction between the energy storage charging station and the distribution network meets the preset optimization conditions.

[0079] Specifically, determining whether the power interaction between the energy storage charging station and the distribution network meets the preset optimization conditions based on the charge / discharge state vector and the initial power allocation vector includes: determining the power fluctuation index between the energy storage charging station and the distribution network based on the target interaction power in the initial power allocation vector and the preset interaction power; determining whether the power fluctuation index is greater than a target deviation threshold; if the power fluctuation index is greater than the target deviation threshold, it indicates that the power interaction between the energy storage charging station and the distribution network meets the preset optimization conditions.

[0080] Step S14: If the preset optimization conditions are met, a multi-objective optimization model is constructed using the target constraints and k-means clustering algorithm. Based on the multi-objective optimization model, a distributed solution is performed using the alternating direction multiplier method to obtain the target power allocation scheme. The target power allocation scheme is then converted into control commands to perform corresponding power coordination operations.

[0081] In this embodiment, the target constraints are first defined. The first preset constraint, which characterizes the energy storage power constraint, is given by the following formula:

[0082] ;

[0083] in, This represents the minimum charge / discharge efficiency of the energy storage battery. The charge / discharge efficiency of the energy storage battery; The maximum charge / discharge efficiency of the energy storage battery is defined as follows: the minimum charge / discharge efficiency and the maximum charge / discharge efficiency are fixed parameters determined based on the energy storage battery supplier. The second preset constraint is the vehicle charge / discharge power constraint; wherein, the vehicle charge / discharge power constraint includes the charge / discharge power constraint for a single vehicle and the total charge / discharge power constraint for all target vehicles; the corresponding formula is as follows:

[0084] ;

[0085] ;

[0086] in; Maximum charging power for a single vehicle; The charging and discharging power for a single vehicle; This represents the maximum discharge power of a single vehicle. The negative of the total charging power of all target vehicles, i.e., the sum of the maximum charging power of individual vehicles; The total charging and discharging power of all target vehicles connected to the energy storage charging station; It is the negative of the total discharge power of all target vehicles, that is, the sum of the maximum discharge power of a single vehicle.

[0087] It is understood that the third preset constraint is a state of charge (SOC) constraint; the SOC constraint includes the energy storage battery SOC constraint and the vehicle SOC constraint; the corresponding formula is as follows:

[0088] ;

[0089] ;

[0090] in, This is the minimum state of charge of the energy storage battery; The state of charge of the energy storage battery is the battery state of charge in the energy storage side data. This represents the maximum state of charge (SOC) of the energy storage battery. This represents the minimum state of charge of the vehicle. The vehicle charge state of the target vehicle; This represents the maximum value of the vehicle's state of charge.

[0091] Furthermore, the vehicle state of charge is determined based on the initial vehicle state of charge in the vehicle-side data and the vehicle charging and discharging efficiency; the corresponding formula is as follows:

[0092] ;

[0093] in, The vehicle's state of charge, i.e., the first The target vehicle at the current moment After State of charge corresponding to the time period; This refers to the initial vehicle state of charge in the vehicle-side data; For the first The rated battery capacity of the target vehicle; For the first The charging and discharging power of the target vehicle; The charge / discharge power is a positive number; The charging efficiency of the energy storage battery is determined based on the supplier of the energy storage battery. The discharge efficiency of the energy storage battery is given.

[0094] In this embodiment, the fourth preset constraint is the distribution network safety operation constraint, which includes voltage constraints and frequency constraints, and the corresponding formulas are as follows:

[0095] ;

[0096] ;

[0097] in, This represents the minimum voltage value of the distribution network. The bus voltage in the grid-side data; This represents the maximum voltage of the distribution network. This refers to the frequency deviation in the grid-side data; This represents the upper limit of the allowable frequency deviation.

