Optimized dispatching control method and system for transformer area energy storage

Abstract

The invention discloses an optimized dispatching control method and system for transformer area energy storage, and relates to the technical field of energy storage dispatching, and the method comprises the following steps: integrating an intelligent load management system with an energy storage system, thereby monitoring the electrical load of a transformer area in real time, and feeding back the real-time data to the energy storage system; historical load data and electricity price data are collected, a prediction model is trained, future load and electricity price are predicted in real time, and prediction data are generated. And according to a prediction result, a preliminary energy storage system scheduling strategy is formulated, and a target function R is constructed, so that the target function R can dynamically adapt to changing load and electricity price conditions. According to the invention, through tight integration of the intelligent load management system and the energy storage system, real-time monitoring of the power grid load and efficient scheduling of the energy storage system are realized; in other words, the energy storage system can charge or discharge at the best time in combination with accurate load and electricity price prediction and scheduling strategy rules, power grid resources are utilized to the maximum extent, and unnecessary resource waste is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage scheduling, and in particular to an optimization scheduling control method and system for energy storage in a substation. Background Art

[0002] With the development of energy internet, the application of distributed energy and energy storage technology is becoming more and more extensive. As a key component of the power system, the regional energy storage system can effectively balance the grid load, reduce the peak-to-valley difference of the grid, and improve the absorption capacity of renewable energy. In the existing regional energy storage management system, the main technical problems are:

[0003] Inaccurate load and electricity price forecasts: Existing energy storage dispatch systems have insufficient accuracy in predicting future grid load and electricity prices. Most systems rely on simple historical data statistical methods or traditional linear regression models, which results in an inability to provide accurate forecast results when faced with complex and changing grid load and electricity price environments, thus affecting the dispatch effect of the energy storage system;

[0004] Inflexible dispatching strategies: Existing energy storage dispatching strategies are usually based on preset rules or empirical rules, lacking the ability to respond to dynamic changes in the power grid in real time, making it difficult for energy storage systems to effectively respond to instantaneous changes in load demand and electricity price fluctuations. This rigid dispatching strategy cannot fully tap the potential of energy storage systems, nor can it maximize economic benefits. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems existing in the above-mentioned existing optimized dispatching control method and system of substation energy storage, the present invention is proposed.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] A method for optimizing the dispatching and controlling of energy storage in a substation area, the method comprising the following steps:

[0009] Step 1: Integrate the intelligent load management system with the energy storage system to monitor the power load in the substation in real time and feed back the real-time data to the energy storage system;

[0010] Step 2: Collect historical load data and electricity price data, identify the patterns of load changes and electricity price fluctuations, use the support vector machine model to train the prediction model so that it can accurately predict future loads and electricity prices, use the established prediction model, continuously input real-time data into the prediction model, make real-time predictions of future loads and electricity prices, and generate prediction data;

[0011] Step 3: Based on the prediction results, formulate a preliminary energy storage system scheduling strategy and construct the objective function R so that it can dynamically adapt to changing load and electricity prices.

[0012] As a preferred solution of the method for optimizing dispatching and controlling energy storage in a substation according to the present invention, the training process of the model in step 2 is as follows:

[0013] Preprocess the collected historical load data and electricity price data, handle missing values ​​and outliers, denoise the data, and standardize the data:

[0014] Among them, X is the original data, μ is the mean, and σ is the standard deviation;

[0015] The data set is divided into training set and test set in a ratio of 80:20;

[0016] The training set data is used to train the SVM model, and the prediction expression of the training model is obtained as follows:

[0017]

[0018] Where x is the input feature vector, α i is the Lagrange multiplier, y i is the label of the training sample, K(x i ,x is the kernel function, and its expression is: K(x i ,x)=exp(-γ||x i -x j || 2 ), γ is the kernel parameter, x i and x j is the input vector and b is the bias term.

