Wind and light storage load resource scheduling and proportioning optimization system and method in source network load storage integrated environment

Abstract

The invention relates to the technical field of power resource scheduling, in particular to a wind and light storage load resource scheduling and proportioning optimization system and method in a source network load storage integrated environment, and the system comprises a data collection module, a data processing module, a prediction and evaluation module, a scheduling and optimization module, a control and execution module and a monitoring and evaluation module. According to the invention, the prediction and evaluation module is utilized to predict wind and light resources and load demands, evaluate the performance of the energy storage system and predict the wind and light resources, so that the system can know available renewable energy resources in advance, and the prediction accuracy directly affects the resource allocation decision of the scheduling and optimization module; the prediction of the load demand is helpful for the system to prepare for power supply in advance, the power failure risk caused by imbalance of power supply and demand is avoided, and the power utilization satisfaction degree of the user is improved; real-time monitoring and evaluation of the performance of the energy storage system provide key operation state information for a scheduling and optimizing module.

Description

Technical Field

[0001] This invention relates to the field of power resource dispatching technology, and is a system for dispatching and optimizing the allocation of wind, solar, storage and load resources in an integrated power generation, grid, load and storage environment. It also includes a method for dispatching and optimizing the allocation of wind, solar, storage and load resources in an integrated power generation, grid, load and storage environment. Background Technology

[0002] With the continuous growth of global energy consumption and the increasing severity of environmental problems, the development and utilization of renewable energy has become an important direction for global energy transition. Wind and solar energy, as clean and renewable energy sources, are of great significance for optimizing the energy structure and protecting the environment through large-scale application. However, the intermittency and uncertainty of wind and solar energy pose challenges to the stable operation of the power grid. Therefore, the concept of integrated generation, grid, load, and storage has been proposed, aiming to achieve efficient energy utilization and reliable grid operation by integrating wind and solar power generation, energy storage systems, and load management. In an integrated generation, grid, load, and storage environment, how to effectively schedule and optimize wind, solar, and energy storage resources to maximize energy utilization and minimize system operating costs has become a key technical issue.

[0003] However, existing technologies have the following shortcomings: the scheduling strategy lacks precision and cannot be dynamically adjusted according to real-time wind and solar resources and load demand; at the same time, there is a lack of an integrated scheduling and optimization system, which cannot achieve comprehensive management and control of the entire source-grid-load-storage integrated environment.

[0004] Existing systems often rely on fixed rules or simple threshold judgments for scheduling strategies, failing to accurately predict and dynamically adjust based on real-time changes in wind and solar power output, load demand fluctuations, and energy storage system status. This results in low system efficiency and an inability to achieve optimal resource allocation. Furthermore, wind and solar power generation, energy storage systems, and load management often operate independently, lacking a unified platform for collaborative management and overall optimization. This decentralized management model leads to information silos, hindering coordinated interaction among the power generation, grid, load, and storage systems.

[0005] Existing systems manage energy storage systems in a rather crude manner, lacking precise assessment and optimization of their performance status. This leads to unreasonable charging and discharging strategies, shortened lifespan, and underutilization of system benefits. With increasing renewable energy penetration and the continuous integration of new loads, existing systems often struggle to adapt to this dynamic and complex environment. Traditional systems tend to focus on early-stage scheduling decisions, lacking effective monitoring and evaluation mechanisms for the effectiveness of these decisions, thus failing to provide feedback for continuous system optimization. Summary of the Invention

[0006] This invention provides a system and method for scheduling and optimizing the allocation of wind, solar, and energy storage resources in an integrated source-grid-load-storage environment, which can solve the problem of not being able to dynamically adjust according to real-time wind and solar resources and load demand.

[0007] This invention can predict future wind and solar power demand and dynamically adjust resource allocation based on the predicted demand, which helps the system prepare for power supply in advance, avoids the risk of power outages caused by power supply and demand imbalance, and improves user satisfaction with electricity use.

