Energy storage system optimization method and device for low-voltage transformer area, equipment and storage medium

Abstract

The invention relates to the field of power systems, and discloses an energy storage system optimization method, device and equipment for a low-voltage transformer area and a storage medium, and the method comprises the steps: obtaining the power load data, the power generation data of renewable energy sources, the meteorological data and the three-phase power grid data of the low-voltage transformer area at the current moment; predicting load data and power generation data of the low-voltage transformer area at the next time point of the current moment based on the power load data, the power generation data and the meteorological data by using a pre-trained prediction model; and determining balance parameters among phases in the three-phase power grid based on the electrical parameters of the phases in the three-phase power grid data by using the three-phase linear power grid model, and optimizing three-phase energy storage configuration parameters in the energy storage system according to the balance parameters, the predicted load data and the power generation data by using an improved genetic algorithm. According to the invention, the problems of low system operation efficiency and resource waste caused by inflexible matching of configuration and operation strategies of an existing energy storage system can be solved.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a method, device, equipment and storage medium for optimizing an energy storage system in a low-voltage area. Background Art

[0002] With the rapid development of renewable energy and the increasing complexity of low-voltage power loads, traditional power dispatch and energy storage management methods face severe challenges. Low-voltage power stations play a vital role in power supply. However, due to large load fluctuations and unstable renewable energy output, the stability and economic efficiency of power supply often fail to meet actual needs.

[0003] Existing low-voltage energy storage systems typically employ static configurations and simple, rule-based scheduling strategies. Due to a lack of dynamic optimization and intelligent scheduling, battery storage energy utilization efficiency is low, and the energy storage system configuration cannot flexibly respond to load fluctuations and energy changes. This results in insufficient energy storage equipment during peak loads or excessive energy storage during valley loads, failing to effectively mitigate the peak-valley variation in the power grid and impacting power system stability.

[0004] Therefore, there is an urgent need for a low-voltage substation energy storage system that can dynamically optimize configuration based on real-time data, and improve the configuration accuracy and operating efficiency of the energy storage system through data-driven methods to reduce unnecessary waste of resources. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for optimizing a low-voltage energy storage system in a low-voltage area to solve the problem that the configuration of the existing low-voltage energy storage system is inflexible, resulting in low system operating efficiency and waste of resources.

[0006] A first aspect of the present invention provides a method for optimizing an energy storage system in a low-voltage area, comprising:

[0007] Obtaining operating data for the current time period in the low-voltage substation, the operating data including power load data, renewable energy generation data, meteorological data, and three-phase power grid data;

[0008] Using a pre-trained prediction model, based on the power load data, the power generation data of the renewable energy source, and the meteorological data, the load data and the power generation data of the low-voltage substation for the prediction period are predicted;

[0009] A three-phase linear power grid model is used to determine the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data, and an improved genetic algorithm is used to optimize the three-phase energy storage configuration parameters in the energy storage system based on the balance parameters, predicted load data and power generation data.

[0010] In a feasible embodiment, the prediction model is a load prediction model based on a long short-term memory network (LSTM) and a power generation prediction model based on a support vector regression (SVR); the pre-trained prediction model is used to predict the load data and power generation data of the low-voltage substation at the next time point at the current moment based on the power load data, the power generation data of the renewable energy and the meteorological data, including: inputting the power load data into the load prediction model, extracting the first time series feature of the load at each time point in the power load data; calculating the load data of the predicted time period in the low-voltage substation based on each of the first time series features and the meteorological data; inputting the power generation data of the renewable energy into the power generation prediction model, extracting the second time series feature of the power generation at each time point in the power generation data of the renewable energy; and calculating the power generation data of the predicted time period in the low-voltage substation based on each of the second time series features and the meteorological data.

[0011] In a feasible embodiment, the three-phase linear power grid model is a model based on a three-phase power grid load flow algorithm; the use of the three-phase linear power grid model to determine the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data includes: using the three-phase power grid load flow algorithm to calculate the load flow of the three-phase power grid based on the voltage, current and power factor of each phase in the three-phase power grid data; using the three-phase unbalanced method to calculate the load proportion of each phase based on the load flow of the three-phase power grid, and using the load proportion of each phase as the balance parameter between the phases in the three-phase power grid.

[0012] In a feasible embodiment, the improved genetic algorithm is used to optimize the three-phase energy storage configuration parameters in the energy storage system according to the balance parameters, predicted load data and power generation data, including: obtaining all energy storage configuration schemes of the energy storage system in the current time period, and constructing an initial population based on all the energy storage configuration schemes, each individual of the initial population is an energy storage configuration scheme, and each energy storage configuration scheme includes the type, capacity, charging and discharging time and power of the energy storage device; calculating the fitness value of each individual based on the balance parameters, predicted load data and power generation data; selecting individuals whose fitness values meet the preset fitness threshold for crossover operations and mutation operations to generate a new population until convergence to the optimal solution, and optimizing the three-phase energy storage configuration parameters in the energy storage system based on the optimal solution, wherein the crossover operation is to select multiple individuals whose fitness values meet the preset fitness threshold for gene exchange, and the mutation operation is to crossover multiple individuals from different spatial dimensions.

[0013] In a feasible implementation, the calculation formula of the fitness value is:

[0014] F=

[0015] Where n is a certain forecast period, is the load power, is the power generation power, is the energy storage power, Fitness value of the previous time period.

[0016] In a feasible embodiment, after optimizing the three-phase energy storage configuration parameters in the energy storage system according to the balancing parameters, predicted load data, and power generation data using the improved genetic algorithm, the method further includes: generating a charge and discharge schedule for all devices in the energy storage system based on the optimized three-phase energy storage configuration parameters, predicted load data, and power generation data, wherein the charge and discharge schedule includes the charge and discharge time period, power, and priority of the device; obtaining real-time load data and power generation data for the predicted time period, and selecting a number of devices from the charge and discharge schedule according to the balancing parameters using an improved optimization strategy to perform dynamic scheduling planning to obtain a charge and discharge strategy, wherein the improved optimization strategy is a control strategy that adds linear programming to the fuzzy control algorithm; and scheduling each device in the energy storage system to perform charge and discharge operations based on the charge and discharge strategy.

[0017] In a feasible implementation, the improved optimization strategy is used to select a number of devices from the charge and discharge timing table according to the balance parameters for dynamic scheduling planning to obtain a charge and discharge strategy, including: calculating the data deviation between the real-time data and the predicted data within the prediction time period, the data deviation including the difference between the real-time load data and the predicted load data, and the difference between the real-time power generation data and the predicted power generation data; constructing a linear programming objective function for each device based on the balance parameters and the data deviation, wherein the linear programming objective function is ,in, is the unit energy cost during the charging and discharging period, is the absolute value of the charging and discharging power of the equipment, n is the predicted time period, t [0, n]; finding an optimal solution for the linear programming objective function, and selecting a plurality of devices from the charge and discharge timing table based on the optimal solution, and using a fuzzy control algorithm to fuzzify the parameters of the plurality of devices to obtain a charge and discharge strategy.

[0018] The second aspect of the present invention provides an energy storage system control device for a low-voltage substation, comprising: an acquisition module for acquiring working data at the current moment in the low-voltage substation, the working data including power load data, renewable energy power generation data, meteorological data and three-phase power grid data; a prediction module for using a pre-trained prediction model to predict the load data and power generation data of the low-voltage substation at the next time point at the current moment based on the power load data, the renewable energy power generation data and the meteorological data; an optimization module for using a three-phase linear power grid model to determine the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data, and using an improved genetic algorithm to optimize the three-phase energy storage configuration parameters in the energy storage system according to the balance parameters, predicted load data and power generation data.