[0098] Specifically, the target constraints include a first preset constraint, a second preset constraint, a third preset constraint, and a fourth preset constraint; wherein, the first preset constraint is that the battery charging and discharging power of the energy storage battery is within a first target charging and discharging power range; the first target charging and discharging power range is determined based on the energy storage battery provider; the second preset constraint is that the vehicle charging and discharging power of the target vehicle is within a second target charging and discharging power range; the second target charging and discharging power range is determined based on the charging power threshold and discharging power threshold of the target vehicle; the third preset constraint is that the battery state of charge is within a first target safety range, and the initial vehicle state of charge is within a second target safety range; the fourth preset constraint is that the bus voltage is within a target voltage range, and the frequency deviation is within a target allowable deviation range.

[0099] Understandably, after determining the target constraints, the vehicle feature vector corresponding to the target vehicle is constructed, and the corresponding formula is as follows:

[0100] ;

[0101] in, The initial vehicle state of charge in the vehicle-side data; The required state of charge for the vehicle; The remaining time before departure; The charging power threshold; The discharge power threshold; The user priority weight; The access charging piles are numbered. After obtaining the vehicle feature vectors, the Euclidean distance between each feature vector and the cluster center is determined to group target vehicles with similar features into k vehicle clusters; k is determined by the silhouette coefficient method or elbow method in the k-means clustering algorithm.

[0102] Furthermore, a multi-objective optimization model is constructed based on the stated objective constraints and the multi-source dataset, with different multi-objective optimization models built for different needs. In one specific embodiment, the formula corresponding to the multi-objective optimization model for the energy storage unit (i.e., energy storage battery) of the energy storage charging station is as follows:

[0103] ;

[0104] in, The target interaction power between the energy storage charging station and the power distribution network; The preset interaction power; , , These are the weighting coefficients; The target battery's state of charge; This represents the current state of battery charge. The square of the current of the energy storage battery; , This is a coefficient representing the cost of battery degradation; The reference state of charge (SOC) of the energy storage battery can be set according to actual conditions. This multi-objective optimization model aims to reduce SOC fluctuations and damage to the battery from high current, thereby extending the energy storage life.

[0105] In another specific embodiment, the formula corresponding to the multi-objective optimization model for the target vehicle is as follows:

[0106] ;

[0107] in, The target total charging and discharging power is issued by the power distribution network to the target vehicle; Total charging and discharging power for all target vehicles; , These are the weighting coefficients; The user priority weight; This refers to the initial state of vehicle charge; Let represent the charging and discharging power of the i-th target vehicle. This multi-objective optimization model prioritizes protecting the batteries of high-priority vehicles while minimizing battery damage to all vehicles. A pre-defined battery degradation cost function is used. The corresponding formula is as follows:

[0108] ;

[0109] in, This refers to the initial state of vehicle charge; The vehicle charging and discharging power corresponding to the i-th target vehicle.

[0110] In this embodiment, based on the distributed solution method of alternating direction multipliers, the global optimization problem is decomposed into an energy storage subproblem, a vehicle-to-grid interface subproblem, and a station-level coordination subproblem. Boundary power and coupling variables are synchronously exchanged among nodes using Lagrange multipliers to obtain the optimal power vector, i.e., the target power vector. The corresponding formula is as follows:

[0111] ;

[0112] in, The target power vector; The optimal charge / discharge power corresponding to the energy storage battery; The optimal charging and discharging power corresponding to the target vehicle; The optimal output power corresponding to the energy storage converter.

[0113] Specifically, the process of constructing a multi-objective optimization model using target constraints and k-means clustering, and then performing a distributed solution based on the multi-objective optimization model using the alternating direction multiplier method to obtain a target power allocation scheme, includes: constructing a vehicle feature vector based on the initial vehicle state of charge, the vehicle demand state of charge, the remaining time before departure, the charging power threshold, the discharging power threshold, the access charging pile number, and the user priority weight from the vehicle-side data; clustering the vehicle feature vectors corresponding to the target vehicle using the contour coefficient method in the k-means clustering algorithm to obtain k vehicle clusters; constructing a multi-objective optimization model based on the vehicle clusters, the preset interactive power, the target interactive power, the user priority weight, the load prediction value, and the current from the grid-side data, and using target constraints; and performing a distributed solution based on the multi-objective optimization model using the alternating direction multiplier method to obtain a target power vector; the target power vector includes a first target charge / discharge power vector corresponding to the energy storage battery, a second target charge / discharge power vector corresponding to the target vehicle, and a third target charge / discharge power vector corresponding to the energy storage converter.