[0008] 1) This invention, through an integrated prediction and evaluation module, utilizes advanced algorithms such as the ARIMA model and multiple linear regression to perform high-precision prediction of wind and solar resources and loads, and to evaluate the performance of energy storage systems in real time. This provides accurate data support for scheduling decisions, enabling the system to dynamically and adaptively schedule resources based on real-time conditions. It solves the problem of scheduling strategies lacking precision and unable to respond dynamically.

[0009] 2) This invention achieves comprehensive management and control of the integrated power generation, grid, load, and storage environment by constructing a complete system architecture that integrates data acquisition, processing, prediction, scheduling, control, and monitoring. The scheduling and optimization module formulates collaborative scheduling strategies based on global information, thereby minimizing the overall system operating cost and maximizing energy utilization efficiency. This solves the problem of a lack of system integration, which makes it difficult to achieve global optimization.

[0010] 3) This invention, through an energy storage system evaluation submodule, calculates key performance indicators such as coulombic efficiency in real time and continuously monitors system performance trends. This provides a scientific basis for optimizing charging and discharging strategies and scheduling maintenance plans, significantly improving the utilization efficiency and operational economy of energy storage systems. It addresses the problems of low utilization efficiency and insufficient performance evaluation in energy storage systems.

[0011] 4) The modular design adopted in this invention has good scalability. Each functional module is relatively independent yet works collaboratively, enabling easy access to new data sources, new prediction models, and new control strategies. This allows the system to adapt to future changes in energy structure and the development of new technologies, thus solving the problem of poor system scalability and adaptability.

[0012] 5) This invention, through an independent monitoring and evaluation module, continuously collects system operation data, compares and analyzes actual operating results with optimization goals, providing an important basis for adjusting scheduling strategies and continuously improving the system, forming a complete "prediction-scheduling-execution-monitoring-feedback" optimization closed loop. This solves the problem of insufficient effective monitoring and feedback of operational results.

[0013] One of the technical solutions of this invention is achieved through the following measures: a system for scheduling and optimizing the allocation of wind, solar, and energy storage resources in an integrated source-grid-load-storage environment, comprising: Data acquisition module: Collects real-time data on wind, solar, and energy storage resources and the power grid; Data processing module: performs data processing on the collected real-time data; Prediction and Assessment Module: Utilizes processed data to predict wind and solar resources and load demand, and assesses the performance of energy storage systems; Scheduling and optimization module: Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage system, formulate scheduling strategies and allocation optimization schemes for wind, solar and energy storage resources. Control and Execution Module: Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, it generates scheduling instructions to control the wind, solar and storage resources and load in real time to achieve optimal system operation; Monitoring and evaluation module: Real-time monitoring of the entire system's operational status.

[0014] The following are further optimizations and / or improvements to the above-mentioned technical solution: Furthermore, the aforementioned prediction and evaluation module includes a wind and solar resource prediction submodule, a load prediction submodule, and an energy storage system evaluation submodule. The wind and solar resource prediction submodule inputs the time series of real-time wind and solar resource data into the ARIMA prediction model and outputs wind and solar resource prediction time series data.

[0015] Furthermore, the aforementioned load forecasting submodule: inputs historical load-related data into a load forecasting multiple linear regression model to obtain load forecasts for a future period. The load forecasting multiple linear regression model is as follows: Among them, L y This is the load forecast; T is temperature; H is humidity; X n These are independent variables other than temperature and humidity; β0, β1, ..., β n ϵ is the regression coefficient and ϵ is the error term.

[0016] Furthermore, the aforementioned energy storage system evaluation submodule: collects the charging and discharging data of the energy storage system, calculates the coulombic efficiency based on the charging and discharging data, and evaluates the changing trend of the energy storage system based on the coulombic efficiency.

[0017] Furthermore, the aforementioned scheduling and optimization module includes a resource scheduling submodule and a resource allocation optimization submodule. The resource scheduling submodule utilizes the predicted results of wind and solar resources and load demand, as well as the performance evaluation results of the energy storage system, with the goal of minimizing the system's operating costs and maximizing energy utilization, to determine the optimal resource allocation scheme and generate scheduling instructions, taking into account various scheduling strategies.