[0019] The third aspect of the present invention provides an electronic device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the electronic device executes the above-mentioned low-voltage area energy storage system control method.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which, when executed on a computer, enables the computer to execute the above-mentioned method for controlling an energy storage system in a low-voltage area.

[0021] In the technical solution provided by the present invention, the working data of the current time period in the low-voltage substation is obtained, and the working data includes power load data, renewable energy power generation data, meteorological data and three-phase power grid data; a pre-trained prediction model is used to predict the load data and power generation data of the predicted time period in the low-voltage substation based on the power load data, the renewable energy power generation data and the meteorological data; a three-phase linear power grid model is used to determine the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data, and an improved genetic algorithm is used to optimize the three-phase energy storage configuration parameters in the energy storage system according to the balance parameters, the predicted load data and the power generation data. In the present invention, by real-time collection and analysis of the power load, power generation data, meteorological information and three-phase power grid data of the low-voltage substation, a three-phase power grid model and an improved genetic algorithm are used to dynamically adjust the configuration and operation strategy of the energy storage system to achieve configuration flexibility and improve the adaptability, economy and operation efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of an embodiment of a method for controlling an energy storage system in a low-voltage area according to an embodiment of the present invention;

[0023] Figure 2Schematic diagram of another embodiment of a method for controlling an energy storage system in a low-voltage area according to an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of an embodiment of an energy storage system control device for a low-voltage station area according to an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of another embodiment of the energy storage system control device for the low-voltage station area according to an embodiment of the present invention;

[0026] Figure 5 FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The embodiments of the present invention provide a method, device, equipment and storage medium for controlling an energy storage system in a low-voltage substation. Based on the analysis and prediction of real-time data, a three-phase linear power grid model and an improved genetic algorithm are used to optimize the configuration of the energy storage device, thereby meeting the power demand of the low-voltage substation to the greatest extent and avoiding the problems of over-configuration or under-configuration that may exist in traditional static configuration methods.

[0028] The terms "first," "second," "third," "fourth," and so on (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that shown or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[0029] It is understandable that the execution subject of the present invention can be an energy storage system optimization device in a low-voltage substation, or it can be a terminal or a local monitoring platform or a server, which is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example. There are multiple power generation equipment and energy storage equipment in the energy storage system of the low-voltage substation, and the equipment can be connected through a local area network. The equipment reports data to the server through the local area network, and the server performs unified scheduling and configuration optimization. The present invention realizes the configuration optimization of the low-voltage substation energy storage system by applying a prediction model, a three-phase power grid model and an improved genetic algorithm, thereby ensuring the load balance of the power grid and the efficient utilization of the battery system.

[0030] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1, an embodiment of the energy storage system control method of the low-voltage station area in the embodiment of the present invention includes:

[0031] 101. Obtain operating data of the current time period in the low-voltage substation, where the operating data includes power load data, renewable energy generation data, meteorological data, and three-phase power grid data.

[0032] It is understood that the current extreme working data of the low-voltage area is obtained through smart meters, meteorological sensors and power generation monitoring systems. The current time period should be understood as the time point when the resource allocation optimization of the energy storage system is triggered and the time length composed of T time points before the triggering time point, or the time for each completion of energy storage and scheduling. The working data specifically includes but is not limited to the following data:

[0033] Power load data: includes the power consumption of each user. The data is collected once a minute. Of course, based on the actual configuration optimization accuracy, the data can be customized to be less than 1 minute or even shorter.

[0034] Renewable energy power generation data: mainly obtains the real-time power generation of photovoltaic and wind power generation systems;

[0035] Meteorological data: such as temperature, wind speed, and light intensity, which affect load demand and power generation;

[0036] Three-phase grid data: Obtain grid parameters such as voltage, current, and power factor for each phase.

[0037] These data are uploaded to the server in real time and preprocessed, including data cleaning, missing value filling and normalization operations, to ensure the accuracy of subsequent predictive analysis.

[0038] 102. Using the pre-trained prediction model, the load data and power generation data of the forecast period in the low-voltage substation are predicted based on the power load data, power generation data and meteorological data.

[0039] It should be noted that the prediction time period can be the next time period of the current time period, or any time period after the current time period. The prediction model is actually a hybrid model containing two network structures, which are used to predict load data and power generation data respectively. Specifically, the prediction model is trained using a large amount of historical load data and historical power generation data respectively.

[0040] Specifically, when using a pre-trained prediction model to predict future load data and power generation data, it includes:

[0041] Load data forecasting uses a model derived from a long short-term memory (LSTM) network to perform time series forecasts on future load data. The input is the current power load data and the corresponding meteorological data. The LSTM model extracts the load variation characteristics from the input power load data to generate time series features with long-term dependencies. Based on these time series features and combined with meteorological data, the model predicts the load demand at the next point in time, thereby obtaining the corresponding load data.

[0042] Power Generation Forecast: This forecast uses a support vector regression (SVR) model to predict the power generation of renewable energy sources (such as photovoltaic and wind power). The input is the current power generation data and corresponding meteorological data (such as sunlight intensity and wind speed). SVR regresses this data to estimate future power generation, thereby generating power generation data.

[0043] Through the above two-step prediction, the load demand and power generation forecast results of the low-voltage substation in the future can be obtained, providing key input for the optimization of the energy storage system.

[0044] 103. Using a three-phase linear power grid model, the balance parameters between the phases in the three-phase power grid are determined based on the electrical parameters of each phase in the three-phase power grid data, and an improved genetic algorithm is used to optimize the three-phase energy storage configuration parameters in the energy storage system based on the balance parameters, predicted load data and power generation data.

[0045] This step can be understood as including two steps: load balancing analysis and configuration parameter optimization, where:

[0046] When using a three-phase power grid model for load balancing analysis, the load flow of the three-phase power grid is first calculated: based on the voltage, current, and power factor data of the three-phase power grid, a load flow algorithm is used to calculate the load distribution in the power grid to ensure that the current and voltage of each phase are within a reasonable range.

[0047] Then, the balancing parameters are calculated: the load percentage of each phase is calculated using the three-phase imbalance method to determine the degree of load imbalance in the three-phase grid. The calculated balancing parameters serve as key reference data for optimizing energy storage configuration.

[0048] When using the improved genetic algorithm to optimize energy storage configuration, first, an initial population is created: an initial population is constructed, and each individual in the population represents an energy storage configuration scheme, including the type, capacity, charging and discharging time period and power of the energy storage device.

[0049] Then calculate the fitness: use the predicted load data, power generation data and the balance parameters of the three-phase power grid to calculate the fitness of each energy storage configuration scheme.

[0050] Furthermore, individuals are selected: suitable individuals are selected based on fitness values, and crossover and mutation operations are performed to generate a new population.

[0051] Finally, converge to the optimal solution: After several generations of iteration, converge to the optimal solution and obtain the configuration plan of the energy storage equipment, including capacity, charging and discharging time and power distribution.

[0052] In summary, by acquiring real-time data from low-voltage substations and utilizing prediction modules, three-phase linear grid models, and improved genetic algorithms to dynamically configure the parameters of the energy storage system, the inflexible and irrational configuration issues of traditional energy storage systems are resolved. This makes the capacity, quantity, and operating mode of energy storage equipment more precise, minimizes the three-phase imbalance of the grid, improves grid stability, and reduces the investment and operating costs of the energy storage system.

[0053] See also Figure 2 Another embodiment of the method for controlling an energy storage system in a low-voltage area according to the present invention includes:

[0054] 201. Obtain the operating data of the energy storage system in the low-voltage substation.