[0114] In this embodiment, for the second target charging / discharging power vector corresponding to the target vehicle, power allocation and adjustment need to be performed by combining the capability coefficient and demand weight of the target vehicle in each vehicle cluster. In discharge mode, the target vehicle outputs electrical energy to the energy storage charging station or the power distribution network. The corresponding formula is as follows:

[0115] ;

[0116] in, Let be the optimal discharge power for the i-th vehicle; This represents the total discharge power of the k-th vehicle cluster. Let be the discharge capacity coefficient of the i-th vehicle; The discharge demand weight of the i-th vehicle is given by the denominator, which is the weighted sum of discharges of the k-th vehicle cluster. There are k vehicle clusters. In charging mode, the target vehicle absorbs electrical energy from the energy storage charging station or the power distribution network, i.e. The corresponding formula is as follows:

[0117] ;

[0118] in, The optimal charging power for the i-th vehicle; The total charging power of the k-th vehicle cluster; Let be the charging capacity coefficient of the i-th vehicle; The denominator is the weight of the charging demand of the i-th vehicle; the denominator is the weighted sum of the charging demand of the k-th vehicle cluster.

[0119] It is understandable that some of the parameters in the two formulas above correspond to the following formulas:

[0120] ;

[0121] ;

[0122] ;

[0123] ;

[0124] in, Let be the discharge capacity coefficient of the i-th vehicle; The discharge power threshold in the vehicle-side data; Let be the charging capacity coefficient of the i-th vehicle; The charging power threshold in the vehicle-side data; Let be the discharge demand weight for the i-th vehicle; This refers to the initial state of vehicle charge; The user priority weight; Weight the charging demand of the i-th vehicle; The required state of charge for the vehicle.

[0125] Furthermore, after obtaining the optimal charging and discharging power corresponding to the target vehicle, the total power command of the vehicle cluster is determined by combining the second target charging and discharging power vector. The first target charging and discharging power vector, the total power command, and the third target charging and discharging power vector are respectively converted into the corresponding first control command, second control command, and third control command. The above control commands are then sent to the bidirectional converter, the vehicle-to-grid interface module, and the charging station control unit. When sudden situations such as voltage exceeding limits, frequency abnormalities, or energy storage temperature abnormalities are detected, to avoid equipment damage or grid failure, the power deviation of the above control commands during actual execution is corrected using a PI regulator. The formula corresponding to the deviation is as follows:

[0126] ;

[0127] in, The power deviation of the control command during actual execution; The target total charging and discharging power is issued by the power distribution network to the target vehicle; This refers to the measured power during the actual execution process. The corresponding correction formula is shown below:

[0128] ;

[0129] in, These are the revised control commands; The target total charging and discharging power is issued by the power distribution network to the target vehicle; This is the proportionality coefficient; The integral coefficient; This is the integral of the power error; This refers to the power deviation during the actual execution of the control command.

[0130] Understandably, when an increase in power disturbance or a frequency deviation from the normal range is detected, the proportional coefficient is automatically increased to enhance the control response speed; when the situation tends to stabilize, the integral coefficient is reduced to avoid overshoot. This ensures the smoothness and robustness of power output under various operating conditions, effectively improving the stable operation capability of energy storage charging stations under multi-mode operating conditions. Specifically, the step of converting the target power allocation scheme into control commands to perform corresponding power collaborative execution operations includes: converting the first target charge / discharge power vector into a first control command corresponding to the energy storage battery; performing power allocation and adjustment based on the second target charge / discharge power vector and the capability coefficient and demand weight corresponding to the target vehicle in each vehicle cluster to obtain the total power command for the vehicle cluster; the capability coefficient is determined based on the charging power threshold and the discharging power threshold corresponding to the target vehicle; the demand weight is determined based on the initial vehicle state of charge, the vehicle demand state of charge, and the user priority weight corresponding to the target vehicle; converting the total power command into a second control command corresponding to the target vehicle, and converting the third target charge / discharge power vector into a third control command corresponding to the energy storage converter; and performing corresponding power collaborative execution operations based on the first control command, the second control command, and the third control command.

