Wind and light energy storage strategy optimization method based on data acquisition and monitoring control system

Abstract

The invention belongs to the technical field of new energy power generation scheduling and energy management, and discloses a wind and light energy storage strategy optimization method based on a data acquisition and monitoring control system, and the method comprises the following specific steps: S1, multi-source data acquisition; s2, data preprocessing and feature extraction; s3, performing short-term prediction calculation; s4, energy storage scheduling optimization calculation; s5, generating and issuing a scheduling instruction; s6, scheduling execution monitoring and feedback acquisition; and S7, carrying out closed-loop deviation analysis and strategy correction. According to the invention, through multi-source data acquisition and preprocessing, key parameters such as wind speed, illumination and state of charge, historical power and load data are jointly analyzed, and a hybrid prediction method combining time sequence prediction and environment variable correction is adopted, so that higher-precision prediction of wind and light output and load trend is realized; this prediction not only captures the time continuity of the power variation.

Description

Technical Field

[0001] This invention belongs to the field of new energy power generation dispatch and energy management technology, specifically a wind-solar-storage strategy optimization method based on data acquisition and monitoring control system. Background Technology

[0002] With the large-scale grid connection of wind farms and photovoltaic power plants, the output of new energy sources is characterized by strong volatility and high unpredictability, which poses a huge challenge to grid dispatch and system stability. Most existing energy storage dispatch methods adopt fixed thresholds or start-up and shutdown strategies based on a single data source, failing to combine multi-source real-time data for accurate prediction and dynamic optimization. This results in insufficient suppression of power fluctuations, low utilization efficiency of energy storage systems, and even performance degradation of energy storage units due to overcharging and over-discharging.

[0003] Traditional forecasting methods often rely solely on time series trends, neglecting the nonlinear effects of environmental changes, making it difficult to meet scheduling requirements in complex scenarios. At the same time, existing systems lack an effective closed loop between forecasting, optimization, command issuance, and on-site execution, and feedback data such as power response, state of charge changes, and equipment alarms are not fully utilized, resulting in the system's inability to promptly correct forecasting models and scheduling strategies based on actual results. Summary of the Invention

[0004] The purpose of this invention is to provide a wind-solar-storage strategy optimization method based on a data acquisition and monitoring control system, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a wind-solar-storage energy strategy optimization method based on a data acquisition and monitoring control system, wherein the specific steps of the wind-solar-storage energy strategy optimization method based on a data acquisition and monitoring control system are as follows:

[0006] S1, Multi-source data acquisition: Real-time operating data of wind farms, photovoltaic power plants, energy storage systems and grid side are acquired through data acquisition and monitoring control system. The data includes wind speed, light intensity, ambient temperature, energy storage state of charge, grid frequency and user load, providing input basis for subsequent data processing and prediction.

[0007] S2, Data preprocessing and feature extraction: The real-time data is denoised, anomaly detected, missing value filled and standardized, and key feature parameters related to power fluctuations and load changes are extracted to ensure the quality of input data and the effectiveness of features, so as to improve prediction accuracy;

[0008] S3, Short-term forecast calculation: Based on the aforementioned characteristic parameters, a hybrid forecasting method combining an autoregressive moving average model and a machine learning model based on environmental variables is used to predict the wind and solar power output and load trends within the future scheduling cycle. The forecast results serve as the direct input for energy storage scheduling optimization calculation.

[0009] S4, Energy storage scheduling optimization calculation: Using the prediction results, the current energy storage state of charge and energy storage health status (including cycle life, capacity decay and temperature rise level), under the condition of following system operation constraints, dynamically calculate the charging and discharging power, start and stop timing and energy storage unit priority of the next scheduling cycle, form an optimized scheduling scheme, and enable scheduling and prediction to be linked.