[0055] It should be noted that the working data includes power load data, renewable energy generation data, meteorological data and three-phase power grid data, among which:

[0056] Power load data can be collected in real time using smart meters and sensors in low-voltage substations. This includes the real-time power demand of each electricity user (such as residential and commercial users). The data collection frequency can be set to 1 minute or less to ensure timely data.

[0057] Renewable energy data collection can use meteorological sensors and online monitoring platforms to collect real-time power generation and forecast data for renewable energy sources such as solar photovoltaics and wind power. For example, the power output of solar panels is affected by factors such as light intensity and temperature, while the output of wind turbines is affected by wind speed and direction.

[0058] Meteorological data (such as temperature, wind speed, humidity, and light intensity) can be collected through weather stations or third-party meteorological data platforms. Meteorological data has a significant impact on load demand and renewable energy generation, and is particularly important when predicting load fluctuations in low-voltage areas.

[0059] The collection of three-phase grid data can also be achieved using smart meters and sensors. The three-phase grid data includes three-phase current and three-phase voltage. The three-phase current and three-phase voltage of the low-voltage substation are collected in real time and used to analyze the load distribution and three-phase imbalance of the substation grid. The electrical characteristics of each phase of the grid can be accurately obtained.

[0060] In this embodiment, after the data is collected, the collected data is further transmitted and stored. Specifically, the data is transmitted to a server via a wireless network or a wired network and stored in a database on the server. It should be noted that when transmitting the data, a high-speed encrypted method is required to ensure low latency and high reliability to avoid loss of critical data.

[0061] Furthermore, before storage, data is cleaned and standardized to ensure quality and consistency. Cleaning primarily removes missing and outlier values and fills in missing load data. Standardization, which can be understood as data normalization, involves normalizing collected power load data (e.g., Min-Max normalization) to bring the data range into a standardized range, ensuring data stability and accuracy.

[0062] 202. Forecast of load and power generation data.

[0063] Specifically, the prediction is achieved using a prediction model, which is a load prediction model based on a long short-term memory network (LSTM) and a power generation prediction model based on a support vector regression (SVR).

[0064] For load data prediction, the power load data is input into the load forecasting model to extract the first time series features of the load at each time point in the power load data; based on each first time series feature and the meteorological data, the load data for the predicted time period in the low-voltage substation is calculated. The LSTM model specifically includes the following components: preprocessing layer, input layer, candidate layer, update layer, and output layer, where:

[0065] The preprocessing layer is composed of the forget gate, and its calculation formula is: , where f t is the output of the forget gate, σ is the Sigmoid activation function, W f is the weight matrix, which is the empirical value set by testing, b f is the bias term, h t−1 is the hidden state of the previous time step, x t It is the power load data at the current moment.

[0066] After the current power load data is input into the preprocessing layer, it is processed by the Sigmoid activation function to remove the environmental influencing factors in the power load data, and then output to the input layer.

[0067] In the input layer, the Sigmoid activation function is used to perform secondary activation processing on the preprocessed power load data. The process of the secondary activation processing is the same as that of the preprocessing layer. The difference is the weight matrix. A layer of weight is added to further optimize the elimination of environmental factors.

[0068] The power load data after secondary activation passes through the candidate layer and the update layer in sequence to record and update the features and output them to the output layer, thereby outputting the first time series features.

[0069] The candidate layer here can be understood as a candidate memory unit, and its formula is:

[0070] ,in, is a candidate memory feature.

[0071] The update layer can be understood as updating the memory unit, and its formula is: , where C t is the memory feature of the current time step, C t−1 is the memory feature of the previous time step.

[0072] Based on the above layers, the prediction formula of the load forecasting model is obtained:

[0073] ,in is the load forecast value at the next time point, is the load data at the past moment, is the temperature data at the current time point, is the humidity data at the current time point, and f is the function of the load forecasting model.

[0074] The time characteristics, lag characteristics and trend characteristics in the power load data are extracted, and the above time characteristics, lag characteristics and trend characteristics are formed into a feature matrix (i.e., the first time series characteristics), which is used as input to the load forecasting model to obtain the load forecast result for a period of time in the future (for example, 1 minute later).

[0075] For the prediction of power generation data, the power generation data of the renewable energy is input into the power generation prediction model, and the second time series characteristics of the power generation at each time point in the power generation data of the renewable energy are extracted; based on each second time series characteristic and the meteorological data, the power generation data of the predicted time period in the low-voltage station area is calculated; the calculation formula of the power generation prediction model is:

[0076] , where G(x) is the predicted power generation, is a kernel function (such as a Gaussian kernel), is the Lagrange multiplier, and b is the bias term.

[0077] It should be noted that the kernel function is used to map the input data into a high-dimensional feature space, thereby linearizing nonlinear problems in this high-dimensional space. Through this mapping, SVR can solve complex nonlinear regression problems. The kernel function transforms the data from the original space into a high-dimensional space, where classification or regression can be performed linearly without the need for explicit conversion calculations.

[0078] To select a kernel function, we first analyze the linear relationship between power generation at each time point in the power generation data. In renewable energy generation forecasts (such as solar and wind power), power generation often exhibits nonlinear characteristics, and the relationship between different features (such as meteorological data and historical power generation data) is complex. Therefore, based on this relationship, we select a kernel function that can capture nonlinear relationships. In this paper, the Gaussian radial basis kernel function (RBF kernel) is selected. Due to its parameterized form and favorable properties, this kernel function can effectively map input data into a high-dimensional space, enabling the model to linearize when dealing with nonlinear problems in high-dimensional space.

[0079] After determining that the kernel function is the RBF kernel function, it is also necessary to determine the core parameters and other hyperparameters. The core parameters are implemented through the cross-validation method. The specific steps are as follows:

[0080] Select a parameter range (e.g. test from 0.1 to 10).

[0081] Within this range, the model is trained and validated using the cross-validation method, and the prediction error (such as mean square error MSE) corresponding to the value of each core parameter is calculated.

[0082] The value that minimizes the validation error is selected as the final core parameter.

[0083] Other hyperparameters include penalty parameters and error tolerance, both of which are determined using cross-validation. Specifically:

[0084] The determination of penalty parameters includes:

[0085] The range of candidate values to be selected: The values usually selected are within a certain range, such as [10 −3 ,10 3 ].

[0086] Divide the training set and validation set: Divide the training data into multiple small subsets, use one of the subsets as the validation set, and the remaining subsets as the training set.

[0087] Grid search: Train and validate the model over a range of candidate values, selecting the value that minimizes the validation error.

[0088] Select the best value: Get the best value through cross validation.

[0089] The determination of the fault tolerance rate includes:

[0090] Select by experience: Typically, the value range is [0.01, 0.1]. Generally, a smaller value (such as 0.01) is chosen to start with, and then adjusted based on the results of cross-validation.

[0091] Cross-validation: As with the penalty parameter, cross-validation is used to determine the optimal value. Grid search is also a common selection method.

[0092] The hysteresis characteristics, meteorological characteristics, and periodic characteristics of the renewable energy power generation data are extracted, and the above hysteresis characteristics, meteorological characteristics, and periodic characteristics are formed into a feature matrix (i.e., the second time series characteristics), which is used as input into the power generation prediction model to obtain the power generation prediction result for a period of time in the future (for example, 1 minute later).

[0093] 203. Use the three-phase power grid model to calculate the balance parameters of the three-phase power grid.

