Capacity Configuration Method and System Based on Source-Grid-Load-Storage Integration

Abstract

The present invention relates to the technical field of electrical storage capacity configuration, and specifically, to a capacity configuration method and system based on source-network-load-storage integration. The method includes the following steps: obtaining power consumption data, power generation data, and ambient temperature, and using the ARIMA model combined with the linear regression model to analyze and predict the load demand; initially calculating and analyzing the energy storage capacity configuration based on the actual load demand, and establishing an optimization model for source-network-load-storage capacity configuration in which the source-network-load-storage and the energy storage capacity restrict each other; introducing the factor of ambient temperature change, and redesigning the energy storage capacity configuration strategy; using the phase space analysis algorithm to evaluate the stability of the capacity configuration strategy, and introducing the Lyapunov exponent into the optimization model for source-network-load-storage capacity configuration to determine the capacity configuration strategy. The capacity configuration method and system based on source-network-load-storage integration adjust the energy storage capacity configuration strategy based on the dynamic changes of the actual load demand and environmental factors, and combine the Lyapunov exponent analysis to optimize the energy storage capacity configuration for system stability.

Description

Technical Field

[0001] The present invention relates to the technical field of electric storage capacity configuration, and specifically, to a capacity configuration method and system based on source-grid-load-storage integration. Background Art

[0002] The capacity configuration method based on source-grid-load-storage integration aims to dynamically adjust the energy storage capacity configuration strategy to cope with load demand fluctuations and environmental changes and ensure the stability and optimality of the energy storage system under variable load conditions. By combining the prediction of load demand considering factors such as environmental temperature and humidity and the analysis of the stability of energy storage capacity configuration using the Lyapunov index, the optimization adjustment and real-time feedback mechanism of energy storage capacity configuration are controlled to achieve that under different load demands and environmental conditions, the energy storage capacity configuration can quickly and effectively respond to sudden load fluctuations.

[0003] Existing energy storage capacity configuration methods usually have difficulty in coping with sudden changes in load demand and the influence of environmental factors. And under normal load demands, the energy storage capacity configuration strategy of capacity configuration is unchanged. However, when there are large changes in environmental temperature and humidity, especially during the peak electricity consumption seasons in winter and summer, it will lead to sudden changes in load demand, and then the energy storage capacity configuration strategy needs to change immediately following the sudden change in load demand. Only calculating the energy storage capacity configuration initially by the source-grid-load-storage capacity configuration optimization model cannot make the source-grid-load-storage reach the best and safest strategy simultaneously. Introducing the Lyapunov index into the source-grid-load-storage capacity configuration optimization model can well judge whether the initially calculated energy storage capacity configuration is stable. Therefore, a capacity configuration method and system based on source-grid-load-storage integration are provided. Summary of the Invention

[0004] The purpose of the present invention is to provide a capacity configuration method and system based on source-grid-load-storage integration to solve the problem proposed in the above background art that under normal load demands, the energy storage capacity configuration strategy of capacity configuration is unchanged, but when there are large changes in environmental temperature and humidity, especially during the peak electricity consumption seasons in winter and summer, it will lead to sudden changes in load demand, and then the energy storage capacity configuration strategy needs to change immediately following the sudden change in load demand.

[0005] To achieve the above purpose, the present invention aims to provide a capacity configuration method based on source-grid-load-storage integration, including:

[0006] S1. Obtain power consumption data, power generation data, and environmental parameters, and use the ARIMA model combined with the linear regression model to analyze and predict the load demand;

[0007] S2. Based on the actual load demand, initially calculate and analyze the energy storage capacity configuration, establish a source-grid-load-storage capacity configuration optimization model between the source-grid-load-storage and the energy storage capacity, and initially calculate the energy storage capacity configuration;

[0008] S3. Evaluate the stability of the capacity configuration strategy using the phase space analysis algorithm, introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model, and determine the final capacity configuration strategy;

[0009] S4. Based on the final capacity configuration strategy, feedback and execute the three-party strategies of source-network-load scheduling.

[0010] As a further improvement of this technical solution, in S1, obtain power consumption data, power generation data, and environmental parameters, and use the ARIMA model combined with the linear regression model to analyze and predict the load demand. The specific method steps are as follows:

[0011] S1.1. Obtain power consumption data , power generation data , load curve , and environmental parameters;

[0012] Among them, is the time, and the environmental parameters include temperature and humidity ;

[0013] S1.2. Build a power demand forecasting model based on the ARIMA model;

[0014] S1.3. Use the power demand forecasting model to analyze and calculate the predicted load demand;

[0015] S1.4. Use the linear regression model to correct the predicted load demand and calculate the actual load demand.