[0018] Furthermore, the allocation optimization submodule analyzes the current energy supply and demand situation of the system during the execution of the scheduling command, constructs an optimization model, and the objective function of the optimization model includes minimizing costs, maximizing benefits, or improving the energy utilization rate of the system. The decision variable in the optimization model is the allocation coefficient between wind, solar, storage and load resources. The optimal allocation coefficient between wind, solar and storage resources is solved, and the optimal allocation coefficient is sent to the resource scheduling submodule. The resource scheduling submodule reallocates resources according to the optimal allocation coefficient, generates a new optimal resource allocation scheme, and generates new scheduling commands in real time.

[0019] The second technical solution of the present invention is achieved through the following measures: a method for resource scheduling and allocation optimization of wind, solar, storage and load under an integrated source-grid-load-storage environment, comprising: Collect real-time data on wind, solar, and energy storage resources and the power grid; Perform data processing on the collected real-time data; The processed data is used to predict wind and solar resources and load demand, and to evaluate the performance of energy storage systems. Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage systems, a scheduling strategy and allocation optimization scheme for wind, solar and energy storage resources are formulated. Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, scheduling instructions are generated to control the wind, solar and storage resources and load in real time in order to achieve the optimal operation of the system. Real-time monitoring of the entire system's operational status.

[0020] The beneficial effects of this invention are: The forecasting and evaluation module predicts wind and solar resources and load demand, and evaluates the performance of the energy storage system, providing accurate forward-looking information for the system. The wind and solar resource forecasting submodule uses historical data and advanced forecasting algorithms, such as the ARIMA model, to predict future wind and solar radiation conditions, enabling the system to understand available renewable energy resources in advance. The accuracy of this forecasting directly affects the resource allocation decisions of the scheduling and optimization module, allowing the system to maximize the use of renewable energy and reduce dependence on fossil fuels while ensuring power supply reliability. The load forecasting submodule analyzes historical load data and related influencing factors, such as weather, seasons, and holidays, to predict future load demand. This helps the system prepare for power supply in advance, avoids the risk of power outages caused by power supply and demand imbalances, and improves user satisfaction with electricity usage.

[0021] In this invention, the energy storage system evaluation submodule monitors and evaluates the performance of the energy storage system in real time, providing crucial operational status information for the scheduling and optimization module. By evaluating indicators such as the energy storage system's charge-discharge efficiency, remaining capacity, and health status, the system can accurately grasp the availability of energy storage resources, thereby rationally allocating these resources in the scheduling strategy and optimizing their charge-discharge behavior. This not only improves the lifespan of the energy storage system but also ensures that the system can promptly replenish power during peak loads or when wind and solar resources are insufficient, guaranteeing stable system operation. Furthermore, the evaluation results can guide system maintenance and upgrades, ensuring that the energy storage system operates at high efficiency for an extended period.

[0022] In this invention, the scheduling and optimization module ensures overall system performance improvement and reduced operating costs through precise resource scheduling and efficient allocation optimization. Based on wind and solar resource forecasts, load demand predictions, and energy storage system performance evaluations provided by the prediction and evaluation module, this module formulates optimal resource scheduling strategies and allocation optimization schemes. This allows the system to maximize the utilization of renewable energy while meeting user electricity demands, reducing energy waste. Through intelligent scheduling commands, it adjusts wind and solar power generation, energy storage charging and discharging, and load management in real time, effectively balancing supply and demand and improving system operating efficiency and reliability. Furthermore, the scheduling and optimization module can dynamically adjust strategies based on real-time market electricity prices, grid regulations, and environmental requirements to minimize operating costs and maximize economic benefits, thereby enhancing the system's market competitiveness and promoting a sustainable energy consumption model. In summary, the beneficial effect of the scheduling and optimization module lies in its ability to ensure the system maintains optimal operating conditions in complex and ever-changing energy environments, achieving efficient energy utilization and improved economic benefits, providing strong technical support for building a clean, efficient, and stable modern energy system. Attached Figure Description

[0023] Appendix Figure 1 This is an overall system block diagram of the present invention.

[0024] Appendix Figure 2 This is a system block diagram of the prediction and evaluation module of the present invention.

[0025] Appendix Figure 3 This is a system block diagram of the scheduling and optimization module of the present invention. Detailed Implementation

[0026] The present invention is not limited to the following embodiments, and the specific implementation can be determined according to the technical solution of the present invention and the actual situation.