[0010] S5, Generation and issuance of dispatch instructions: Based on the optimized dispatch scheme, generate specific control instructions including power setting, start and stop commands, and dispatch priority, and issue them to wind turbines, photovoltaic modules and energy storage units in real time through the data acquisition and monitoring control system to ensure that the content of the instructions matches the capabilities of the field equipment.

[0011] S6, Dispatch Execution Monitoring and Feedback Collection: During the issuance and execution of instructions, the dispatch effect is monitored in real time, and feedback data such as power response, state of charge change, prediction deviation, load response and equipment alarm information are collected to provide on-site verification basis for closed-loop adjustment;

[0012] S7, Closed-loop deviation analysis and strategy correction: Based on the feedback data, perform prediction and actual deviation analysis, scheduling effect evaluation and equipment status verification, dynamically correct the prediction model parameters, scheduling optimization objectives and constraints, provide updated calculation basis for the next scheduling cycle, and form a continuous iterative optimization closed loop.

[0013] Preferably, the specific steps of multi-source data acquisition in S1 include the following:

[0014] S11, On-site Multi-Source Data Acquisition: Through the data acquisition and monitoring control system, real-time operational data, including wind speed, solar irradiance, ambient temperature, and energy storage state of charge, is acquired from wind farms, photovoltaic power plants, and energy storage systems. This data serves as the basis for subsequent system analysis, reflecting the current available wind and solar power generation potential and energy storage capacity, and providing accurate input for predictive models.

[0015] The formula for calculating wind and solar power is:

[0016] P=A×η×I

[0017] P: Photovoltaic power (W) or wind power (W), A: Effective area of ​​the module (m2) or swept area of ​​the wind turbine (m2), η: Conversion efficiency (dimensionless), I: Irradiance (W / m2) or kinetic energy density converted from wind speed (W / m2).

[0018] Source: Physics / The law of conservation of energy is used to calculate instantaneous power from parameters such as wind speed and light intensity collected on-site, and is used as a predictive input.

[0019] S12, Grid-side and power-side parameter acquisition: Grid frequency, user load, and actual wind and solar power output are simultaneously collected. By combining environmental conditions such as wind speed and solar irradiance with equipment characteristics, the actual power of wind turbines and photovoltaic modules is calculated. This power calculation is based on energy conversion efficiency and effective equipment area, ensuring that the forecasting process's assessment of power generation capacity is closer to real-world operating conditions.

[0020] Preferably, the specific steps of data preprocessing and feature extraction in S2 include the following:

[0021] S21, Data Cleaning and Feature Extraction: The collected real-time data is denoised, outlier identified, missing items filled in, and standardized to ensure that the data source is consistent and the range is reasonable; then, key features directly related to power fluctuations and load changes, such as wind speed fluctuation amplitude and light stability, are extracted to provide robust input conditions for subsequent forecasts.

[0022] S22, Energy Storage State Assessment and Constraint Configuration: This section introduces health state parameters into energy storage scheduling optimization, including cycle count, capacity retention rate, and temperature rise, dynamically adjusting the upper charge limit and lower discharge limit. This effectively prevents performance degradation caused by overcharging or over-discharging, ensuring that scheduling calculations not only focus on power balance but also consider the long-term stability of the energy storage system.

[0023] Preferably, the specific steps for short-term forecast calculation in S3 include the following:

[0024] S31, Time Series Trend Prediction: Based on the extracted historical power, load changes and other features, an autoregressive moving average model is used to predict short-term trends; this model can capture the continuity and fluctuation characteristics in the time series, and provide the system with a baseline judgment of wind and solar power output and load in the future.

[0025] S32, Environment-Driven Nonlinear Correction: Incorporating environmental variables (such as sudden weather changes) into a machine learning prediction model to correct time series prediction results and improve adaptability to nonlinear fluctuations; the final prediction results will serve as direct input to the optimization calculation process to more accurately formulate energy storage scheduling plans.

[0026] The formula for the model's predictive expression principle is:

[0027]

[0028] In the formula, Xt: predicted value, c: constant term, Autoregressive coefficient, θ: moving average coefficient, ∈t: white noise term.