[0131] To further improve the power quality and safety of the system, this invention integrates harmonic suppression and power factor correction algorithms into the converter control layer. The harmonic suppression stage employs a harmonic detection and compensation strategy based on Fast Fourier Transform (FFT), capable of filtering out low-order harmonic components such as the 5th and 7th harmonics in real time, thereby maintaining the sinusoidal nature of the output current. Furthermore, an islanding detection mechanism can be built-in, employing a detection strategy combining active disturbance and passive voltage change methods to identify and respond to islanding operation status within milliseconds, preventing the inverter from feeding back current to the distribution network under grid outage conditions. This embodiment supports a fast communication protocol based on the IEC 61850 standard, enabling low-latency protection signal broadcasting and multi-device synchronous switching. By defining a GOOSE (Generic Object Oriented Substation Event) message mechanism, when a node detects a voltage or frequency over-limit event, it can broadcast a power disconnection command within milliseconds.

[0132] As can be seen from the above, this application constructs a multi-dimensional dataset including the energy storage side, vehicle side, and grid side based on the collaborative control request. Based on this multi-dimensional dataset, and utilizing a preset energy storage state estimation model, a preset power flow model, and a preset load prediction model, the initial power allocation relationship between energy storage, vehicles, and the grid is quantified to further determine whether the current power allocation relationship needs optimization. If optimization is required, a multi-objective optimization model is constructed based on objective constraints and the k-means clustering algorithm, and a distributed solution is performed using the alternating direction multiplier method to obtain the globally optimal target power allocation scheme. In this way, the target power allocation scheme enables intelligent scheduling of energy storage charging stations and adaptive energy management of the distribution network, thereby significantly improving the overall operating efficiency of the charging station and the grid.

[0133] As can be seen from the above embodiments, this application determines the target power allocation scheme based on the k-means clustering algorithm, thereby realizing intelligent scheduling of energy storage charging stations and adaptive energy management of the power distribution network. Therefore, the process of determining the target power allocation scheme based on the k-means clustering algorithm is described.

[0134] See Figure 2 As shown, this embodiment of the invention discloses a specific S2G–V2G cooperative control method for an energy storage charging station, including:

[0135] In this embodiment, an energy storage charging station and multiple electric vehicles are physically connected to the power distribution network. The energy storage charging station includes an energy storage system and a bidirectional converter. The bidirectional converter enables bidirectional energy conversion between the power distribution network, the energy storage charging station, and the electric vehicles, while ensuring power quality. By analyzing historical load data of the power distribution network, future load trends are predicted, and charging and discharging scheduling rules for the electric vehicles are determined based on the load forecast values ​​of the power distribution network. For example, charging is prioritized during off-peak hours, and discharging is optimized during peak hours. A multi-objective optimization model is constructed based on the demand of the power distribution network, the status of the energy storage charging station, and the vehicle feature vectors of the electric vehicles. The optimal power allocation scheme is obtained by solving the multi-objective optimization model.

[0136] Figure 3This embodiment illustrates a k-means clustering algorithm. Vehicle feature vectors are constructed based on the feature data of each electric vehicle to form the basic data space for clustering. The silhouette coefficient method in the k-means clustering algorithm is used to evaluate the clustering effect under different numbers of clusters. The cluster with the highest clustering quality is selected. Then, the Euclidean distance between the vehicle feature vector and the cluster center is determined. Electric vehicles with similar features are grouped into k clusters. The cluster center of each cluster is updated based on the mean of all vehicle features within each cluster to improve clustering accuracy. The positions of the cluster centers before and after the update are compared to determine if a large-scale movement has occurred. If the cluster center positions have moved significantly, the process jumps to the step of determining the Euclidean distance between the vehicle feature vector and the cluster center until the cluster center positions stabilize. If the cluster center positions are stable, k stable vehicle clusters are determined.