[0019] As a preferred solution of the optimization dispatching control method of the substation energy storage described in the present invention, the goal of the training process of the SVM model is to minimize the following optimization problem:

[0020]

[0021] Among them, w is the weight vector, b is the bias term, ξ i is the slack variable, C is the penalty parameter, and n is the number of samples;

[0022] The constraints are:

[0023] y i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0, Among them, y i is the label, φ(x i ) is the feature mapping function;

[0024] Through the above minimization optimization operation, the model parameters w and α are solved. i and b, and use them directly in the final SVM prediction expression.

[0025] As a preferred solution of the optimization dispatching control method of the substation energy storage described in the present invention, the prediction process of the SVM model is:

[0026] The preprocessed real-time data x real-time Input it into the trained SVM model and use the model expression to make predictions. The prediction result is

[0027] The predicted future load and electricity price data are stored in the database as a basis for the subsequent dispatch strategy formulation;

[0028] Determine the forecast time window based on the update frequency of real-time data; update real-time data every 15-30 minutes;

[0029] The predicted load and electricity price curves are visualized to facilitate real-time monitoring and evaluation by the dispatching system and management personnel.

[0030] As a preferred solution of the method for optimizing dispatching and controlling energy storage in a substation according to the present invention, the process of formulating the preliminary dispatching strategy is as follows:

[0031] The forecast data set generated by the SVM model includes the load demand L for each time period in the future. t and electricity price p t , according to the intelligent load management system, obtain the current state of charge S0C, maximum charge and discharge power Pmax, minimum SOC (to prevent over-discharge) and maximum SOC (to prevent over-charging);

[0032] Load peak and valley identification: Based on the predicted load data L t , identify the peak and trough periods of future load; usually, the load is higher during peak periods and lower during trough periods; electricity price fluctuation analysis: analyze the electricity price p t The fluctuation of electricity prices can determine the high and low points of electricity prices;

[0033] Then formulate the strategy decision logic:

[0034] d. Charging when electricity prices are low: During periods of low electricity prices (below a certain threshold p low ), if the SOC of the energy storage system is less than the maximum SOC, a charging plan is formulated and the charging power P is calculated. charge ;

[0035] The calculation of charging power takes into account the current grid load L t and the maximum charging power Pmax of the energy storage system to ensure that no additional load pressure is placed on the power grid;

[0036] P charge =min(Pmax,Available Capacity,Grid Load Constraint)

[0037] e. Discharge when electricity price is high: During the period of high electricity price (above a certain threshold p high ), if the SOC of the energy storage system is higher than the minimum SOC, a discharge plan is formulated and the discharge power P is calculated. discharge ; The calculation of discharge power must ensure that the SOC does not drop below the minimum SOC while meeting the requirement of maximizing economic benefits; P discharge =min(Pmax,AvailableEnergy,Grid Load Requirement);

[0038] f, Load balance: During the peak load period, i.e. L t Exceeding a certain threshold L high When the load is low, the energy storage system discharges first to balance the load and reduce the pressure on the grid; t Below a certain threshold L low When charging, the energy storage system is charged first to absorb excess power and increase the overall stability of the system;

[0039] Combining the above logic and formula, a preliminary energy storage scheduling plan is generated, including the charging power P for each time period. charge,t and discharge power P discharge,t .

[0040] As a preferred solution of the optimization dispatching control method of the substation energy storage described in the present invention, the objective function of the dispatching strategy is defined as:

[0041]

[0042] Among them, R is the total revenue; P discharge,t and P charge,t are the discharge and charging power of the energy storage system at time t; pt is the electricity price at time t;

[0043] The scheduling strategy is formulated to maximize the objective function R, that is, to maximize the net benefit of the energy storage system.

[0044] As a preferred solution of the optimization dispatching control method of the substation energy storage described in the present invention, the maximization of the total revenue R is mainly reflected in:

[0045] Taking advantage of electricity price fluctuations, charging is performed when electricity prices are low. The energy storage system stores electricity at a lower cost when electricity prices are low and discharges when electricity prices are high. The energy storage system sells electricity when electricity prices are high to obtain higher returns and maximize the total return R. Considering load balancing, when the grid load is high (especially during periods of high electricity prices), discharge is given priority to reduce grid pressure, which can not only balance the load but also maximize P discharge,t Contribution to R, on the contrary, when the grid load is low, especially in the period of low electricity price, the energy storage system is charged first, which ensures that charging is carried out when the electricity price is low. charge,t , minimizing the negative impact on R.