[0029] Source: Classical time series analysis methods, combined with machine learning corrections, used to predict wind and solar power output and load in the short term.

[0030] Preferably, the specific steps of the energy storage scheduling optimization calculation in S4 include the following:

[0031] S41, Dynamic calculation of charging and discharging power: Combining the predicted power gap, current state of charge and equipment capacity limitations, the available charging and discharging power for the next cycle is dynamically calculated; during this process, the upper limits of charging and discharging are considered to ensure that while meeting the scheduling requirements, the safety and performance boundaries of the energy storage system are followed, and anomalies caused by overload are avoided.

[0032] Optimal expression formula for energy storage charging and discharging power:

[0033]

[0034] In the formula, Pch / dis: charging or discharging power (W), SOCmax: maximum allowable state of charge (%), SOC: current state of charge (%), Δt: scheduling period (h), Pch / dis_max: maximum charging and discharging power of energy storage (W);

[0035] Source: Energy storage system control strategy, used to determine the charging and discharging amount, avoid overcharging and over-discharging, and dynamically adjust in combination with health status parameters;

[0036] S42, Start-up and Shutdown Timing and Priority Arrangement: Based on power calculations, the health status of energy storage units is comprehensively evaluated, such as cycle life, capacity decay, and temperature rise levels, to determine the priority scheduling order and start-up and shutdown timing. By prioritizing the use of units in better condition and with faster response, efficient linkage between scheduling strategies and prediction results is achieved, improving overall system stability.

[0037] Preferably, the specific steps for generating and issuing scheduling instructions in S5 include the following:

[0038] S51, Generate scheduling instructions for matching equipment: Based on the optimized scheduling scheme, generate specific control instructions including power setting, start / stop instructions and priority sorting; when formulating instructions, fully consider the technical parameters and operating capabilities of the field equipment to avoid exceeding the safety range of wind turbines, photovoltaic modules and energy storage units, so as to ensure that the instructions are executable;

[0039] S52 executes commands in real time through the system: The generated scheduling instructions are distributed to each operating unit in real time via the data acquisition and monitoring control system, and protocol adaptation is performed with the field controllers to ensure that the distributed information is fully compatible with the equipment in terms of format, time synchronization, and response requirements. This process ensures that the optimization solution not only remains at the computational level but can also be implemented on-site.

[0040] Preferably, the specific steps for scheduling execution monitoring and feedback collection in S6 include the following:

[0041] S61, Real-time monitoring of power and load response: During command issuance and equipment execution, the system monitors power output, state of charge, and load-side changes in real time; by comparing predicted and actual values, the current deviation level is identified, providing basic data for subsequent evaluation of prediction accuracy and scheduling effectiveness, ensuring that the system operates as expected;

[0042] The formula for calculating the prediction deviation rate is as follows:

[0043] Error_rate=|Ppred-Pact| / Pact

[0044] In the formula, Error_rate: prediction error rate, Ppred: predicted power (W), Pact: actual power (W);

[0045] Source: Engineering error analysis is used in field monitoring to evaluate the error between predicted and actual results;

[0046] S62, Acquisition of Feedback and Alarm Information: The system continuously collects feedback information from the equipment, including response delay, abnormal fluctuations, and alarm signals, to calculate the overall prediction deviation rate. This assessment not only focuses on power deviation but also covers load changes and energy storage status, providing a comprehensive and reliable on-site verification basis for subsequent optimization.

[0047] Preferably, the specific steps of closed-loop deviation analysis and strategy correction in S7 include the following:

[0048] S71, Deviation Analysis and Effect Evaluation: Based on the collected feedback data, the system analyzes the deviation between the predicted and actual values ​​and evaluates the overall effect of the scheduling scheme in terms of power response, state of charge management and load matching; at the same time, it checks the equipment status, identifies abnormalities or bottlenecks that occur during operation, and provides accurate references for subsequent optimization.