[0137] Understandably, a multi-objective optimization model is constructed using objective constraints and k-means clustering algorithm, and then the multi-objective optimization model is solved in a distributed manner to obtain a target power allocation scheme. This target power allocation scheme is then converted into specific control commands, which are sent to the corresponding execution modules to drive the equipment to perform charging and discharging operations. Next, the actual operating power of the energy storage charging station, the electric vehicle, and the bidirectional converter is collected. A PI regulator is used to correct the power deviation between the actual operating power and the target power to dynamically update the scheduling strategy, enabling electric vehicles to participate in the active power service of the power distribution network.

[0138] As can be seen from the above, the multi-objective optimization model constructed in this application maintains the energy storage load state near the reference value, avoiding overcharging and over-discharging, while allowing the energy storage charging station to flexibly switch charging and discharging states between grid demand and vehicle demand. This prevents the energy storage charging station from being idle for a long time or operating at full load, thus extending the lifespan of the energy storage battery. Then, a clustering algorithm is used to group a large number of vehicles, significantly reducing the computational complexity of the multi-objective optimization model. Furthermore, after obtaining the control command corresponding to the target power allocation scheme, the actual power deviation is corrected to reduce energy loss. In this way, the energy storage charging station, vehicles, and power distribution network are coordinated for control, which not only solves the operational pain points of the power distribution network but also improves the operational value of the energy storage charging station and the user experience.

[0139] Accordingly, see Figure 4 As shown, this application also provides an S2G–V2G cooperative control device for an energy storage charging station, comprising:

[0140] The dataset determination module 11 is used to determine the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system; the multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the distribution network.

[0141] The dataset input module 12 is used to input the multi-source dataset into the target model to obtain the charging and discharging state vector and the initial power allocation vector of the energy storage charging station; the target model includes a preset energy storage state estimation model, a preset power flow model and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle and the power distribution network;

[0142] The power interaction judgment module 13 is used to determine whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions based on the charging and discharging state vector and the initial power allocation vector.

[0143] The collaborative execution module 14 is used to construct a multi-objective optimization model using the target constraints and k-means clustering algorithm if the preset optimization conditions are met, perform distributed solution based on the multi-objective optimization model and using the alternating direction multiplier method to obtain the target power allocation scheme, and convert the target power allocation scheme into control commands to perform corresponding power collaborative execution operations using the control commands.

[0144] In some specific embodiments, the dataset determination module 11 may specifically include:

[0145] The first data determination unit is used to acquire the coordinated control request issued by the distribution network dispatch center or energy management system, and determine the energy storage side data corresponding to the energy storage charging station based on the coordinated control request; the energy storage side data includes first data corresponding to the energy storage battery in the energy storage charging station and second data corresponding to the energy storage converter in the energy storage charging station; the first data includes the voltage, current, battery state of charge, health status, operating temperature of the energy storage battery at the current moment, and the total charging and discharging power of the target vehicle connected; the second data includes the real-time output power of the energy storage converter; the battery state of charge represents the remaining capacity ratio of the energy storage battery;

[0146] The second data determination unit is used to determine the vehicle-side data corresponding to the target vehicle accessing the energy storage charging station based on the cooperative control request; the vehicle-side data includes the target vehicle's battery capacity, initial vehicle state of charge, charging power threshold, discharging power threshold, vehicle charging and discharging efficiency, vehicle demand state of charge, remaining time after leaving the station, access charging pile number, and user priority weight; the initial vehicle state of charge represents the proportion of remaining power of the target vehicle when it accesses the energy storage charging station;

[0147] The dataset construction unit is used to determine the grid-side data corresponding to the distribution network based on the coordinated control request, and to construct a multi-source dataset using the energy storage-side data, the vehicle-side data and the grid-side data; the grid-side data includes the preset interaction power, electricity price signal, frequency deviation and bus voltage between the energy storage charging station and the distribution network.

[0148] In some specific embodiments, the dataset input module 12 may specifically include:

[0149] The capacity acquisition unit is used to determine the battery charging and discharging power based on the voltage and current of the energy storage battery, and to acquire the charging efficiency, discharging efficiency and rated capacity of the energy storage battery.

[0150] The target state of charge determination unit is used to determine the target state of charge of the energy storage battery at the next moment based on the battery state of charge of the energy storage battery at the current moment, the battery charging and discharging power, the charging efficiency and the discharging efficiency, and using a preset energy storage state estimation model.