[0046] An optimized dispatching control system for regional energy storage applied to the above-mentioned optimized dispatching control method for regional energy storage is integrated with an intelligent load management system and includes:

[0047] Data collection and processing module, which collects and stores historical load data and electricity price data, and pre-processes these data;

[0048] The load and electricity price forecasting module trains historical data based on the support vector machine model to generate a forecasting model, and uses real-time data to make real-time forecasts of future loads and electricity prices;

[0049] The dispatch strategy generation module generates a preliminary energy storage system dispatch strategy based on the load and electricity price forecast results;

[0050] The strategy optimization module defines the objective function of the scheduling strategy to optimize the overall operation effect of the energy storage system and achieve maximum economic benefits.

[0051] Beneficial effects of the present invention:

[0052] 1. The present invention uses a support vector machine (SVM) model to train historical load data and electricity price data, and continuously optimizes and updates the prediction model through real-time data input. Compared with traditional prediction methods, the SVM model can better capture the nonlinear changes in grid load and electricity prices, thereby significantly improving the accuracy of prediction. This provides reliable data support for the scheduling of energy storage systems;

[0053] 2. The present invention achieves real-time monitoring of grid load and efficient dispatch of energy storage system through close integration of intelligent load management system and energy storage system; that is, combined with accurate load and electricity price forecast and dispatch strategy rules, energy storage system can charge or discharge at the best time, maximize the use of grid resources and avoid unnecessary waste of resources. This not only improves the economic benefits of energy storage system, but also greatly improves the overall operation efficiency of the system and grid stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0055] Figure 1 This is a schematic diagram of the overall structure of an optimized dispatching control method for substation energy storage and its system proposed by the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Reference Figure 1 , is an embodiment of the present invention, and provides an optimization dispatching control method for energy storage in a substation, the method comprising the following steps:

[0060] Step 1: Integrate the intelligent load management system with the energy storage system to monitor the power load of the substation in real time and feed the real-time data back to the energy storage system. Based on the real-time load data provided by the intelligent load management system, the dispatch strategy of the energy storage system is optimized in real time.

[0061] Step 2: Collect historical load data and electricity price data, identify the patterns of load changes and electricity price fluctuations, use the support vector machine model to train the prediction model so that it can accurately predict future loads and electricity prices, use the established prediction model, continuously input real-time data into the prediction model, make real-time predictions of future loads and electricity prices, and generate prediction data;

[0062] The training process of the model in step 2 is: preprocessing the collected historical load data and electricity price data, processing missing values ​​and outliers, denoising the data, and standardizing the data:

[0063] Among them, X is the original data, μ is the mean, and σ is the standard deviation;

[0064] The data set is divided into training set and test set in a ratio of 80:20;

[0065] Specifically, during the training process of the SVM model, the goal is to minimize the following optimization problem:

[0066]

[0067] Among them, w is the weight vector, b is the bias term, ξ i is the slack variable, C is the penalty parameter, and n is the number of samples;

[0068] The constraints are:

[0069] y i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0, Among them, y i is the label, φ(x i ) is the feature mapping function;

[0070] Through the above minimization optimization operation, the model parameters w and α are solved. i and b, and use them directly in the final SVM prediction expression.

[0071] In order to solve this optimization problem, the Lagrange multiplier α is introduced i and β i ;, construct the Lagrangian function::

[0072]

[0073] Among them, α i ≥0 and β i ≥0.