[0049] S72, Model Correction and Strategy Update: Based on the results of deviation analysis and effect evaluation, the weight parameters of the prediction model are dynamically adjusted, and the target and constraint configuration of the scheduling optimization are corrected. This ensures that the calculation of the next scheduling cycle is more in line with the actual operating characteristics, realizes the system's self-learning and continuous optimization, and improves the overall stability and adaptability.

[0050] The beneficial effects of this invention are as follows:

[0051] 1. This invention incorporates key parameters such as wind speed, solar radiation, and state of charge, along with historical power and load data, into the analysis through multi-source data acquisition and preprocessing. It adopts a hybrid prediction method that combines time series forecasting with environmental variable correction, achieving higher accuracy in predicting wind and solar power output and load trends. This prediction not only captures the temporal continuity of power changes but also senses nonlinear fluctuations caused by sudden weather or equipment status changes, thus providing a more reliable input basis for energy storage scheduling and significantly improving the system's adaptability and predictive response capabilities in complex environments.

[0052] 2. This invention introduces energy storage health status parameters, including cycle life, capacity decay, and temperature rise level, into the scheduling optimization process to dynamically adjust the charging and discharging power and start / stop priority of each energy storage unit. This design avoids the crude approach of simply allocating tasks according to power gaps and effectively prevents performance degradation and shortened lifespan caused by overcharging, over-discharging, or high-temperature operation. Through health-aware scheduling, the system can not only utilize each energy storage unit more evenly but also reduce the maintenance burden caused by high-intensity operation, thereby improving the overall reliability and economy of the energy storage system.

[0053] 3. This invention achieves closed-loop linkage of prediction, optimization, execution, and correction through real-time issuance and feedback collection of scheduling instructions. The system not only monitors power response and load changes, but also dynamically corrects model parameters and optimization strategies by analyzing prediction deviations, load responses, and equipment alarms. This closed-loop mechanism ensures that the scheduling scheme can be continuously iterated and updated based on actual results, solving the problem of the disconnect between prediction and execution in traditional schemes. It enables the system to have self-learning and continuous optimization capabilities, greatly improving the operational stability and scheduling flexibility in new energy scenarios. Attached Figure Description

[0054] Figure 1 This is a flowchart of the wind and solar energy storage strategy optimization method based on the data acquisition and monitoring control system of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] like Figure 1As shown in the figure, this invention provides a method for optimizing wind-solar-storage energy storage strategies based on a data acquisition and monitoring control system. The specific steps of this method are as follows:

[0057] S1, Multi-source data acquisition: Real-time operating data of wind farms, photovoltaic power plants, energy storage systems and grid side are acquired through data acquisition and monitoring control system. The data includes wind speed, light intensity, ambient temperature, energy storage state of charge, grid frequency and user load, providing the input basis for subsequent data processing and prediction.

[0058] S2, Data Preprocessing and Feature Extraction: Denoising, anomaly detection, missing value completion and standardization are performed on real-time data, and key feature parameters related to power fluctuations and load changes are extracted to ensure the quality of input data and the effectiveness of features, so as to improve prediction accuracy;

[0059] S3, Short-term forecast calculation: Based on characteristic parameters, a hybrid forecasting method combining an autoregressive moving average model and a machine learning model based on environmental variables is used to predict the power output and load trends of wind and solar power generation in the future scheduling cycle. The forecast results serve as the direct input for energy storage scheduling optimization calculation.

[0060] S4, Energy Storage Scheduling Optimization Calculation: Utilizing the prediction results, the current energy storage state of charge and the energy storage health status (including cycle life, capacity decay, and temperature rise level), and under the condition of following system operation constraints, dynamically calculate the charging and discharging power, start-up and shutdown timing, and energy storage unit priority for the next scheduling cycle to form an optimized scheduling scheme, enabling scheduling and prediction to be linked.