[0094] Using a three-phase grid model, load flows are calculated based on real-time grid data, and the current, voltage, and power factor of each phase are obtained. The three-phase imbalance method is used to calculate the load proportion of each phase and determine the load balance parameters of the three-phase grid, providing a basis for optimizing the energy storage system.

[0095] In this embodiment, the three-phase power grid model is a model obtained by training using a three-phase power grid load flow algorithm. Based on this, when calculating the balance parameters, the three-phase power grid load flow algorithm is specifically used to calculate the load flow of the three-phase power grid based on the voltage, current and power factor of each phase in the three-phase power grid data; the three-phase unbalanced method is used to calculate the load proportion of each phase based on the load flow of the three-phase power grid, and the load proportion of each phase is used as the balance parameter between the phases in the three-phase power grid.

[0096] In practical applications, current and voltage data are extracted from the three-phase grid data and converted into corresponding vectors. The balance calculation formula is constructed using Ohm's theorem: V=Z*I, where V is the voltage vector, Z is the impedance matrix, and I is the current vector. Based on the results calculated by the above formula, the three-phase grid model is used to analyze the load imbalance degree of each phase of the grid. Based on the analyzed load imbalance degree, the balance parameters such as current, voltage and power factor in the three-phase grid are determined, and feedback signals are provided for subsequent energy storage system optimization.

[0097] In another feasible embodiment, when analyzing the load imbalance degree of each phase of the power grid, the current deviation and voltage deviation of each phase of the power grid are calculated, and a three-phase imbalance factor is used as an evaluation index of the power grid balance. The balance parameter is determined based on the evaluation index, wherein the calculation formula of the imbalance factor is:

[0098] ,in, is the current deviation, voltage deviation and power difference, is the three-phase current unbalance factor, is the current of the i-th phase.

[0099] The three-phase power grid load flow algorithm is actually used to process the voltage, phase angle and power distribution of each phase in the power grid, including:

[0100] Node voltage calculation: The relationship between the voltage magnitude and phase angle of each phase can be calculated using the load flow algorithm. Based on the phase difference between voltage and current, the current, power, and voltage balance in the three-phase power grid is solved.

[0101] Power calculation: Based on the voltage, current and power factor of each phase, calculate the active power (P) and reactive power (Q) of each phase (A, B, C) as follows:

[0102]

[0103]

[0104] in, Represent the voltage, current and power factor of phase A respectively.

[0105] Based on the current, voltage and power factor of the three-phase power grid, multiple calculations are performed until the calculation results converge, and the voltage, current and power distribution of each node and each phase are obtained, that is, the load flow of the three-phase power grid is obtained.

[0106] Then, based on the results of the load flow calculation, the differences in current, voltage, and power of each phase are calculated to obtain the three-phase imbalance of the power grid, including:

[0107] Current imbalance (ΔI):

[0108]

[0109] This formula is used to evaluate the difference between the three-phase currents. Large current imbalances may cause grid failures or equipment overloads.

[0110] Voltage imbalance (ΔV):

[0111]

[0112] Voltage imbalance will affect the normal operation of power equipment, resulting in reduced energy efficiency and increased equipment losses.

[0113] Power Imbalance: Calculates power imbalance by comparing the active power and reactive power of each phase. Large power imbalance may indicate that one phase is being supplied with too much or too little power.

[0114] Finally, based on the load flow calculation results and the analysis of the three-phase imbalance, the load proportion of each phase is calculated. The calculation method of the load proportion is:

[0115]

[0116] Among them, P A , P B , P C They are the active powers of phases A, B, and C in the three-phase power grid.

[0117] These load percentages reflect the contribution of each phase to the overall grid load and can inform energy storage device configuration. For phases with high load percentages, more energy storage will be allocated to these phases to achieve grid load balance.

[0118] Determine load balancing parameters: The calculated load percentage for each phase is used as a balancing parameter for subsequent energy storage configuration optimization. Based on the load percentage, an optimization algorithm can dynamically adjust the energy storage device's charging and discharging strategy to achieve load balancing between phases.

[0119] 204. Improve genetic algorithm to optimize energy storage configuration.

[0120] Specifically, an improved genetic algorithm (IGA) is used to optimize energy storage device configuration. The algorithm initializes the population, calculates fitness values, and performs crossover and mutation operations to select the optimal energy storage configuration. This process takes into account the capacity of the energy storage device, the charging and discharging time periods, and the power distribution.

[0121] It should be noted that the improved genetic algorithm used in the present invention has the following major improvements compared to the traditional genetic algorithm:

[0122] Individual selection strategy: By setting a preset balance value to screen excellent individuals for subsequent crossover and mutation operations, the convergence speed and optimization effect of the algorithm are improved.

[0123] Crossover and mutation operations: Through carefully designed crossover and mutation operations, the diversity of the population is increased, which helps the algorithm find the optimal solution in a wider search space and escape from the local optimal solution.

[0124] These improvements make the improved genetic algorithm more efficient and accurate in optimizing the configuration parameters of three-phase energy storage systems.

[0125] In practical applications, the steps for optimizing the three-phase energy storage configuration parameters in the energy storage system can be generally divided into the following steps:

[0126] Step 1, construct the initial population;

[0127] First, generate energy storage configuration plans: Based on parameters such as the type, capacity, charging and discharging time, and power of the energy storage equipment, generate a series of possible energy storage configuration plans.

[0128] Then, construct the initial population: the generated energy storage configuration scheme is used as the individual of the initial population, each individual represents an energy storage configuration scheme, and the size of the initial population should be determined according to the complexity of the problem and the computing resources.

[0129] Step 2, genetic algorithm iteration process;

[0130] First, calculate the fitness value: for each individual in the initial population, calculate its fitness value according to the fitness function, that is, calculate the adaptability of each individual in balancing the grid load and energy storage.

[0131] Then, the selection operation is performed: according to the fitness value, a part of excellent individuals are selected as parents for subsequent crossover and mutation operations; roulette wheel selection, tournament selection and other strategies can be used for selection operations.

[0132] It should be noted that the individual fitness is first evaluated, and the fitness function of each individual is set as:

[0133]

[0134] Among them, F(x i ) is individual x i The total fitness, f j (xi) is the individual x i The fitness value on the objective function j, ω j is the weight of objective function j, and M is the number of objective functions.

[0135] Then, in the individual selection, the fitness value of each individual is mapped to the selection probability. Assuming there are N individuals, the individual selection probability is:

[0136]

[0137] Among them, P(x i ) is individual x i The probability of being selected.

[0138] Finally, a weighted roulette wheel selection algorithm is used to randomly select individuals from the current population to enter the next generation based on probability. This means that the corresponding interval is set in the roulette wheel according to the fitness value of each individual, and individuals in the population are randomly selected.

[0139] Furthermore, crossover operation: perform crossover operation on the selected parent individuals to generate new individuals; the crossover operation can adopt strategies such as single-point crossover, double-point crossover, and uniform crossover.

[0140] During the crossover process, it should be ensured that the genes of the new individuals (i.e., some parameters of the energy storage configuration scheme) are within a reasonable range and meet the constraints of the power grid.

[0141] Assume there are two parent individuals and The crossover operation is as follows:

[0142] Generate crossover offspring: For each gene and , using a random exchange strategy:

[0143]

[0144] Among them, r j is a uniform random number, and r j ∈[0,1]. If r j <0.5, then the parent The gene of the parent is passed to the offspring y1, otherwise the parent The genes of the offspring y1 are passed on to the offspring y1. Similarly, the genes of the other offspring y2 come from the exchange of the parents.