[0027] The present invention will be further described below with reference to embodiments: Example 1: As Figure 1As shown, a system for resource scheduling and allocation optimization of wind, solar, storage, and load in an integrated source-grid-load-storage environment includes: Data acquisition module: Collects real-time data on wind, solar, and energy storage resources and the power grid; The data acquisition module collects real-time data through various sensors and monitoring devices installed in different locations, including anemometers, light sensors, smart meters, and energy storage system monitoring units. During data acquisition, data can be collected synchronously and asynchronously according to preset sampling frequencies and accuracy requirements to ensure the real-time nature and accuracy of the data. The collected data includes, but is not limited to, wind speed, wind direction, light intensity, temperature, humidity, energy storage system charging and discharging status, battery remaining capacity, and load demand.

[0028] Data processing module: performs data processing on the collected real-time data, including data cleaning, normalization, data completion, and storage; Specifically, data processing involves several steps: First, data cleaning is performed to remove invalid, erroneous, and outlier data points. Then, data normalization is conducted to eliminate the influence of different units and scales. Next, data completion is performed to handle missing and outlier values, ensuring data continuity and integrity. Furthermore, the data processing module can compress and store the data to reduce storage space requirements and improve data retrieval efficiency. The processed data will be stored in a database or data warehouse for use and analysis by the prediction and evaluation module, scheduling and optimization module, and other related modules.

[0029] Prediction and Evaluation Module: Utilizes processed data to predict wind and solar resources and load demand, and evaluates the performance of energy storage systems. The results will serve as input for the scheduling and optimization module. Scheduling and optimization module: Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage system, formulate scheduling strategies and allocation optimization schemes for wind, solar and energy storage resources. Control and execution module: Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, it generates scheduling instructions and uses corresponding execution mechanisms to control wind, solar and storage resources and load in real time to achieve optimal system operation; The control and execution module includes a series of control strategies and actuators, including a wind and solar power generation control unit, an energy storage system control unit, and a load management unit. The control strategies generate specific control signals based on scheduling instructions and predetermined algorithms and logic. The actuators are responsible for converting these control signals into actual physical actions, including adjusting the output power of the wind and solar generators, controlling the charging and discharging behavior of the energy storage system, and adjusting the operating status of the load. The control and execution module can also monitor the execution results in real time to ensure accurate execution of scheduling instructions and make timely adjustments or issue alarms when anomalies occur.

[0030] Monitoring and evaluation module: Real-time monitoring of the entire system's operational status.

[0031] The monitoring and evaluation module continuously collects system operating data, including equipment status, energy flow, and environmental parameters, through monitoring devices connected to various parts of the system. This data is analyzed in real time to detect any anomalies or potential failure risks. Based on the system's operating data, and in conjunction with preset performance indicators and evaluation models, the module evaluates the system's operational effectiveness and economic benefits. This includes comparing actual operating data with optimization targets, calculating the system's energy utilization rate, operating costs, and revenues. Feedback from the monitoring and evaluation module is crucial for continuous system optimization. It helps operators understand system performance, provides a basis for adjustments to the scheduling and optimization module, and ensures the long-term stable and efficient operation of the system.

[0032] Example 2: As Figure 2 As shown, as an optimization of the above embodiment, the prediction and evaluation module includes a wind and solar resource prediction submodule, a load prediction submodule, and an energy storage system evaluation submodule. The wind and solar resource prediction submodule: inputs the time series of real-time wind and solar resource data into the ARIMA prediction model and outputs wind and solar resource prediction time series data.