[0061] S5, Dispatch instruction generation and issuance: Based on the optimized dispatch scheme, generate specific control instructions including power setting, start and stop commands, dispatch priority, etc., and issue them to wind turbines, photovoltaic modules and energy storage units in real time through the data acquisition and monitoring control system to ensure that the instruction content matches the capabilities of the field equipment.

[0062] S6, Dispatch Execution Monitoring and Feedback Collection: During the issuance and execution of instructions, the dispatch effect is monitored in real time, and feedback data such as power response, state of charge change, prediction deviation, load response and equipment alarm information are collected to provide on-site verification basis for closed-loop adjustment;

[0063] S7, Closed-loop Deviation Analysis and Strategy Correction: Based on feedback data, perform prediction and actual deviation analysis, scheduling effect evaluation and equipment status verification, dynamically correct prediction model parameters, scheduling optimization objectives and constraints, provide updated calculation basis for the next scheduling cycle, and form a continuous iterative optimization closed loop.

[0064] Example 1: Standard wind-solar-storage energy storage scenario application

[0065] In a power grid system where a wind farm and a photovoltaic power station are jointly connected, the method of this invention is adopted. A SCADA system is used to collect real-time data on wind speed, solar irradiance, ambient temperature, energy storage state of charge, grid frequency, and load. The system uses a time series and environmental correction model to predict the wind and solar power output and load trends for the next hour. Based on the prediction results and the current state of the energy storage, the system dynamically calculates the charging and discharging power and start-up / shutdown plan for the next 15-minute cycle and distributes this information to the energy storage system and new energy equipment. The system monitors the power response and deviation every minute and updates the prediction and scheduling parameters in the next cycle to achieve steady-state operation and fluctuation suppression.

[0066] Example 2: Adaptive Scheduling for Complex Weather

[0067] In offshore wind farm applications, wind speed and climate changes are frequent. After introducing the solution of this invention, the system not only collects conventional data, but also takes into account storm and gale warning information. The prediction module combines historical data with real-time environmental anomalies to make corrections, thereby improving the accuracy of short-term predictions. The energy storage scheduling part reserves a safety margin based on the predicted fluctuation range and prioritizes scheduling battery cells with better health conditions to reduce scheduling failures caused by abnormal weather. By monitoring prediction deviations and equipment status in real time, the system can dynamically adjust parameters under severe weather conditions to ensure stable grid-connected power.

[0068] Example 3: Collaborative Optimization Scheduling of Multiple Energy Storage Units

[0069] In a wind-solar hybrid power station equipped with multiple energy storage units (lithium batteries, supercapacitors, and sodium-sulfur batteries), the system collects the independent state of charge, health parameters, and response characteristics of each energy storage unit. The scheduling optimization calculation considers the health weight and dynamic capabilities of each energy storage unit, and allocates the power contribution and priority of different units according to the predicted gap. After the control commands are decomposed, they are distributed to each unit, and its response, temperature, and alarm information are monitored in real time. The strategy for the next cycle is adjusted through deviation analysis to achieve efficient collaboration among multiple units and improve the overall scheduling flexibility.

[0070] In S1, multi-source data acquisition refers to obtaining real-time operational data from wind farms, photovoltaic power plants, and energy storage systems through a data acquisition and monitoring control system. This data includes wind speed, solar irradiance, ambient temperature, and energy storage state of charge. This data serves as the basis for subsequent system analysis, reflecting the current available wind and solar power generation potential and energy storage capacity, and providing accurate input for predictive models.

[0071] The formula for calculating wind and solar power is:

[0072] P=A×η×I

[0073] P: Photovoltaic power (W) or wind power (W), A: Effective area of ​​the module (m2) or swept area of ​​the wind turbine (m2), η: Conversion efficiency (dimensionless), I: Irradiance (W / m2) or kinetic energy density converted from wind speed (W / m2).