[0145] Crossover probability: The crossover operation is performed only when certain probability conditions are met. The crossover probability is P c (usually Pc∈[0.6,0.9), that is:

[0146] , where C cross is the number of crossover operations performed, C total is the total number of individuals in the population.

[0147] Furthermore, mutation operation: mutation operation is performed on the newly generated individuals to further increase the diversity of the population; the mutation operation can adopt strategies such as random mutation and Gaussian mutation.

[0148] During the mutation process, it is also necessary to ensure that the genes of the new individuals are within a reasonable range and meet the constraints of the power grid.

[0149] For individual x=(x 1 ,x 2 ,...,xk )The mutation operation is as follows:

[0150] Randomly select genes for mutation: Assume that in the mutation operation, the mutation probability of each gene is P m , under the mutation probability, the individual's gene x i was changed to The specific formula is:

[0151]

[0152] Among them, r i is a random number, if r i <P m , then gene x i is replaced by a new random value (the value range depends on the specific problem), otherwise it remains unchanged.

[0153] Mutation probability: probability of mutation P m Usually low (such as P m =0.01 to P m = 0.1) to avoid excessively disturbing the excellent solutions that have been found.

[0154] Furthermore, the population is updated: new individuals generated after crossover and mutation operations are added to the population to replace some individuals with lower fitness; after the population is updated, the next round of iteration is carried out.

[0155] Step 3: Convergence judgment and output of optimal solution;

[0156] First, convergence judgment: During the iteration process, the average fitness value of the population or the fitness value of the optimal individual is calculated regularly; if the average fitness value or the fitness value of the optimal individual does not change significantly within a certain number of generations, or reaches a preset threshold, the algorithm is considered to have converged to the optimal solution.

[0157] Then, the optimal solution is output: when the algorithm converges to the optimal solution, the optimal solution is output as the three-phase energy storage configuration parameters in the energy storage system; at the same time, detailed information such as the fitness value of the optimal solution, the type, capacity, charging and discharging time and power of the energy storage device can be output.

[0158] Step 4: Subsequent processing and verification;

[0159] First, verify the optimal solution: Apply the obtained optimal solution to the actual energy storage system and perform simulation or experimental verification; by comparing the simulation or experimental results with the expected goals (such as the effect of load peak shaving and valley filling, the economic efficiency of the energy storage system, etc.), evaluate the feasibility and effectiveness of the optimal solution.

[0160] Then, optimization and adjustment: Based on the verification results, necessary adjustments and optimizations are made to the optimal solution to improve its performance and effect in practical applications.

[0161] In this embodiment, all energy storage configuration schemes of the energy storage system at the current moment are obtained, and an initial population is constructed based on all the energy storage configuration schemes. Each individual in the initial population is an energy storage configuration scheme, and each energy storage configuration scheme includes the type, capacity, charge and discharge time, and power of the energy storage device. The fitness value of each individual is calculated based on the balance parameters, predicted load data, and power generation data. Based on the fitness value, individuals whose balance degree meets the preset balance value are selected for crossover and mutation operations to generate a new population until convergence to the optimal solution. The three-phase energy storage configuration parameters in the energy storage system are optimized based on the optimal solution, wherein the crossover operation is to select multiple individuals whose balance degree reaches the preset balance value to exchange genes with each other, and the mutation operation is to crossover multiple individuals from different spatial dimensions.

[0162] It should be noted that after the fitness value of an individual in a certain time period is calculated based on the above fitness function, the fitness value of the next time period can be calculated directly based on the fitness value of a certain time period, that is, the above fitness function can be simplified to the following formula:

[0163] F= ,

[0164] Where n is a certain forecast period, is the load power, is the power generation power, is the energy storage power, is the fitness value of the previous time period.

[0165] Furthermore, the maintenance costs of equipment with different configurations also vary. Therefore, in the process of configuration optimization, in addition to optimizing the parameters, the efficiency of the individual equipment after the optimization is also maximized, including:

[0166] Maximizing Charge and Discharge Efficiency Costs: During energy storage system optimization, differences in charge and discharge efficiency across different energy storage devices directly impact operating costs. Energy storage devices with lower charge and discharge efficiency require more energy to complete the same charge and discharge tasks, increasing the operating costs of the power system. Therefore, when calculating fitness, the charge and discharge efficiency of each energy storage configuration must be considered, and the charge and discharge loss costs are calculated using the following formula:

[0167]

[0168] in, is the loss cost during the charging and discharging process, and are the charging power and discharging power in each period respectively, and are the charging and discharging efficiencies of the energy storage device, k3 is the coefficient of the charging and discharging loss cost, t is a time point in the prediction time period, t∈[0,N], and the prediction time period contains N time points.

[0169] The fitness function can be expressed by the following comprehensive formula:

[0170] ,in, and is the weight of each cost. The higher the fitness value, the better the energy storage configuration scheme performs in balancing grid load and energy storage.

[0171] 205. Dynamic scheduling and charge-discharge optimization.

[0172] Based on the optimized energy storage configuration parameters, a charge and discharge schedule is generated. Fuzzy control algorithms and linear programming (LP) are then used to dynamically optimize scheduling based on real-time grid load and power generation capacity changes. Ultimately, the charge and discharge strategies of the energy storage devices are adjusted to ensure grid load balance and reduce energy storage costs. This can be achieved through the following steps:

[0173] Step 1, define fuzzy variables and membership functions;

[0174] Determine input and output variables: According to the requirements of the control system, determine the variables that need to be controlled, such as data deviation, equipment charging and discharging power, etc. as input variables, and the specific parameters of the charging and discharging strategy as output variables.

[0175] Select membership function: Select an appropriate membership function for each fuzzy variable, such as triangular, trapezoidal, or Gaussian functions. The membership function is used to describe the fuzziness of the variable value and convert the clear value into a fuzzy value.

[0176] Define fuzzy sets: Based on the value ranges of input and output variables, define a series of fuzzy sets, such as "small", "medium", "large", etc. Each fuzzy set corresponds to a membership function.

[0177] Step 2, establish a fuzzy rule base;

[0178] Formulate fuzzy rules: Develop a series of fuzzy control rules based on expert experience and system requirements.

[0179] The rules are similar in form to the conditional statements of “if…then…”, such as “if the data deviation is small and the device power is low, then the charging and discharging strategy is stable”.

[0180] Storing rules: Store the formulated fuzzy rules in the rule base for subsequent reasoning.

[0181] Step 3, fuzzify input variables;

[0182] Calculate membership: Use membership function to convert the clear value of the input variable into fuzzy value, that is, calculate the membership of the input variable in each fuzzy set.

[0183] Construct fuzzy sets: Construct fuzzy sets of input variables based on the calculated membership degrees.

[0184] Step 4, fuzzy reasoning;

[0185] Matching rules: Match the corresponding rules in the rule base based on the fuzzy set of input variables.

[0186] Calculate output fuzzy sets: Use inference methods (such as maximin inference) to calculate the fuzzy sets of output variables. The inference process may involve the combination and operation of multiple rules.

[0187] Step 5, defuzzify the output variables;

[0188] Select a defuzzification method: Choose an appropriate defuzzification method based on actual needs, such as the centroid method, maximum membership method, or weighted average method.

[0189] Compute crisp output values: Converts the fuzzy sets of output variables into crisp control output quantities using the selected defuzzification method.

[0190] Step 6: Application and optimization;

[0191] Implementation control: Apply the calculated clear output to the actual system to achieve dynamic scheduling planning of charging and discharging strategies.

[0192] Monitoring and adjustment: During actual application, the system performance and changes in output variables are continuously monitored.

[0193] The membership function, fuzzy set and rule base are adjusted according to the monitoring results to optimize the control performance.