[0151] The interaction power determination unit is used to determine the target interaction power between the energy storage charging station and the power distribution network based on the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle connected to the network, and the total power loss generated by the energy storage charging station during operation, using a preset power flow model.

[0152] The prediction value determination unit is used to determine the predicted load value of the distribution network based on historical distribution network load data and using the time series prediction method in the preset load prediction model;

[0153] A state vector determination unit is used to construct the charge and discharge state vector of the energy storage battery using the target battery's state of charge, the energy storage battery's charging efficiency, and the energy storage battery's discharging efficiency.

[0154] The allocation vector construction unit is used to construct an initial power allocation vector using the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle connected, and the target interactive power.

[0155] In some specific embodiments, the power interaction judgment module 13 may specifically include:

[0156] A power index determination unit is used to determine the power fluctuation index between the energy storage charging station and the power distribution network based on the target interactive power in the initial power allocation vector and the preset interactive power.

[0157] An indicator judgment unit is used to determine whether the power fluctuation indicator is greater than the target deviation threshold.

[0158] The condition satisfaction unit is used to indicate that if the power fluctuation index is greater than the target deviation threshold, then the power interaction between the energy storage charging station and the distribution network meets the preset optimization conditions.

[0159] In some specific implementations, the target constraint conditions include a first preset constraint condition, a second preset constraint condition, a third preset constraint condition, and a fourth preset constraint condition.

[0160] In some specific embodiments, the collaborative execution module 14 may specifically include:

[0161] The feature vector construction unit is used to construct the vehicle feature vector based on the initial vehicle state of charge, the vehicle demand state of charge, the remaining time after departure, the charging power threshold, the discharging power threshold, the access charging pile number, and the user priority weight in the vehicle-side data.

[0162] The vector clustering unit is used to cluster the feature vectors of the target vehicle using the contour coefficient method in the k-means clustering algorithm to obtain k vehicle clusters.

[0163] The optimization model building unit is used to build a multi-objective optimization model based on the vehicle cluster, the preset interaction power, the target interaction power, the user priority weight, the load forecast value, and the current in the power grid side data, and using target constraints.

[0164] The target vector determination unit is used to perform distributed solution based on the multi-objective optimization model and using the alternating direction multiplier method to obtain the target power vector; the target power vector includes the first target charge and discharge power vector corresponding to the energy storage battery, the second target charge and discharge power vector corresponding to the target vehicle, and the third target charge and discharge power vector corresponding to the energy storage converter.

[0165] In some specific embodiments, the collaborative execution module 14 may specifically include:

[0166] The first vector conversion unit is used to convert the first target charging and discharging power vector into a first control command corresponding to the energy storage battery;

[0167] A power adjustment unit is used to perform power allocation and adjustment based on the second target charging and discharging power vector and the capability coefficient and demand weight corresponding to the target vehicle in each vehicle cluster, so as to obtain the total power command of the vehicle cluster; the capability coefficient is determined based on the charging power threshold and the discharging power threshold corresponding to the target vehicle; the demand weight is determined based on the initial vehicle state of charge, the vehicle demand state of charge, and the user priority weight corresponding to the target vehicle.

[0168] The second vector conversion unit is used to convert the total power command into a second control command corresponding to the target vehicle, and to convert the third target charging and discharging power vector into a third control command corresponding to the energy storage converter;

[0169] The collaborative execution unit is used to perform corresponding power collaborative execution operations based on the first control command, the second control command, and the third control command.

[0170] Furthermore, embodiments of this application also disclose an electronic device, Figure 5 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the S2G–V2G cooperative control method for energy storage charging stations disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be a computer.