[0033] The ARIMA prediction model is established using the following method: S1: Determine the difference order (d): By observing the stationarity of the time series, determine the difference order that needs to be applied to the data in order to obtain a stationary time series; S2: Determine the order p of the autoregressive term and the order q of the moving average term: Autoregressive term (AR): The order p of the autoregressive term is determined by the ACF (autocorrelation function) plot. The lag number at which the ACF (autocorrelation function) first becomes significantly lower than the confidence interval is selected as the initial value of p. Moving average (MA): The order q of the moving average is determined by the PACF (partial autocorrelation function) plot. The lag number at which the PACF first significantly falls below the confidence interval is selected as the initial value of q. S3: Model parameter estimation: Estimate the parameters ϕp and θq of the ARIMA model using maximum likelihood estimation or other optimization methods; S4: Model Diagnosis: Check whether the model meets the assumptions through residual analysis and whether the residuals are white noise. If the residuals are white noise, the ARIMA model training is complete and an ARIMA prediction model is formed. S5: Prediction: Use the ARIMA prediction model to predict wind and solar resources for a future period of time; The ARIMA model is represented as ARIMA(p,d,q), and its calculation formula is: Where Xt is time series data (i.e., real-time data of wind and solar resources); L is the lag operator; ϕ1, ϕ2, ..., ϕp are the coefficients of the autoregressive term; θ1, θ2, ..., θq are the coefficients of the moving average term; ϵt is the white noise sequence; and d is the difference order.

[0034] Example 3: As an optimization of Example 2 above, the load forecasting submodule: inputs historical load-related data into a load forecasting multiple linear regression model to obtain load forecasts for a future period. The load forecasting multiple linear regression model is as follows: Among them, L y This is the load forecast; T is temperature; H is humidity; X n These are independent variables other than temperature and humidity; β0, β1, ..., β n ϵ is the regression coefficient and ϵ is the error term.

[0035] The multiple linear regression model for load forecasting is established using the following method: S1: Collect historical data related to the load, including temperature, humidity, season, weekday / weekend, and historical load; S2: Data Processing: Processing the collected data, including feature selection and feature transformation (such as normalization). S3: Model Building: Construct a multiple linear regression model, that is, determine the relationship between the dependent variable (load) and the independent variables; S4: Parameter Estimation: Use the least squares method or other optimization algorithms to estimate the regression coefficients (β0, β1, ..., β) of the multiple linear regression model. n ); S5: Model Validation: Verify the accuracy of the model through cross-validation or hold-out method to ensure that the model has good generalization ability and obtain a multiple linear regression model for load forecasting.

[0036] Example 4: As an optimization of Example 2 above, the energy storage system evaluation submodule collects the charging and discharging data of the energy storage system, calculates the coulombic efficiency based on the charging and discharging data, and evaluates the changing trend of the energy storage system based on the coulombic efficiency.

[0037] Specific methods for assessing the changing trends of energy storage systems based on coulomb efficiency include: S1: Data Collection: Collect charging and discharging data of the energy storage system, including current, voltage, and time during charging, as well as corresponding parameters during discharging.

[0038] S2: Calculate the charge and discharge amount: Calculate the actual charge and discharge amount based on the charge and discharge data. The formula is Q=I×t, where I is the current and t is the time. S3: Calculate the coulomb efficiency: Use the formula to calculate the coulomb efficiency, i.e.: η coulomb = Q discharge / Q charge × 100%, where η coulomb is the coulombic efficiency; Q discharge is the amount of charge discharged; and Q charge is the amount of charge charged. S4: Analysis and Optimization: Evaluate the changing trend of the energy storage system based on the coulombic efficiency, analyze the reasons for the low coulombic efficiency, including battery aging and temperature effects, and propose optimization measures based on the analysis results; S5: Performance Monitoring: Continuously monitor the coulombic efficiency of the energy storage system to assess the trend of system performance changes and provide a basis for maintenance and upgrades.

[0039] Example 5: Figure 3 As shown, as an optimization of the above embodiment 1, the scheduling and optimization module includes a resource scheduling submodule and a ratio optimization submodule. The resource scheduling submodule: using the prediction results of wind and solar resources and load demand and the performance evaluation results of the energy storage system, with the goal of minimizing the operating cost of the system and maximizing the energy utilization rate, considers various scheduling strategies, determines the optimal resource allocation scheme, and generates scheduling instructions.