[0194] In this embodiment, after optimizing the three-phase energy storage configuration parameters in the energy storage system according to the balancing parameters, the predicted load data, and the power generation data using an improved genetic algorithm, the following steps are further included:

[0195] Generate a charge and discharge schedule for all devices in the energy storage system based on the optimized three-phase energy storage configuration parameters, predicted load data, and power generation data, wherein the charge and discharge schedule includes the device's charge and discharge time period, power, and priority;

[0196] Acquire real-time load data and power generation data for a forecast period, and use an improved optimization strategy to select a number of devices from the charge and discharge timing table according to the balance parameters for dynamic scheduling planning to obtain a charge and discharge strategy, wherein the improved optimization strategy is a control strategy that adds linear programming to a fuzzy control algorithm;

[0197] The devices in the energy storage system are scheduled to perform charging and discharging operations based on the charging and discharging strategy.

[0198] In practical applications, based on predicted load data, power generation data and grid load flow analysis results, a charging and discharging schedule for energy storage equipment is generated to optimize the selection of charging and discharging time periods, including the selection of battery charging periods and the priority setting of discharge periods.

[0199] Assume that in a low-voltage substation, after optimizing the three-phase energy storage system configuration parameters and analyzing the predicted load and power generation data, the following charge and discharge schedule for the energy storage system devices is obtained. For example, for a group of energy storage devices, device A charges from 0:00 AM to 6:00 AM, charges 500 kWh, and has a high priority; device B discharges from 6:00 PM to 10:00 PM, discharges 300 kWh, and has a medium priority. This information forms the basis for scheduling the charge and discharge schedules for all devices in the energy storage system, providing an initial plan for subsequent dynamic scheduling.

[0200] During the forecast period (e.g., 6:00 PM to 10:00 PM), real-time load and power generation data for the low-voltage substation is collected through smart meters and a power generation monitoring system. Assume that the real-time load data shows that the actual load at 7:00 PM is 50 kW higher than the forecast, and the real-time power generation data shows that the photovoltaic power generation is 30 kW lower than the forecast.

[0201] Furthermore, after obtaining the charge and discharge schedule, a fuzzy control algorithm (FLC) is used to dynamically adjust the charge and discharge strategy of the energy storage device based on real-time grid load, power generation capacity, and grid imbalance data. The fuzzy control rules are as follows: , where M is the number of rules, Output(t) is the charging and discharging decision of the energy storage device, is a fuzzy rule, Input variables, such as real-time load and power generation, are used; according to the dynamically adjusted charging and discharging strategy, the charging and discharging power distribution of the energy storage equipment is optimized to minimize the grid load fluctuation and maximize the operating efficiency of the energy storage system.

[0202] The step of dynamically scheduling the charge and discharge schedule according to the balance parameters using the improved optimization strategy to obtain a charge and discharge strategy includes:

[0203] Calculate the data deviation between the real-time data and the predicted data within the prediction time period, the data deviation includes the difference between the real-time load data and the predicted load data, and the difference between the real-time power generation data and the predicted power generation data; construct the linear programming objective function of each device based on the balance parameter and the data deviation, wherein the linear programming objective function is ,in, is the unit energy cost during the charging and discharging period, is the absolute value of the charging and discharging power of the device, and n is the prediction time period; an optimal solution is obtained for the linear programming objective function, and based on the optimal solution, several devices are selected from the charging and discharging timing table, and the parameters of the several devices are fuzzy processed using a fuzzy control algorithm to obtain a charging and discharging strategy.

[0204] This linear programming objective function uses absolute value constraints on charge and discharge power to eliminate negative power fluctuations during the charge and discharge process, ensuring smooth charging and discharging, and reducing battery energy losses during charging and discharging. This approach can effectively improve the efficiency of energy storage systems, especially when charging and discharging frequently change, and avoid damage to the battery due to excessive power fluctuations.

[0205] Calculating data deviations: At 7:00 PM, the real-time load data was 800 kW, while the forecasted load data was 750 kW, a difference of 50 kW. The real-time power generation data was 100 kW, while the forecasted power generation data was 130 kW, a difference of -30 kW. These data deviations reflect the difference between actual power conditions and forecasts and are crucial for formulating subsequent dispatch strategies.

[0206] Constructing a linear programming objective function: Given a unit energy cost of 0.5 yuan / kWh for the charging and discharging time period (e.g., 7:00 PM to 8:00 PM), a linear programming objective function is constructed for each device based on balancing parameters (e.g., the required power supplement for phase A to balance the grid) and data deviations. For devices A and B, their possible charge and discharge powers are substituted into the function. Taking into account the device's charge and discharge capacity limitations (e.g., the maximum discharge power of device A is 100 kW, and the maximum discharge power of device B is 80 kW), the optimal charge and discharge power combination that satisfies grid balance and device constraints is determined through calculation.

[0207] Solve for the optimal solution and select devices: Use a linear programming algorithm to solve the objective function and obtain the optimal solution. Suppose the optimal solution indicates that device A should discharge at 50 kW and device B should discharge at 50 kW. Based on this result, devices A and B are selected from the charge and discharge schedule to participate in this scheduling.

[0208] Fuzzy processing to obtain charging and discharging strategies: Fuzzy control algorithms are used to fuzzify the charging and discharging parameters of devices A and B. For example, based on factors such as real-time grid load fluctuations and the current remaining power of the device, parameters such as the device's charging and discharging power and charging and discharging time are fuzzified into fuzzy sets such as "high," "medium," and "low." For device A, its discharge power of 50kW is fuzzified to "medium," and the discharge time is adjusted based on the remaining power and grid demand; similar fuzzy processing is performed for device B. Ultimately, these fuzzified parameters are combined to obtain a specific charging and discharging strategy, such as device A continuously discharging at a medium discharge power from 7:00 PM to 8:00 PM, and device B also discharging at a medium discharge power during the same time period. Dynamic adjustments are made based on real-time conditions to ensure grid load balance and efficient operation of the energy storage system.

[0209] Furthermore, after obtaining the charging and discharging strategy, it also includes: solving the optimal energy storage equipment scheduling strategy based on constraints such as energy storage capacity and charging and discharging time windows to maximize the economic benefits of the energy storage system; real-time feedback of scheduling results, and adjustment based on changes in grid load to ensure that the charging and discharging energy of the energy storage equipment is minimized, while reducing the operating costs of the grid.

[0210] It is understandable that the constraints specifically include:

[0211] The charging power of the energy storage device must not exceed its maximum capacity ;

[0212] The discharge power of the energy storage device shall not exceed its maximum discharge capacity ;

[0213] The charging and discharging process of the energy storage device must meet the grid load balance, that is:

[0214] ,in, is the charging power in the i-th period, is the discharge power in the jth period, ensuring that the energy storage system effectively balances the grid load;

[0215] By setting the above constraints, we can ensure that the charging and discharging behavior of the energy storage device does not exceed its capacity, and maximize the operating efficiency of the energy storage device while meeting the load balance of the power grid.

[0216] At this time, the fuzzy control rules used in the dynamic scheduling of the charging and discharging strategy of the energy storage device using the fuzzy control algorithm (FLC) include but are not limited to any of the following:

[0217] Input conditions include: grid load fluctuations, power generation changes, and the current status of energy storage devices (such as remaining capacity, charge and discharge efficiency, etc.);

[0218] Output conditions include: charging power, discharging power, charging and discharging priority of energy storage equipment;

[0219] By utilizing fuzzy control algorithms, it is possible to flexibly handle complex and uncertain grid load fluctuations and adjust the charging and discharging strategies of energy storage devices based on real-time data to ensure stable system operation.