[0016] As a further improvement of this technical solution, in S1.2, build a power demand forecasting model based on the ARIMA model. The specific method steps are as follows:

[0017] S1.2.1. Conduct time series analysis on the load curve , and initialize the autoregressive term order , the number of differences , and the moving average term order ;

[0018] S1.2.2. Use the constructed ARIMA model to build a power demand forecasting model:

[0019] ;

[0020] Among them, is the predicted load demand; is the long-term mean; is the autoregressive term order; is the number of differences; is the moving average term order; is the autoregressive parameter; is the moving average parameter; is the time the differential load data at; is the time the error term at; is the time the error term at; is the total order of the autoregressive term; is the total order of the moving average term.

[0021] As a further improvement of this technical solution, in S1.4, a linear regression model is used to correct the predicted load demand, and the actual load demand is calculated. The specific method is as follows:

[0022] ;

[0023] where, is the actual load demand; is the intercept term; is the ARIMA prediction coefficient; is the temperature coefficient; is the humidity coefficient.

[0024] As a further improvement of this technical solution, in S2, based on the actual load demand, the energy storage capacity configuration is initially calculated and analyzed, and an optimization model for the source-grid-load-storage capacity configuration between the source-grid-load-storage and the energy storage capacity is established. The specific method steps are as follows:

[0025] S2.1. Combine the renewable energy power generation and the charge and discharge characteristics of the energy storage system to initially estimate the energy storage capacity configuration:

[0026] ;

[0027] where, is the initially estimated energy storage capacity configuration; is the renewable energy power generation; is the start time of the estimation; is the end time of the estimation;

[0028] S2.2. Comprehensively construct an optimization model for the source-grid-load-storage capacity configuration with the actual load demand, renewable energy power generation, and energy storage capacity configuration, and calculate the optimal energy storage capacity configuration:

[0029] Optimization model for source-grid-load-storage capacity configuration:

[0030] ;

[0031] where, is the time the charging power of the energy storage system; is the charging efficiency of the energy storage system; is the load demand weight; is the capacity configuration weight;

[0032] Use the particle swarm optimization algorithm to solve the source-network-load-storage capacity configuration optimization model and obtain the optimal energy storage capacity configuration .

[0033] As a further improvement of this technical solution, in S3, use the phase space analysis algorithm to evaluate the stability of the capacity configuration strategy, and introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy. The specific method steps are as follows:

[0034] S3.1. Construct a two-dimensional phase space through the delay coordinate with the actual load demand and the charging power of the energy storage system, and solve the Lyapunov exponent;

[0035] S3.2. Introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy.

[0036] As a further improvement of this technical solution, in S3.1, construct a two-dimensional phase space through the delay coordinate with the actual load demand and the charging power of the energy storage system, and solve the Lyapunov exponent. The specific method steps are as follows:

[0037] S3.1.1. Construct a two-dimensional phase space through the delay coordinate with the actual load demand and the charging power of the energy storage system:

[0038] ;

[0039] where is the state vector of the system's actual load demand combined with the charging power of the energy storage system;

[0040] S3.1.2. Calculate the Lyapunov exponent based on the two-dimensional phase space and the system state vector:

[0041] ;

[0042] where is the Lyapunov exponent; is the initial difference of the two-dimensional phase space trajectory; is the time two-dimensional phase space trajectory difference.

[0043] As a further improvement of this technical solution, in S3.2, introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy. The specific method is as follows:

[0044] ;

[0045] Among them, is the Lyapunov exponent weight; is the Lyapunov exponent;

[0046] Use the particle swarm optimization algorithm again to solve the source-network-load-storage capacity configuration optimization model, and obtain the final energy storage capacity configuration .

[0047] As a further improvement of this technical solution, in S4, based on the final capacity configuration strategy, feedback and execute the three-party strategies of source-network-load scheduling, specifically as follows:

[0048] S4.1. Renewable energy power generation scheduling: When the actual load demand is lower than the renewable energy power generation, directly use the renewable energy;

[0049] S4.2. Grid scheduling: When the actual load demand is higher than the renewable energy power generation, give priority to using the renewable energy and obtain additional power from the grid;

[0050] S4.3. Load management: When the actual load demand is higher than the renewable energy power generation, adjust the electricity consumption management of industrial users and residential users.