[0040] The resource scheduling submodule utilizes the predicted results of wind and solar resources and load demand, along with the performance evaluation results of the energy storage system, to construct a multi-objective optimization problem based on the system's operational constraints. During the solution process, the resource scheduling submodule considers various scheduling strategies, including the priority of wind and solar resources, the charging and discharging strategies of the energy storage system, and the interaction strategies with the power grid. Through iterative calculations, it finds the optimal resource allocation scheme that minimizes system operating costs, maximizes energy utilization, and ensures system reliability and stability. Finally, the resource scheduling submodule sends the generated scheduling commands to the control and execution module to achieve real-time control of wind, solar, and energy storage resources.

[0041] Example 6: As an optimization of Example 5 above, the allocation optimization submodule: During the execution of the scheduling instruction, the current energy supply and demand status of the system is analyzed, and an optimization model is constructed. The objective function of the optimization model includes minimizing cost, maximizing revenue, or improving the energy utilization rate of the system. The decision variable in the optimization model is the allocation coefficient between wind, solar, storage and load resources. The optimal allocation coefficient between wind, solar and storage resources is solved, and the optimal allocation coefficient is sent to the resource scheduling submodule. The resource scheduling submodule reallocates resources according to the optimal allocation coefficient, generates a new optimal resource allocation scheme, and generates new scheduling instructions in real time.

[0042] First, the current energy supply and demand situation of the system is analyzed, including the availability of wind and solar resources, the charging and discharging status of the energy storage system, and the changing trends of load demand. Then, based on this information, an optimization model is constructed. The objective function of this model includes minimizing costs, maximizing revenue, or improving the system's energy utilization rate. The decision variables in the optimization model are the matching coefficients between wind, solar, energy storage, and load resources, while the constraints cover the system's technical limitations, economic constraints, and environmental requirements.

[0043] Example 7: A method for resource scheduling and allocation optimization of wind, solar, storage and load under an integrated source-grid-load-storage environment, comprising: Collect real-time data on wind, solar, and energy storage resources and the power grid; Perform data processing on the collected real-time data; The processed data is used to predict wind and solar resources and load demand, and to evaluate the performance of energy storage systems. Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage systems, a scheduling strategy and allocation optimization scheme for wind, solar and energy storage resources are formulated. Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, scheduling instructions are generated to control the wind, solar and storage resources and load in real time in order to achieve the optimal operation of the system. Real-time monitoring of the entire system's operational status.

[0044] In summary, the forecasting and evaluation module is used to predict wind and solar resources and load demand, and to evaluate the performance of the energy storage system, providing the system with accurate forward-looking information. Forecasting wind and solar resources allows the system to understand available renewable energy resources in advance. The accuracy of this forecasting directly affects the resource allocation decisions of the scheduling and optimization module, enabling the system to maximize the use of renewable energy and reduce dependence on fossil fuels while ensuring power supply reliability. By forecasting future load demand, this helps the system prepare for power supply in advance, avoiding the risk of power outages caused by power supply and demand imbalances, and improving user satisfaction. Real-time monitoring and evaluation of the energy storage system's performance provides the scheduling and optimization module with key operational status information. The information scheduling and optimization module ensures that the system maintains optimal operating conditions in complex and ever-changing energy environments, achieving efficient energy utilization and improved economic benefits, providing strong technical support for building a clean, efficient, and stable modern energy system.

[0045] The above technical features constitute various embodiments of the present invention, which have strong adaptability and implementation effect. Unnecessary technical features can be added or removed according to actual needs to meet the needs of different situations.

Claims

1. A system for resource scheduling and allocation optimization of wind, solar, storage, and load in an integrated source-grid-load-storage environment, characterized in that, include: Data acquisition module: Collects real-time data on wind, solar, and energy storage resources and the power grid; Data processing module: processes the collected real-time data; Prediction and Assessment Module: Utilizes processed data to predict wind and solar resources and load demand, and assesses the performance of energy storage systems; Scheduling and optimization module: Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage system, formulate scheduling strategies and allocation optimization schemes for wind, solar and energy storage resources. Control and Execution Module: Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, it generates scheduling instructions to control the wind, solar and storage resources and load in real time to achieve optimal system operation; Monitoring and evaluation module: Real-time monitoring of the entire system's operational status.

2. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment as described in claim 1, characterized in that, The prediction and evaluation module includes a wind and solar resource prediction submodule, a load prediction submodule, and an energy storage system evaluation submodule. The wind and solar resource prediction submodule inputs the time series of real-time wind and solar resource data into the ARIMA prediction model and outputs wind and solar resource prediction time series data.

3. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment as described in claim 2, characterized in that, Load forecasting submodule: Inputs historical load-related data into a load forecasting multiple linear regression model to obtain load forecasts for a future period. The load forecasting multiple linear regression model is as follows: Among them, L y This is the load forecast; T is temperature; H is humidity; X is... n β0, β1, ..., βn are independent variables other than temperature and humidity; β0, β1, ..., βn are regression coefficients, and ϵ is the error term.

4. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment according to claim 2 or 3, characterized in that, Energy storage system evaluation submodule: collects charge and discharge data of the energy storage system, calculates the coulombic efficiency based on the charge and discharge data, and evaluates the changing trend of the energy storage system based on the coulombic efficiency.

5. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment according to claim 1, 2, or 3, characterized in that, The scheduling and optimization module includes a resource scheduling submodule and a resource allocation optimization submodule. The resource scheduling submodule uses the forecast results of wind and solar resources and load demand and the performance evaluation results of the energy storage system to determine the optimal resource allocation scheme and generate scheduling instructions, taking into account various scheduling strategies, with the goal of minimizing the system's operating costs and maximizing energy utilization.

6. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment as described in claim 4, characterized in that, The scheduling and optimization module includes a resource scheduling submodule and a resource allocation optimization submodule. The resource scheduling submodule uses the forecast results of wind and solar resources and load demand and the performance evaluation results of the energy storage system to determine the optimal resource allocation scheme and generate scheduling instructions, taking into account various scheduling strategies, with the goal of minimizing the system's operating costs and maximizing energy utilization.

7. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment as described in claim 5, characterized in that, The allocation optimization submodule analyzes the current energy supply and demand situation of the system during the execution of scheduling instructions, constructs an optimization model, and the objective function of the optimization model includes minimizing costs, maximizing benefits, or improving the energy utilization rate of the system. The decision variable in the optimization model is the allocation coefficient between wind, solar, storage and load resources. The optimal allocation coefficient between wind, solar and storage resources is solved, and the optimal allocation coefficient is sent to the resource scheduling submodule. The resource scheduling submodule reallocates resources according to the optimal allocation coefficient, generates a new optimal resource allocation scheme, and generates new scheduling instructions in real time.

8. The wind-solar-storage-load resource scheduling and allocation optimization system under the integrated source-grid-load-storage environment as described in claim 6, characterized in that, The allocation optimization submodule analyzes the current energy supply and demand situation of the system during the execution of scheduling instructions, constructs an optimization model, and the objective function of the optimization model includes minimizing costs, maximizing benefits, or improving the energy utilization rate of the system. The decision variable in the optimization model is the allocation coefficient between wind, solar, storage and load resources. The optimal allocation coefficient between wind, solar and storage resources is solved, and the optimal allocation coefficient is sent to the resource scheduling submodule. The resource scheduling submodule reallocates resources according to the optimal allocation coefficient, generates a new optimal resource allocation scheme, and generates new scheduling instructions in real time.

9. A method for resource scheduling and allocation optimization of wind, solar, storage, and load in an integrated source-grid-load-storage environment, characterized in that, include: Collect real-time data on wind, solar, and energy storage resources and the power grid; Perform data processing on the collected real-time data; The processed data is used to predict wind and solar resources and load demand, and to evaluate the performance of energy storage systems. Based on the forecast results of wind and solar resources and load demand and the performance evaluation results of energy storage systems, a scheduling strategy and allocation optimization scheme for wind, solar and energy storage resources are formulated. Based on the scheduling strategy and allocation optimization scheme of wind, solar and storage resources, scheduling instructions are generated to control the wind, solar and storage resources and load in real time in order to achieve the optimal operation of the system. Real-time monitoring of the entire system's operational status.

10. The method according to claim 9, characterized in that, The collected real-time data includes wind speed, wind direction, light intensity, temperature, humidity, the charging and discharging status of the energy storage system, the remaining battery capacity, and load demand.

Images