[0220] In summary, the fuzzy control algorithm can quickly set fuzzy rules for load, power generation, and grid imbalance, and output charging and discharging decisions, making this method applicable to energy storage systems with various hardware configurations. Linear programming (LP) is also used to minimize the total energy loss and cost of charging and discharging energy storage equipment. Constraints include energy storage capacity and charging and discharging limits, which can mitigate the problem of system stalls caused by parameter fluctuations.

[0221] 206. Scheduling execution and real-time feedback.

[0222] Based on dynamic scheduling results, energy storage device charging and discharging operations are executed in real time. Grid load changes and the operating status of energy storage devices are monitored in real time, and charging and discharging strategies are adjusted to address load fluctuations. A feedback mechanism ensures the operating efficiency of energy storage devices and grid stability.

[0223] Specifically, this step includes: continuously optimizing the configuration of the energy storage system based on real-time grid load, power generation data, and status monitoring data of energy storage equipment to ensure that the energy storage system can flexibly respond to different load scenarios; adjusting the capacity allocation and charging and discharging strategies of energy storage equipment when grid load fluctuates greatly to reduce the impact of grid imbalance on power system stability; and conducting long-term optimized scheduling based on the health status and service life of energy storage equipment to ensure that high operating efficiency and stability are maintained throughout the equipment's life cycle.

[0224] In an embodiment of the present invention, by real-time collection and analysis of the power load, power generation data, meteorological information and three-phase power grid data of the low-voltage substation, a three-phase power grid model and an improved genetic algorithm are used to dynamically adjust the configuration and operation strategy of the energy storage system to achieve configuration flexibility and improve the adaptability, economy and operation efficiency of the system.

[0225] The three-phase grid model is used to realize load flow analysis and energy storage optimization of the three-phase grid, which minimizes the three-phase imbalance of the grid, improves the stability of the grid, and reduces the investment and operating costs of the energy storage system.

[0226] Fuzzy control algorithms and linear programming are used to flexibly adjust the charging and discharging strategies of energy storage equipment according to factors such as changes in grid load and fluctuations in renewable energy generation, thereby improving the responsiveness and adaptability of the energy storage system.

[0227] The above describes the energy storage system control method of the low-voltage area in the embodiment of the present invention. The following describes the energy storage system control device of the low-voltage area in the embodiment of the present invention. Figure 3 and 4 , an embodiment of the energy storage system control device of the low-voltage station area in an embodiment of the present invention, the device includes:

[0228] An acquisition module 310 is configured to acquire operating data of a low-voltage substation in a current time period, wherein the operating data includes power load data, renewable energy generation data, meteorological data, and three-phase power grid data;

[0229] A prediction module 320 is configured to use a pre-trained prediction model to predict the load data and power generation data for a prediction period in the low-voltage substation based on the power load data, the power generation data of the renewable energy, and the meteorological data;

[0230] The optimization module 330 is used to use a three-phase linear power grid model to determine the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data, and to use an improved genetic algorithm to optimize the three-phase energy storage configuration parameters in the energy storage system based on the balance parameters, predicted load data, and power generation data.

[0231] Optionally, the prediction model is a load prediction model based on a long short-term memory network (LSTM) and a power generation prediction model based on a support vector regression (SVR);

[0232] The prediction module 320 includes:

[0233] The first prediction unit 321 is configured to input the power load data into the load prediction model, extract the first time series characteristics of the load at each time point in the power load data, and calculate the load data of the low-voltage substation at the next time point at the current moment based on each of the first time series characteristics and the meteorological data;

[0234] The second prediction unit 322 is used to input the power generation data of the renewable energy into the power generation prediction model, extract the second time series characteristics of the power generation at each time point in the power generation data of the renewable energy; and calculate the power generation data of the low-voltage substation at the next time point of the current time point based on each second time series characteristic and the meteorological data.

[0235] Optionally, the three-phase linear power grid model is a model based on a three-phase power grid load flow algorithm;

[0236] The optimization module 330 includes a calculation unit 331, which is used to:

[0237] Utilizing the three-phase power grid load flow algorithm, the load flow of the three-phase power grid is calculated based on the voltage, current and power factor of each phase in the three-phase power grid data;

[0238] The three-phase unbalance method is used to calculate the load proportion of each phase based on the load flow of the three-phase power grid, and the load proportion of each phase is used as the balance parameter between the phases in the three-phase power grid.

[0239] The optimization module 330 includes: an optimization unit 332 for

[0240] Obtain all energy storage configuration schemes of the energy storage system at the current moment, and construct an initial population based on all the energy storage configuration schemes, where each individual in the initial population is an energy storage configuration scheme, and each energy storage configuration scheme includes the type, capacity, charge and discharge time, and power of the energy storage device;

[0241] Calculating the fitness value of each individual based on the balance parameter, the predicted load data and the power generation data;

[0242] Individuals whose fitness values meet a preset fitness threshold are selected for crossover and mutation operations to generate a new population until convergence to an optimal solution, and the three-phase energy storage configuration parameters in the energy storage system are optimized based on the optimal solution, wherein the crossover operation is to select multiple individuals whose fitness values meet a preset fitness threshold to exchange genes with each other, and the mutation operation is to crossover multiple individuals from different spatial dimensions.

[0243] Optionally, the calculation formula of the fitness value is:

[0244] F= , where n is a certain forecast period, is the load power, is the power generation power, is the energy storage power, is the fitness value of the previous time period.

[0245] Optionally, the apparatus further includes a scheduling module 340, configured to:

[0246] Generate a charge and discharge schedule for all devices in the energy storage system based on the optimized three-phase energy storage configuration parameters, predicted load data, and power generation data, wherein the charge and discharge schedule includes the device's charge and discharge time period, power, and priority;

[0247] Acquire real-time load data and power generation data for a forecast period, and use an improved optimization strategy to select a number of devices from the charge and discharge timing table according to the balance parameters for dynamic scheduling planning to obtain a charge and discharge strategy, wherein the improved optimization strategy is a control strategy that adds linear programming to a fuzzy control algorithm;

[0248] The devices in the energy storage system are scheduled to perform charging and discharging operations based on the charging and discharging strategy.

[0249] Optionally, the scheduling module 340 is specifically configured to:

[0250] Calculating a data deviation between real-time data and predicted data within a prediction time period, wherein the data deviation includes a difference between real-time load data and predicted load data, and a difference between real-time power generation data and predicted power generation data;

[0251] A linear programming objective function of each device is constructed based on the balance parameter and the data deviation, wherein the linear programming objective function is ,in, is the unit energy cost during the charging and discharging period, is the absolute value of the charging and discharging power of the equipment, and n is the prediction time period;

[0252] An optimal solution is obtained for the linear programming objective function, and based on the optimal solution, several devices are selected from the charge and discharge timing table. A fuzzy control algorithm is used to fuzzify the parameters of the several devices to obtain a charge and discharge strategy.

[0253] In an embodiment of the present invention, the current power load data, renewable energy generation data, meteorological data, and three-phase grid data of the low-voltage substation are obtained; a pre-trained prediction model is used to predict the load data and power generation data of the low-voltage substation at the next time point based on the power load data, power generation data, and meteorological data; a three-phase linear grid model is used to determine the balance parameters between the phases in the three-phase grid based on the electrical parameters of each phase in the three-phase grid data; and an improved genetic algorithm is used to optimize the three-phase energy storage configuration parameters in the energy storage system based on the balance parameters, predicted load data, and power generation data. This solves the problem that the existing energy storage system configuration is inflexible in matching the operation strategy, resulting in low system operation efficiency and resource waste.