[0051] On the other hand, the present invention provides a capacity configuration system based on source-network-load-storage integration, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the above-mentioned capacity configuration method based on source-network-load-storage integration.

[0052] Compared with the prior art, the beneficial effects of the present invention:

[0053] 1. In the capacity configuration method and system based on source-network-load-storage integration, based on the dynamic coupling analysis of load demand and external factors such as environmental temperature and humidity, the energy storage capacity configuration strategy can be adjusted in real time to ensure that the energy storage system can flexibly adapt under environmental changes and load demand fluctuations, and ensure the continuity and stability of power supply.

[0054] 2. In the capacity configuration method and system based on source-network-load-storage integration, by introducing the Lyapunov exponent into the energy storage capacity configuration optimization model and combining the particle swarm optimization algorithm for global optimal solution, it is possible to judge and ensure the stability of the energy storage system's capacity configuration under variable loads and environmental conditions, prevent system imbalance problems caused by unstable energy storage capacity, and ensure the safe and optimal configuration of the energy storage capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is the overall method flow chart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0056] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts belong to the scope of protection of the present invention. Embodiment 1

[0057] Please refer to Figure 1 As shown, this embodiment provides a capacity configuration method based on source-network-load-storage integration, including the following steps:

[0058] S1. Obtain power consumption data, power generation data, and environmental parameters, and use the ARIMA model combined with the linear regression model to analyze and predict the load demand;

[0059] In step S1 of this embodiment, power consumption data, power generation data, and environmental parameters are obtained, and the ARIMA model combined with the linear regression model is used to analyze and predict the load demand. The specific method steps are as follows:

[0060] S1.1. Obtain power consumption data , power generation data , load curve and environmental parameters;

[0061] Among them, is the time, and the environmental parameters include temperature and humidity ;

[0062] S1.2. Build a power demand prediction model based on the ARIMA model;

[0063] S1.3. Use the power demand prediction model to analyze and calculate the predicted load demand;

[0064] S1.4. Use the linear regression model to correct the predicted load demand and calculate the actual load demand.

[0065] In step S1.2 of this embodiment, a power demand prediction model is built based on the ARIMA model. The specific method steps are as follows:

[0066] S1.2.1. Perform time series analysis on the load curve , and initialize the autoregressive term order , the number of differences and the moving average term order ;

[0067] S1.2.2. Use the built ARIMA model to build a power demand prediction model:

[0068] ;

[0069] wherein, is the predicted load demand; is the long-term mean; is the order of the autoregressive term; is the number of differencing; is the order of the moving average term; is the autoregressive parameter; is the moving average parameter; is the time at which the differenced load data; is the time at which the error term; is the time at which the error term; is the total order of the autoregressive terms; is the total order of the moving average terms.

[0070] In this embodiment, the ARIMA model is a time series prediction model applied to model and predict time series data with trends; the ARIMA model consists of three parts: autoregression, differencing, and moving average;

[0071] The ARIMA model is used to construct a power demand prediction model as follows:

[0072] Power demand is essentially a time series data and usually contains seasonal fluctuations, long-term trends, and short-term fluctuations. The ARIMA model can better capture the changing patterns of power demand by processing these characteristics through autoregression and moving average; the power demand curve usually has long-term trends and periodic changes. ARIMA makes non-stationary data converted into stationary data through differencing technology, thus facilitating modeling and prediction; the ARIMA model is based on historical data for modeling and prediction and can handle seasonal fluctuations and trend changes;

[0073] The power demand prediction model is a mathematical model established based on historical power demand data and environmental parameters; it is used to predict the power demand in a future period or in the long term.

[0074] In this embodiment S1.4, a linear regression model is used to correct the predicted load demand and calculate the actual load demand. The specific method is as follows:

[0075] ;

[0076] wherein, is the actual load demand; is the intercept term; is the ARIMA prediction coefficient; is the temperature coefficient; is the humidity coefficient.