[0074] The original problem is converted into a dual problem by performing dual optimization on the Lagrangian function L. First, the partial derivatives of w, b, and ξ are calculated and set to zero;

[0075] Derivative w:

[0076]

[0077] Derivative with respect to b:

[0078]

[0079] Derivative of ξ:

[0080]

[0081] Substituting these results into the Lagrangian function and eliminating w and ξ, we obtain the optimal form of the dual problem:

[0082]

[0083] Among them, α i The following constraints are met:

[0084]

[0085] By solving the above dual problem, the Lagrange multiplier α of each training sample can be determined i

[0086] The final prediction expression of the training model is:

[0087]

[0088] Where x is the input feature vector, α i is the Lagrange multiplier, y i is the label of the training sample, K(x i ,x is the kernel function, and its expression is: K(x i ,x)=exp(-γ||x i -x j || 2 ), γ is the kernel parameter, x i and x j is the input vector and b is the bias term.

[0089] b is obtained through the conditions of the support vectors:

[0090]

[0091] Usually choose those α i The support vectors between 0 and C are used to calculate b.

[0092] The prediction process of the above SVM model is:

[0093] The preprocessed real-time data x real-time Input it into the trained SVM model and use the model expression to make predictions. The prediction result is

[0094] The predicted future load and electricity price data are stored in the database as a basis for the subsequent dispatch strategy formulation;

[0095] Determine the forecast time window based on the update frequency of real-time data; update real-time data every 15-30 minutes;

[0096] The predicted load and electricity price curves are visualized to facilitate real-time monitoring and evaluation by the dispatching system and management personnel.

[0097] Step 3: Based on the prediction results, formulate a preliminary energy storage system scheduling strategy and construct the objective function R so that it can dynamically adapt to changing load and electricity prices.

[0098] Specifically, the process of formulating the preliminary scheduling strategy is as follows:

[0099] The forecast data set generated by the SVM model includes the load demand L for each time period in the future. t and electricity price p t , according to the intelligent load management system, obtain the current state of charge S0C, maximum charge and discharge power Pmax, minimum SOC (to prevent over-discharge) and maximum SOC (to prevent over-charging);

[0100] Load peak and valley identification: Based on the predicted load data L t , identify the peak and trough periods of future load; usually, the load is higher during peak periods and lower during trough periods; electricity price fluctuation analysis: analyze the electricity price p t The fluctuation of electricity prices can determine the high and low points of electricity prices;

[0101] Then formulate the strategy decision logic:

[0102] a. Charging when electricity prices are low: During periods of low electricity prices (below a certain threshold p low ), if the SOC of the energy storage system is less than the maximum SOC, a charging plan is formulated and the charging power P is calculated. charge ;

[0103] The calculation of charging power takes into account the current grid load L t and the maximum charging power Pmax of the energy storage system to ensure that no additional load pressure is placed on the power grid;

[0104] P charge=min(Pmax,Available Capacity,Grid Load Constraint)

[0105] b. Discharge when electricity price is high: During the period of high electricity price (above a certain threshold p high ), if the SOC of the energy storage system is higher than the minimum SOC, a discharge plan is formulated and the discharge power P is calculated. discharge ; The calculation of discharge power must ensure that the SOC does not drop below the minimum SOC while meeting the requirement of maximizing economic benefits; P discharge =min(Pmax,AvailableEnergy,Grid Load Requirement);

[0106] c. Load balance: During the peak load period, i.e. L t Exceeding a certain threshold L high When the load is low, the energy storage system discharges first to balance the load and reduce the pressure on the grid; t Below a certain threshold L low When charging, the energy storage system is charged first to absorb excess power and increase the overall stability of the system;

[0107] Combining the above logic and formula, a preliminary energy storage scheduling plan is generated, including the charging power P for each time period. charge,t and discharge power P discharge,t .

[0108] The objective function of the scheduling strategy is defined as:

[0109]

[0110] Among them, R is the total revenue; P discharge,t and P charge,t are the discharge and charging power of the energy storage system at time t; p t is the electricity price at time t;

[0111] The scheduling strategy is formulated to maximize the objective function R, that is, to maximize the net benefit of the energy storage system.