[0254] above Figure 3 and Figure 4 The energy storage system control device of the low-voltage area in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic equipment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0255] See also Figure 5 As shown, the electronic device includes a processor 500 and a memory 501, wherein the memory 501 stores machine executable instructions that can be executed by the processor 500, and the processor 500 executes the machine executable instructions to implement the above-mentioned energy storage system control method for the low-voltage station area.

[0256] Further, Figure 5 The electronic device shown further includes a bus 502 and a communication interface 503 , and the processor 500 , the communication interface 503 and the memory 501 are connected via the bus 502 .

[0257] The memory 501 may include a high-speed random access memory (RAM) and may also include a non-volatile memory (non-volatile memory), for example, at least one disk storage. The communication connection between the system network element and at least one other network element is achieved through at least one communication interface 503 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 502 may be an ISA bus, a PCI bus, or an EISA bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0258] The processor 500 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the processor 500. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 501 , and the processor 500 reads the information in the memory 501 and completes the method steps of the aforementioned embodiment in combination with its hardware.

[0259] The present invention also provides an electronic device, wherein the computer device includes a memory and a processor, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the energy storage system control method of the low-voltage area in the above-mentioned embodiments.

[0260] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the energy storage system control method for the low-voltage area.

[0261] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0262] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0263] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing an energy storage system in a low-voltage area, characterized in that: The steps include: Data acquisition step: obtaining the working data of the low-voltage substation in the current time period, including power load data, renewable energy generation data, meteorological data and three-phase power grid data; Data prediction step: using a pre-trained prediction model to predict the load data and power generation data for the prediction time period in the low-voltage substation based on the power load data, the power generation data of the renewable energy source, and the meteorological data; wherein the prediction model includes a load prediction model based on a long short-term memory network and a power generation prediction model based on support vector regression; Configuration optimization step: using a three-phase linear power grid model, determining the balance parameters between the phases in the three-phase power grid based on the electrical parameters of each phase in the three-phase power grid data, and using an improved genetic algorithm to optimize the three-phase energy storage configuration parameters in the energy storage system according to the balance parameters, predicted load data and power generation data, and controlling the operation scheduling of the energy storage system based on the optimized parameters, wherein the three-phase linear power grid model is a model based on a three-phase power grid load flow algorithm.

2. The method for optimizing the energy storage system in a low-voltage area according to claim 1, characterized in that: The data prediction step includes: Inputting the power load data into the load forecasting model, and extracting the first time series feature of the load at each time point in the power load data; Calculating the load data of the predicted time period in the low-pressure area based on each of the first time series features and the meteorological data; Inputting the power generation data of the renewable energy into the power generation prediction model, and extracting the second time series feature of power generation at each time point in the power generation data of the renewable energy; The power generation data of the predicted time period in the low-voltage station area is calculated based on each of the second time series features and the meteorological data.

3. The method for optimizing the energy storage system in a low-voltage area according to claim 1, characterized in that: The step of determining the balance parameters between the phases in the three-phase power grid in the configuration optimization step includes: Utilizing the three-phase power grid load flow algorithm, the load flow of the three-phase power grid is calculated based on the voltage, current and power factor of each phase in the three-phase power grid data; The three-phase unbalance method is used to calculate the load proportion of each phase based on the load flow of the three-phase power grid, and the load proportion of each phase is used as the balance parameter between the phases in the three-phase power grid.

4. The method for optimizing the energy storage system in a low-voltage area according to claim 1, characterized in that: The configuration optimization step optimizes the three-phase energy storage configuration parameters in the energy storage system according to the balancing parameters, the predicted load data, and the power generation data, including: Obtain all energy storage configuration schemes for the energy storage system in the current time period, and construct an initial population based on all the energy storage configuration schemes, where each individual in the initial population is an energy storage configuration scheme, and each energy storage configuration scheme includes the type, capacity, charge and discharge time, and power of the energy storage device; Calculating the fitness value of each individual based on the balance parameter, the predicted load data and the power generation data; Individuals whose fitness values meet a preset fitness threshold are selected for crossover and mutation operations to generate a new population until convergence to an optimal solution, and the three-phase energy storage configuration parameters in the energy storage system are optimized based on the optimal solution, wherein the crossover operation is to select multiple individuals whose fitness values meet a preset fitness threshold to exchange genes with each other, and the mutation operation is to crossover multiple individuals from different spatial dimensions.

5. The method for optimizing the energy storage system in a low-voltage area according to claim 4, characterized in that: The calculation formula of the fitness value is: F= ; Where n is a certain forecast period, is the load power, is the power generation power, is the energy storage power, is the fitness value of the previous time period.

6. The method for optimizing the energy storage system in a low-voltage area according to claim 1, characterized in that: After the configuration optimization step, the method further includes: Generate a charge and discharge schedule for all devices in the energy storage system based on the optimized three-phase energy storage configuration parameters, predicted load data, and power generation data, wherein the charge and discharge schedule includes the device's charge and discharge time period, power, and priority; Acquire real-time load data and power generation data for a forecast period, and use an improved optimization strategy to select a number of devices from the charge and discharge timing table according to the balance parameters for dynamic scheduling planning to obtain a charge and discharge strategy, wherein the improved optimization strategy is a control strategy that adds linear programming to a fuzzy control algorithm; The devices in the energy storage system are scheduled to perform charging and discharging operations based on the charging and discharging strategy.

7. The method for optimizing the energy storage system in a low-voltage area according to claim 6, characterized in that: The improved optimization strategy is used to select a plurality of devices from the charge and discharge timing table according to the balance parameters for dynamic scheduling planning to obtain a charge and discharge strategy, including: Calculating a data deviation between real-time data and predicted data within a prediction time period, wherein the data deviation includes a difference between real-time load data and predicted load data, and a difference between real-time power generation data and predicted power generation data; A linear programming objective function of each device is constructed based on the balance parameter and the data deviation, wherein the linear programming objective function is ,in, is the unit energy cost during the charging and discharging period, is the absolute value of the charging and discharging power of the equipment, and n is the prediction time period; An optimal solution is obtained for the linear programming objective function, and based on the optimal solution, several devices are selected from the charge and discharge timing table. A fuzzy control algorithm is used to fuzzify the parameters of the several devices to obtain a charge and discharge strategy.

8. A low-voltage energy storage system optimization device, characterized in that: The device comprises: A data acquisition module is used to obtain operating data of the current time period in the low-voltage substation, wherein the operating data includes power load data, renewable energy generation data, meteorological data, and three-phase power grid data; a data prediction module, configured to use a pre-trained prediction model to predict the load data and power generation data for the prediction time period in the low-voltage substation based on the power load data, the power generation data of the renewable energy source, and the meteorological data; wherein the prediction model is a load prediction model based on a long short-term memory network and a power generation prediction model based on support vector regression; a configuration optimization module for determining, using a three-phase linear power grid model, balance parameters between phases in the three-phase power grid based on electrical parameters of each phase in the three-phase power grid data, optimizing the three-phase energy storage configuration parameters in the energy storage system based on the balance parameters, predicted load data, and power generation data using an improved genetic algorithm, and controlling the operation of the energy storage system based on the optimized parameters, wherein the three-phase linear power grid model is a model based on a three-phase power grid load flow algorithm.

9. An electronic device, characterized in that: The electronic device comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the electronic device to execute the energy storage system optimization method for a low-voltage station area according to any one of claims 1 to 7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the low-voltage area energy storage system optimization method according to any one of claims 1 to 7 is implemented.

Images