[0171] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0172] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0173] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the S2G–V2G cooperative control method for the energy storage charging station executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0174] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned S2G–V2G cooperative control method for an energy storage charging station. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0175] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0176] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0177] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0178] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0179] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An S2G–V2G cooperative control method for an energy storage charging station, characterized in that, include: The corresponding multi-source dataset is determined based on the collaborative control request issued by the distribution network dispatch center or energy management system; The multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the power distribution network. The multi-source dataset is input into the target model to obtain the charging and discharging state vector and the initial power allocation vector of the energy storage charging station; the target model includes a preset energy storage state estimation model, a preset power flow model, and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle, and the power distribution network. Based on the charging and discharging state vector and the initial power allocation vector, it is determined whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions. If the preset optimization conditions are met, a multi-objective optimization model is constructed using the target constraints and k-means clustering algorithm. Based on the multi-objective optimization model, a distributed solution is performed using the alternating direction multiplier method to obtain the target power allocation scheme. The target power allocation scheme is then converted into control commands to perform corresponding power coordination operations.

2. The S2G–V2G cooperative control method for energy storage charging stations according to claim 1, characterized in that, The determination of the corresponding multi-source dataset based on the collaborative control request issued by the distribution network dispatch center or energy management system includes: The system acquires a coordinated control request issued by the power distribution network dispatch center or energy management system, and determines the energy storage-side data corresponding to the energy storage charging station based on the coordinated control request. The energy storage-side data includes first data corresponding to the energy storage battery in the energy storage charging station and second data corresponding to the energy storage converter in the energy storage charging station. The first data includes the voltage, current, battery state of charge, health status, operating temperature, and total charging and discharging power of the target vehicle connected to the energy storage battery at the current moment. The second data includes the real-time output power of the energy storage converter. The battery state of charge represents the remaining capacity percentage of the energy storage battery. Based on the collaborative control request, the vehicle-side data corresponding to the target vehicle accessing the energy storage charging station is determined; the vehicle-side data includes the target vehicle's battery capacity, initial vehicle state of charge, charging power threshold, discharging power threshold, vehicle charging and discharging efficiency, vehicle required state of charge, remaining time after leaving the station, access charging pile number, and user priority weight; the initial vehicle state of charge represents the remaining battery capacity of the target vehicle when it accesses the energy storage charging station; Based on the coordinated control request, the grid-side data corresponding to the distribution network is determined, and a multi-source dataset is constructed using the energy storage-side data, the vehicle-side data, and the grid-side data; the grid-side data includes the preset interactive power, electricity price signal, frequency deviation, and bus voltage between the energy storage charging station and the distribution network.

3. The S2G–V2G cooperative control method for energy storage charging stations according to claim 2, characterized in that, The step of inputting the multi-source dataset into the target model to obtain the charging / discharging state vector and initial power allocation vector of the energy storage charging station includes: The charging and discharging power of the energy storage battery is determined based on its voltage and current, and the charging efficiency, discharging efficiency, and rated capacity of the energy storage battery are obtained. Based on the current state of charge of the energy storage battery, the battery charging and discharging power, the charging efficiency and the discharging efficiency, and using a preset energy storage state estimation model, the target state of charge of the battery at the next moment is determined. Based on the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle connected to the grid, and the total power loss generated by the energy storage charging station during operation, the target interaction power between the energy storage charging station and the power distribution network is determined using a preset power flow model. The load forecast value of the distribution network is determined based on historical distribution network load data and using the time series forecasting method in the preset load forecasting model. The charge / discharge state vector of the energy storage battery is constructed using the target battery's state of charge, the energy storage battery's charging efficiency, and the energy storage battery's discharging efficiency. An initial power allocation vector is constructed using the charging efficiency and discharging efficiency of the energy storage battery, the total charging and discharging power of the target vehicle, and the target interactive power.

4. The S2G–V2G cooperative control method for energy storage charging stations according to claim 3, characterized in that, The step of determining whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions based on the charge / discharge state vector and the initial power allocation vector includes: The power fluctuation index between the energy storage charging station and the power distribution network is determined based on the target interactive power in the initial power allocation vector and the preset interactive power. Determine whether the power fluctuation index is greater than the target deviation threshold; If the power fluctuation index is greater than the target deviation threshold, it indicates that the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions.