[0112] In other words, the maximization of total revenue R is mainly reflected in:

[0113] Taking advantage of electricity price fluctuations, charging is performed when electricity prices are low. The energy storage system stores electricity at a lower cost when electricity prices are low and discharges when electricity prices are high. The energy storage system sells electricity when electricity prices are high to obtain higher returns and maximize the total return R. Considering load balancing, when the grid load is high (especially during periods of high electricity prices), discharge is given priority to reduce grid pressure, which can not only balance the load but also maximize P discharge,tContribution to R, on the contrary, when the grid load is low, especially in the period of low electricity price, the energy storage system is charged first, which ensures that charging is carried out when the electricity price is low. charge,t , minimizing the negative impact on R.

[0114] An optimized dispatching control system for regional energy storage applied to the above-mentioned optimized dispatching control method for regional energy storage is integrated with an intelligent load management system and includes:

[0115] Data collection and processing module, which collects and stores historical load data and electricity price data, and pre-processes these data;

[0116] The load and electricity price prediction module trains historical data based on the support vector machine model to generate a prediction model, and uses real-time data to make real-time predictions of future loads and electricity prices. The scheduling strategy generation module generates a preliminary energy storage system scheduling strategy based on the load and electricity price prediction results. The strategy optimization module defines the objective function of the scheduling strategy to optimize the overall operation of the energy storage system and achieve maximum economic benefits.

[0117] In summary, the present invention uses a support vector machine (SVM) model to train historical load data and electricity price data, and continuously optimizes and updates the prediction model through real-time data input. Compared with traditional prediction methods, the SVM model can better capture the nonlinear changes in grid load and electricity price, thereby significantly improving the accuracy of the prediction. This provides reliable data support for the scheduling of the energy storage system. Through the close integration of the intelligent load management system and the energy storage system, real-time monitoring of the grid load and efficient scheduling of the energy storage system can be achieved; that is, combined with accurate load and electricity price forecasts and scheduling strategy rules, the energy storage system can charge or discharge at the best time, maximize the use of grid resources, and avoid unnecessary waste of resources. This not only improves the economic benefits of the energy storage system, but also greatly improves the overall operating efficiency of the system and the stability of the grid.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the dispatching and controlling of energy storage in a substation, characterized in that: The method comprises the following steps: Step 1: Integrate the intelligent load management system with the energy storage system to monitor the power load in the substation in real time and feed back the real-time data to the energy storage system; Step 2: Collect historical load data and electricity price data, identify the patterns of load changes and electricity price fluctuations, use the support vector machine model to train the prediction model so that it can accurately predict future loads and electricity prices, use the established prediction model, continuously input real-time data into the prediction model, make real-time predictions of future loads and electricity prices, and generate prediction data; Step 3: Based on the prediction results, formulate a preliminary energy storage system scheduling strategy and construct the objective function R so that it can dynamically adapt to changing load and electricity prices.

2. The method for optimizing the dispatching and controlling of energy storage in a substation according to claim 1, characterized in that: The training process of the model in step 2 is: Preprocess the collected historical load data and electricity price data, handle missing values ​​and outliers, denoise the data, and standardize the data: Among them, X is the original data, μ is the mean, and σ is the standard deviation; The data set is divided into training set and test set in a ratio of 80:20; The training set data is used to train the SVM model, and the prediction expression of the training model is obtained as follows: Where x is the input feature vector, α i is the Lagrange multiplier, y i is the label of the training sample, K(x i ,x is the kernel function, and its expression is: K(x i ,x)=exp(-γ||x i -x j || 2 ), γ is the kernel parameter, x i and x j is the input vector and b is the bias term.

3. The method for optimizing the dispatching and controlling of energy storage in a substation according to claim 2 is characterized in that: During the training process of the SVM model, the goal is to minimize the following optimization problem: Among them, w is the weight vector, b is the bias term, ξ i is the slack variable, C is the penalty parameter, and n is the number of samples; The constraints are: Among them, y i is the label, φ(x i ) is the feature mapping function; through the above minimization optimization operation, the model parameters w, α are solved i and b, and use them directly in the final SVM prediction expression.