[0077] In this embodiment, the linear regression model is a statistical analysis method used to model the relationship between one or more independent variables and a dependent variable; the ARIMA model is used to predict the load demand based on historical data. It takes into account the autoregression and moving average of the time series, but may not be able to accurately capture dynamic environmental factors (such as temperature, humidity, etc.). The linear regression model can further correct the prediction results of the ARIMA model by introducing temperature and humidity factors, so as to obtain a more accurate actual load demand; the ARIMA model provides a load prediction based on historical data, and by introducing the linear regression model to correct it, more environmental factors can be added to the existing time series prediction, thus achieving a more accurate prediction.

[0078] S2. Based on the actual load demand, initially calculate and analyze the energy storage capacity configuration, establish an optimization model for the source-grid-load-storage capacity configuration between the source-grid-load-storage and the energy storage capacity, and initially calculate the energy storage capacity configuration;

[0079] In step S2 of this embodiment, based on the actual load demand, initially calculate and analyze the energy storage capacity configuration, and establish an optimization model for the source-grid-load-storage capacity configuration between the source-grid-load-storage and the energy storage capacity. The specific method steps are as follows:

[0080] S2.1. Combine the renewable energy power generation and the charging and discharging characteristics of the energy storage system to initially estimate the energy storage capacity configuration:

[0081] ;

[0082] where is the initially estimated energy storage capacity configuration; is the renewable energy power generation; is the start time of the estimation; is the end time of the estimation;

[0083] S2.2. Combine the actual load demand, renewable energy power generation, and energy storage capacity configuration to construct an optimization model for the source-grid-load-storage capacity configuration, and calculate the optimal energy storage capacity configuration:

[0084] Optimization model for source-grid-load-storage capacity configuration:

[0085] ;

[0086] where is the time Charging power of the energy storage system; is the charging efficiency of the energy storage system; is the load demand weight; is the capacity configuration weight;

[0087] Use the particle swarm optimization algorithm to solve the source-network-load-storage capacity configuration optimization model and obtain the optimal energy storage capacity configuration .

[0088] In this embodiment, the source-network-load-storage capacity configuration optimization model is a mathematical model used to balance the relationships among various parts in the power system. Its purpose is to optimize the overall operation efficiency and stability of the power system by reasonably configuring the energy storage capacity. The source-network-load-storage capacity configuration optimization model combines the actual load demand, the power generation of renewable energy, the charge and discharge characteristics of the energy storage system, and the energy storage capacity configuration. It aims to optimize the energy storage capacity configuration according to the changes in power demand, the fluctuations in renewable energy generation, and the performance characteristics of the energy storage system;

[0089] The particle swarm optimization algorithm is an intelligent optimization algorithm that simulates the foraging behavior of bird flocks. By simulating the movement of particles in the solution space, it continuously searches for the optimal solution to the problem; the particle swarm optimization algorithm can effectively perform global search in the entire solution space by simulating the collaborative search of multiple particles, avoiding falling into local optimal solutions; this is particularly important when optimizing the energy storage capacity configuration because the optimization problem involves multiple variables and constraints, and there may be multiple local optimal solutions, while the particle swarm optimization can find a solution closer to the global optimal solution.

[0090] S3. Use the phase space analysis algorithm to evaluate the stability of the capacity configuration strategy, and introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy;

[0091] In this embodiment S3, use the phase space analysis algorithm to evaluate the stability of the capacity configuration strategy, and introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy. The specific method steps are as follows:

[0092] S3.1. Construct a two-dimensional phase space with the actual load demand and the charging power of the energy storage system through delay coordinates, and solve the Lyapunov exponent;

[0093] S3.2. Introduce the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model to determine the final capacity configuration strategy.

[0094] In this embodiment, the phase space analysis algorithm is a method for analyzing the dynamic characteristics of a system by transforming time series data into trajectories in a multi-dimensional space. The system state changes over time, and the phase space analysis reveals the internal laws of these dynamic changes by constructing a phase space; the phase space analysis algorithm usually adopts the delay coordinate embedding method to convert time series data into a multi-dimensional state space,

[0095] The Lyapunov exponent is an important indicator for measuring the sensitivity of a dynamic system to initial conditions. It reflects the stability and chaotic characteristics of the system. If the Lyapunov exponent is positive, it indicates that the system is chaotic, and any small change in the initial conditions will cause a huge change in the system state. If the Lyapunov exponent is negative, it means that the system is stable, and the system state will gradually tend to an equilibrium or stable state. If the Lyapunov exponent is zero, it indicates that the behavior of the system is periodic. The Lyapunov exponent is used to evaluate the stability of the source-network-load-storage capacity configuration strategy. By calculating this exponent, it can be judged whether the energy storage capacity configuration strategy will lead to instability or chaotic behavior due to changes in load demand or the charge-discharge strategy of the energy storage system.