[0074] Source: Physics / The law of conservation of energy is used to calculate instantaneous power from parameters such as wind speed and light intensity collected on-site, and is used as a predictive input;

[0075] The system synchronously collects data on grid frequency, user load, and actual wind and solar power output. By combining environmental conditions such as wind speed and solar irradiance with equipment characteristics, it calculates the actual power output of wind turbines and photovoltaic modules. This power calculation is based on energy conversion efficiency and effective equipment area, ensuring that the forecasting process more closely approximates real-world operating conditions in its assessment of power generation capacity.

[0076] In S2, data preprocessing and feature extraction refer to denoising, outlier identification, missing item completion, and standardization of the collected real-time data to ensure consistent data sources and reasonable ranges. Subsequently, key features directly related to power fluctuations and load changes, such as wind speed fluctuation amplitude and light stability, are extracted to provide robust input conditions for subsequent predictions. In energy storage scheduling optimization, health state parameters, including cycle count, capacity retention rate, and temperature rise, are introduced to dynamically adjust the upper limit of charge and the lower limit of discharge. This can effectively prevent performance degradation caused by overcharging or over-discharging, so that scheduling calculations not only focus on power balance but also take into account the long-term stability of the energy storage system.

[0077] The S3 short-term forecast calculation refers to using an autoregressive moving average model to predict short-term trends based on extracted historical power and load changes. This model can capture the continuity and fluctuation characteristics in time series data, providing the system with a baseline judgment of wind and solar power output and load over a future period. By incorporating environmental variables (such as sudden weather changes) into a machine learning prediction model, the time series forecast results are corrected, improving the system's adaptability to nonlinear fluctuations. The final forecast results will serve as direct input to the optimization calculation stage, enabling more accurate energy storage scheduling plans.

[0078] The formula for the model's predictive expression principle is:

[0079]

[0080] In the formula, Xt: predicted value, c: constant term, Autoregressive coefficient, θ: moving average coefficient, ∈t: white noise term.

[0081] Source: Classical time series analysis methods, combined with machine learning corrections, used to predict wind and solar power output and load in the short term.

[0082] Among them, the energy storage dispatch optimization calculation in S4 refers to dynamically calculating the available charging and discharging power for the next cycle by combining the predicted power gap, the current state of charge, and the equipment capacity limit. In this process, the upper limit of charging and discharging will be considered to ensure that while meeting the dispatch requirements, the safety and performance boundaries of the energy storage system are followed, and to avoid anomalies caused by overload.

[0083] Optimal expression formula for energy storage charging and discharging power:

[0084]

[0085] In the formula, Pch / dis: charging or discharging power (W), SOCmax: maximum allowable state of charge (%), SOC: current state of charge (%), Δt: scheduling period (h), Pch / dis_max: maximum charging and discharging power of energy storage (W);

[0086] Source: Energy storage system control strategy, used to determine the charging and discharging amount, avoid overcharging and over-discharging, and dynamically adjust in combination with health status parameters;

[0087] Based on power calculations, the health status of energy storage units is comprehensively evaluated, including cycle life, capacity decay, and temperature rise levels, to determine the priority scheduling order and start-up / shutdown timing. By prioritizing the use of units in better condition and with faster response times, efficient linkage between scheduling strategies and prediction results is achieved, thereby improving overall system stability.

[0088] In S5, the generation and issuance of dispatch instructions refers to generating specific control instructions, including power settings, start / stop instructions, and priority sorting, based on the optimized dispatch scheme. When formulating instructions, the technical parameters and operating capabilities of the field equipment are fully considered to avoid exceeding the safety range of wind turbines, photovoltaic modules, and energy storage units, so as to ensure that the instructions are executable.

[0089] The generated scheduling instructions are distributed to each operating unit in real time through the data acquisition and monitoring control system, and protocol adaptation is performed with the field controllers to ensure that the distributed information is fully compatible with the equipment in terms of format, time synchronization, and response requirements. This process ensures that the optimization scheme not only remains at the computing level, but can also be implemented on the engineering site.