4. The method for optimizing the dispatching and controlling of energy storage in a substation according to claim 3 is characterized in that: The prediction process of the SVM model is: The preprocessed real-time data x real-time Input it into the trained SVM model and use the model expression to make predictions. The prediction result is The predicted future load and electricity price data are stored in the database as a basis for the subsequent scheduling strategy formulation; Determine the forecast time window based on the update frequency of real-time data; update real-time data every 15-30 minutes; The predicted load and electricity price curves are visualized to facilitate real-time monitoring and evaluation by the dispatching system and management personnel.

5. The method for optimizing the dispatching and controlling of energy storage in a substation according to claim 1, characterized in that: The process of formulating the preliminary scheduling strategy is as follows: The forecast data set generated by the SVM model includes the load demand L for each time period in the future. t and electricity price p t , according to the intelligent load management system, obtain the current state of charge S0C, maximum charge and discharge power Pmax, minimum SOC and maximum SOC; Load peak and valley identification: Based on the predicted load data L t , identify the peak and trough periods of future load; electricity price fluctuation analysis: analyze the electricity price p t The fluctuation of electricity prices can determine the high and low points of electricity prices; Then formulate the strategy decision logic: a. Charging when electricity prices are low: During periods of low electricity prices, if the SOC of the energy storage system is less than the maximum SOC, a charging plan is developed and the charging power P is calculated. charge ; b. Discharge when electricity prices are high: During periods of high electricity prices, if the SOC of the energy storage system is higher than the minimum SOC, a discharge plan is formulated and the discharge power P is calculated. discharge ; c. Load balance: During the peak load period, i.e. L t Exceeding a certain threshold L high When the load is low, the energy storage system discharges first to balance the load and reduce the pressure on the grid; t Below a certain threshold L low When charging, the energy storage system is charged first to absorb excess power and increase the overall stability of the system; Combining the above logic and formula, a preliminary energy storage scheduling plan is generated, including the charging power P for each time period. charge,t and discharge power P discharge,t .

6. The method for optimizing dispatching and controlling energy storage in a substation according to claim 5 is characterized in that: The objective function of the scheduling strategy is defined as: Among them, R is the total revenue; P discharge,t and P charge,t are the discharge and charging power of the energy storage system at time t; p t is the electricity price at time t; The scheduling strategy is formulated to maximize the objective function R, that is, to maximize the net benefit of the energy storage system.

7. The method for optimizing the dispatching and controlling of energy storage in a substation according to claim 6 is characterized in that: The maximization of the total revenue R is mainly reflected in: Taking advantage of electricity price fluctuations, charging is performed when electricity prices are low. The energy storage system stores electricity at a lower cost when electricity prices are low and discharges when electricity prices are high. The energy storage system sells electricity when electricity prices are high to obtain higher returns and maximize the total return R. Considering load balancing, when the grid load is high, discharge is given priority to reduce grid pressure, which can not only balance the load, but also maximize P discharge,t Contribution to R, on the contrary, when the grid load is low, especially in the period of low electricity price, the energy storage system is charged first, which ensures that charging is carried out when the electricity price is low. charge,t , minimizing the negative impact on R.

8. An optimized dispatching and control system for energy storage in a substation area, according to the optimized dispatching and control method for energy storage in a substation area according to claim 7, characterized in that: The system is integrated with the intelligent load management system and includes: Data collection and processing module, which collects and stores historical load data and electricity price data, and pre-processes these data; The load and electricity price forecasting module trains historical data based on the support vector machine model to generate a forecasting model, and uses real-time data to make real-time forecasts of future loads and electricity prices; The dispatch strategy generation module generates a preliminary energy storage system dispatch strategy based on the load and electricity price forecast results; The strategy optimization module defines the objective function of the scheduling strategy to optimize the overall operation effect of the energy storage system and achieve maximum economic benefits.

Images