[0096] The purpose of introducing the Lyapunov exponent into the source-network-load-storage capacity configuration optimization model is to ensure the reliability and security of the capacity configuration strategy through stability analysis, as follows:

[0097] By calculating the Lyapunov exponent, it is judged whether the current capacity configuration strategy will cause system instability. If the Lyapunov exponent is negative, it means that the current strategy is stable and can be continued. If the Lyapunov exponent is positive, it may mean that there is a potential instability in the capacity configuration strategy and adjustment is required.

[0098] When the Lyapunov exponent indicates that the current capacity configuration strategy is unstable, the Lyapunov exponent can be used as a constraint condition to further adjust the capacity configuration strategy to ensure its stability and security.

[0099] In this embodiment S3.1, the actual load demand and the charging power of the energy storage system are used to construct a two-dimensional phase space through delay coordinates, and the Lyapunov exponent is solved. The specific method steps are as follows:

[0100] S3.1.1. Construct a two-dimensional phase space from the actual load demand and the charging power of the energy storage system through delay coordinates:

[0101] ;

[0102] Among them, is the state vector of the actual load demand of the system combined with the charging power of the energy storage system;

[0103] S3.1.2. Calculate the Lyapunov exponent based on the two-dimensional phase space and the system state vector:

[0104] ;

[0105] Among them, is the Lyapunov exponent; is the initial difference of the two-dimensional phase space trajectory; is the time Two-dimensional phase space trajectory difference.

[0106] In this embodiment S3.2, the Lyapunov exponent is introduced into the source-grid-load-storage capacity configuration optimization model to determine the final capacity configuration strategy. The specific method is as follows:

[0107] ;

[0108] Among them, is the Lyapunov exponent weight; is the Lyapunov exponent;

[0109] Use the particle swarm optimization algorithm to solve the source-grid-load-storage capacity configuration optimization model again to obtain the final energy storage capacity configuration .

[0110] S4. Based on the final capacity configuration strategy, feedback and execute the three-party strategies of source-grid-load scheduling;

[0111] In this embodiment S4, based on the final capacity configuration strategy, feedback and execute the three-party strategies of source-grid-load scheduling, which are as follows:

[0112] S4.1. Renewable energy power generation scheduling: When the actual load demand is lower than the renewable energy power generation, directly use the renewable energy;

[0113] S4.2. Grid scheduling: When the actual load demand is higher than the renewable energy power generation, give priority to using the renewable energy and obtain additional power from the grid;

[0114] S4.3. Load management: When the actual load demand is higher than the renewable energy power generation, adjust the power consumption management of industrial users and residential users. Embodiment 2

[0115] This embodiment provides a capacity configuration system based on source-grid-load-storage integration, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement the steps of the above-mentioned capacity configuration method based on source-grid-load-storage integration.

[0116] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A capacity configuration method based on source-network-load-storage integration, characterized in that It includes the following steps: S1. Obtain power consumption data, power generation data, and environmental parameters, and use the ARIMA model combined with the linear regression model to analyze and predict the load demand; S2. Based on the actual load demand, initially calculate and analyze the energy storage capacity configuration, establish an optimization model for the source-grid-load-storage and energy storage capacity configuration, and initially calculate the energy storage capacity configuration; S3. Use the phase space analysis algorithm to evaluate the stability of the capacity configuration strategy, and introduce the Lyapunov exponent into the optimization model for the source-grid-load-storage capacity configuration to determine the final capacity configuration strategy; S4. Based on the final capacity configuration strategy, feedback and execute the three-party strategies for source-grid-load dispatching; The specific method steps in S2 are as follows: S2.

1. Combine the renewable energy power generation and the charge and discharge characteristics of the energy storage system to initially estimate the energy storage capacity configuration; ； Among them, is the initially estimated energy storage capacity configuration; is the renewable energy power generation; is the start time of the estimation; is the end time of the estimation; S2.