5. The S2G–V2G cooperative control method for energy storage charging stations according to claim 3 or 4, characterized in that, The target constraints include a first preset constraint, a second preset constraint, a third preset constraint, and a fourth preset constraint. The first preset constraint is that the battery charging and discharging power of the energy storage battery is within a first target charging and discharging power range; the first target charging and discharging power range is determined based on the energy storage battery provider; the second preset constraint is that the vehicle charging and discharging power of the target vehicle is within a second target charging and discharging power range; the second target charging and discharging power range is determined based on the charging power threshold and discharging power threshold of the target vehicle; the third preset constraint is that the battery state of charge is within a first target safety range, and the initial vehicle state of charge is within a second target safety range; the fourth preset constraint is that the bus voltage is within a target voltage range, and the frequency deviation is within a target allowable deviation range.

6. The S2G–V2G cooperative control method for energy storage charging stations according to claim 3, characterized in that, The process of constructing a multi-objective optimization model using objective constraints and k-means clustering, and then performing a distributed solution based on this model using the alternating direction multiplier method to obtain the objective power allocation scheme includes: The vehicle feature vector is constructed based on the initial vehicle state of charge, the vehicle demand state of charge, the remaining time before departure, the charging power threshold, the discharging power threshold, the access charging pile number, and the user priority weight in the vehicle-side data. The contour coefficient method in the k-means clustering algorithm is used to cluster the feature vectors of each vehicle corresponding to the target vehicle to obtain k vehicle clusters; Based on the vehicle cluster, the preset interaction power, the target interaction power, the user priority weight, the load forecast value, and the current in the grid-side data, and using the target constraints, a multi-objective optimization model is constructed. Based on the multi-objective optimization model and using the alternating direction multiplier method for distributed solution, the target power vector is obtained; the target power vector includes the first target charge and discharge power vector corresponding to the energy storage battery, the second target charge and discharge power vector corresponding to the target vehicle, and the third target charge and discharge power vector corresponding to the energy storage converter.

7. The S2G–V2G cooperative control method for energy storage charging stations according to claim 6, characterized in that, The step of converting the target power allocation scheme into control commands, and using the control commands to perform corresponding power coordination operations, includes: The first target charge / discharge power vector is converted into a first control command corresponding to the energy storage battery. Power allocation and adjustment are performed based on the second target charging and discharging power vector and the capability coefficient and demand weight corresponding to the target vehicle in each vehicle cluster to obtain the total power command of the vehicle cluster; the capability coefficient is determined based on the charging power threshold and the discharging power threshold corresponding to the target vehicle; the demand weight is determined based on the initial vehicle state of charge, the vehicle demand state of charge, and the user priority weight corresponding to the target vehicle. The total power command is converted into a second control command corresponding to the target vehicle, and the third target charging and discharging power vector is converted into a third control command corresponding to the energy storage converter; Based on the first control command, the second control command, and the third control command, perform corresponding power coordination operations.

8. An S2G–V2G collaborative control device for an energy storage charging station, characterized in that, include: The dataset determination module is used to determine the corresponding multi-source datasets based on the collaborative control requests issued by the power distribution network dispatch center or energy management system. The multi-source dataset includes energy storage side data corresponding to the energy storage charging station, vehicle side data corresponding to the target vehicle connected to the energy storage charging station, and grid side data corresponding to the power distribution network. The dataset input module is used to input the multi-source dataset into the target model to obtain the charging and discharging state vector and the initial power allocation vector of the energy storage charging station; the target model includes a preset energy storage state estimation model, a preset power flow model and a preset load prediction model; the initial power allocation vector is a vector reflecting the current power allocation between the energy storage charging station, the target vehicle and the power distribution network; The power interaction judgment module is used to determine whether the power interaction between the energy storage charging station and the power distribution network meets the preset optimization conditions based on the charging and discharging state vector and the initial power allocation vector. The collaborative execution module is used to construct a multi-objective optimization model using the target constraints and k-means clustering algorithm if the preset optimization conditions are met, perform distributed solution based on the multi-objective optimization model and using the alternating direction multiplier method to obtain the target power allocation scheme, and convert the target power allocation scheme into control commands to perform corresponding power collaborative execution operations using the control commands.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the S2G–V2G collaborative control method for an energy storage charging station as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the S2G–V2G collaborative control method for an energy storage charging station as described in any one of claims 1 to 7.

Images