[0090] In S6, scheduling execution monitoring and feedback collection refers to the system's real-time monitoring of power output, state of charge, and load-side changes during command issuance and equipment execution. By comparing predicted and actual values, the current deviation level is identified, providing basic data for subsequent evaluation of prediction accuracy and scheduling effectiveness, and ensuring that the system operates as expected.

[0091] The formula for calculating the prediction deviation rate is as follows:

[0092] Error_rate=|Ppred-Pact| / Pact

[0093] In the formula, Error_rate: prediction error rate, Ppred: predicted power (W), Pact: actual power (W);

[0094] Source: Engineering error analysis is used in field monitoring to evaluate the error between predicted and actual results;

[0095] The system continuously collects feedback information from the equipment, including response delay, abnormal fluctuations, and alarm signals, to calculate the overall prediction deviation rate. This assessment not only focuses on power deviation but also covers load changes and energy storage status, providing a comprehensive and reliable on-site verification basis for subsequent optimization.

[0096] In S7, closed-loop deviation analysis and strategy correction refer to the system analyzing the deviation between predicted and actual values ​​based on the collected feedback data, and evaluating the overall effectiveness of the scheduling scheme in terms of power response, state of charge management and load matching; at the same time, it checks the equipment status, identifies abnormalities or bottlenecks that occur during operation, and provides accurate references for subsequent optimization.

[0097] Based on the results of deviation analysis and effect evaluation, the weight parameters of the prediction model are dynamically adjusted, and the target and constraint configuration of scheduling optimization are corrected. This ensures that the calculation of the next scheduling cycle is more in line with the actual operating characteristics, realizes the system's self-learning and continuous optimization, and improves the overall stability and adaptability.

[0098] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0099] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A wind-solar-storage energy strategy optimization method based on a data acquisition and monitoring control system, characterized in that: The specific steps of this wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system are as follows: S1, Multi-source data acquisition: Real-time data from wind power, photovoltaics, energy storage and the grid side are acquired through the monitoring and control system to provide reliable input for subsequent processing and forecasting; S2, Data Preprocessing and Feature Extraction: Cleaning, correcting and standardizing the collected data, extracting key features such as power fluctuations and load changes to improve prediction accuracy; S3, Short-term forecast calculation: Combining time series and environmental correction models, it predicts the wind and solar power output and load trends in the short period, providing input for scheduling optimization; S4, Energy Storage Scheduling Optimization Calculation: Based on predictions and energy storage health status, dynamically calculate power allocation, start-up and shutdown timing, and unit priority under operational constraints; S5, Scheduling instruction generation and issuance: Generate scheduling instructions that match the capabilities of the equipment and issue them to each unit in real time through the monitoring system to ensure that execution is feasible; S6, Dispatch Execution Monitoring and Feedback Acquisition: Real-time monitoring of power, charge, load and alarm feedback, evaluation of dispatch effectiveness, and data support for closed-loop adjustment; S7, Closed-loop deviation analysis and strategy correction: Analyze the deviation between prediction and actual results, dynamically adjust model parameters and optimization objectives, and continuously improve the scheduling scheme for the next cycle.

2. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for multi-source data acquisition in S1 include the following: S11, On-site multi-source data acquisition: Real-time operating data, including wind speed, light intensity, ambient temperature and energy storage status, are obtained from wind farms, photovoltaic power stations and energy storage systems through the data acquisition and monitoring control system. The formula for calculating wind and solar power is: P = A × η × I P: Photovoltaic power or wind power, A: Effective area of ​​the module or swept area of ​​the wind turbine, η: Conversion efficiency, I: Kinetic energy density converted from irradiance or wind speed; S12, Grid-side and power-side parameter acquisition: Synchronously collect grid frequency, user load and actual wind and solar power output, and calculate the actual power of wind turbines and photovoltaic modules by combining environmental conditions such as wind speed and sunlight with equipment characteristics.

3. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps of data preprocessing and feature extraction in S2 include the following: S21, Data Cleaning and Feature Extraction: The collected real-time data is denoised, outlier identified, missing items filled in, and standardized to ensure that the data source is consistent and the range is reasonable; then, key features directly related to power fluctuations and load changes are extracted. S22, Energy Storage Status Assessment and Constraint Configuration: Introduce health status parameters in energy storage scheduling optimization, including cycle count, capacity retention rate and temperature rise, and dynamically adjust the upper limit of charge and the lower limit of discharge.

4. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for short-term forecast calculation in S3 include the following: S31, Time Series Trend Forecasting: Based on the extracted historical power and load change features, an autoregressive moving average model is used to predict short-term trends; S32, Environment-driven nonlinear correction: Incorporating environmental variables into a machine learning prediction model to correct time series prediction results. The final prediction results will serve as direct input for the optimization calculation process, enabling more accurate energy storage scheduling plans. The formula for the model's predictive expression principle is: In the formula, Xt: predicted value, c: constant term, Autoregressive coefficient, θ: moving average coefficient, ∈t: white noise term. Source: Classical time series analysis methods, combined with machine learning corrections, used to predict wind and solar power output and load in the short term.

5. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for energy storage scheduling optimization calculation in S4 include the following: S41, Dynamic calculation of charging and discharging power: Based on the predicted power gap, current state of charge and equipment capacity limitations, dynamically calculate the available charging and discharging power for the next cycle; Optimal expression formula for energy storage charging and discharging power: In the formula, Pch / dis: charging or discharging power, SOCmax: maximum allowable state of charge, SOC: current state of charge, Δt: scheduling period, Pch / dis_max: maximum charging and discharging power of energy storage. S42, Start-up and shutdown timing and priority arrangement: Based on power calculation, comprehensively assess the health status of the energy storage unit and determine the priority scheduling order and start-up and shutdown timing.

6. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for generating and issuing scheduling instructions in S5 include the following: S51, Generate scheduling instructions for matching equipment: Based on the optimized scheduling scheme, generate specific control instructions including power setting, start / stop instructions and priority sorting; S52, through real-time system execution: The generated scheduling instructions are sent to each operating unit in real time through the data acquisition and monitoring control system, and the protocol is adapted with the field controller to ensure that the sent information is fully matched with the equipment in terms of format, time synchronization and response requirements.

7. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for scheduling execution monitoring and feedback collection in S6 include the following: S61, Real-time monitoring of power and load response: During command issuance and equipment execution, the system monitors power output, state of charge, and load-side changes in real time; by comparing predicted values ​​with actual values, the current deviation level is identified; The formula for calculating the prediction deviation rate is as follows: Error_rate=|Ppred-Pact| / Pact In the formula, Error_rate: prediction error rate, Ppred: predicted power (W), Pact: actual power (W); S62, Collection of Feedback and Alarm Information: The system continuously collects feedback information from the equipment, including response delay, abnormal fluctuations, and alarm signals, to calculate the overall prediction deviation rate.

8. The wind-solar-storage energy strategy optimization method based on data acquisition and monitoring control system according to claim 1, characterized in that: The specific steps for closed-loop deviation analysis and strategy correction in S7 include the following: S71, Deviation Analysis and Effect Evaluation: Based on the collected feedback data, the system analyzes the deviation between the predicted and actual values ​​and evaluates the overall effect of the scheduling scheme in terms of power response, state of charge management and load matching; at the same time, it checks the equipment status, identifies abnormalities or bottlenecks that occur during operation, and provides accurate references for subsequent optimization. S72, Model Correction and Strategy Update: Based on the results of bias analysis and effect evaluation, dynamically adjust the weight parameters of the prediction model and correct the target and constraint configuration of the scheduling optimization.

Images