2. Comprehensively construct an optimization model for the source-grid-load-storage capacity configuration with the actual load demand, renewable energy power generation, and energy storage capacity configuration, and calculate the optimal energy storage capacity configuration; Optimization model for source-grid-load-storage capacity configuration: ； Among them, is the time Charging power of the energy storage system; is the charging efficiency of the energy storage system; is the load demand weight; is the capacity configuration weight; Use the particle swarm optimization algorithm to solve the source-network-load-storage capacity configuration optimization model and obtain the optimal energy storage capacity configuration ; The specific method steps in S3 are as follows: S3.

1. Construct a two-dimensional phase space with the actual load demand and the charging power of the energy storage system through the delay coordinate, and solve the Lyapunov exponent; S3.

2. Introduce the Lyapunov exponent into the optimization model for the source-grid-load-storage capacity configuration to determine the final capacity configuration strategy.

2. The capacity configuration method based on source-network-load-storage integration according to claim 1, wherein: In S1, to obtain power consumption data, power generation data, and environmental parameters, and use the ARIMA model combined with the linear regression model to analyze and predict the load demand, the specific method steps are as follows: S1.

1. Obtain power consumption data , power generation data , load curves and environmental parameters; Among them, is the moment, and the environmental parameters include temperature and humidity ; S1.

2. Construct a power demand prediction model based on the ARIMA model; S1.

3. Use the power demand prediction model to analyze and calculate the predicted load demand; S1.

4. Use the linear regression model to correct the predicted load demand and calculate the actual load demand.

3. The capacity configuration method based on source-network-load-storage integration according to claim 2, wherein: In S1.2, to construct a power demand prediction model based on the ARIMA model, the specific method steps are as follows: S1.2.

1. Perform time series analysis on the load curve and initialize the order of the autoregressive term , the number of differencing times and the order of the moving average term ; S1.2.

2. Use the constructed ARIMA model to construct a power demand prediction model: ； Wherein, is the predicted load demand; is the long-term mean; is the order of the autoregressive term; is the number of differencing; is the order of the moving average term; is the autoregressive parameter; is the moving average parameter; is the time at the differenced load data; is the time at the error term; is the time at the error term; is the total order of the autoregressive term; is the total order of the moving average term.

4. The capacity configuration method based on source-network-load-storage integration according to claim 3, characterized in that: In S1.4, to use the linear regression model to correct the predicted load demand and calculate the actual load demand, the specific method is as follows: ； Among them, is the actual load demand; is the intercept term; is the ARIMA prediction coefficient; is the temperature coefficient; is the humidity coefficient.

5. The capacity configuration method based on source-network-load-storage integration according to claim 4, characterized in that: In S3.1, to construct a two-dimensional phase space with the actual load demand and the charging power of the energy storage system through the delay coordinate, and solve the Lyapunov exponent, the specific method steps are as follows: S3.1.

1. Construct a two-dimensional phase space with the actual load demand and the charging power of the energy storage system through the delay coordinate: ； Among them, is the state vector of the actual load demand of the system combined with the charging power of the energy storage system; S3.1.

2. Calculate the Lyapunov exponent based on the two-dimensional phase space and the system state vector; ； Among them, is the Lyapunov exponent; is the initial difference of the two-dimensional phase space trajectory; is the time the difference of the two-dimensional phase space trajectory.

6. The capacity configuration method based on source-network-load-storage integration according to claim 5, characterized in that: In S3.2, to introduce the Lyapunov exponent into the optimization model for the source-grid-load-storage capacity configuration to determine the final capacity configuration strategy, the specific method is as follows: ； Among them, is the Lyapunov exponent weight; is the Lyapunov exponent; Use the particle swarm optimization algorithm again to solve the source-network-load-storage capacity configuration optimization model and obtain the final energy storage capacity configuration .

7. The capacity configuration method based on source-network-load-storage integration according to claim 6, wherein: In S4, based on the final capacity configuration strategy, feedback and execute the three-party strategies for source-grid-load dispatching, specifically as follows: S4.

1. Renewable energy power generation dispatching: When the actual load demand is lower than the renewable energy power generation, directly use the renewable energy; S4.

2. Grid dispatching: When the actual load demand is higher than the renewable energy power generation, give priority to using the renewable energy and obtain additional power from the grid; S4.

3. Load management: When the actual load demand is higher than the renewable energy generation, adjust the electricity consumption management of industrial users and residential users.

8. A capacity configuration system based on source-network-load-storage integration, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes a computer program to implement the capacity configuration method based on source-network-load-storage integration according to any one of claims 1-7.

Images