A wind-solar integrated power generation prediction system and method

Abstract

The present invention discloses a wind-solar integrated power generation prediction system and method, which relates to the field of wind-solar integrated power generation technology, including a data acquisition module, a function prediction module, a data processing and analysis module, and a result output and visualization module; in the data acquisition module, a past data acquisition submodule is used: responsible for collecting historical data, including wind tower data, environmental monitoring data, power data, and working data of wind power and photovoltaic units, etc.; at the same time, a real-time data acquisition submodule is used: real-time collection of current wind tower data and environmental dynamic change data. The wind-solar integrated power generation prediction system and method described in the present invention combines past and real-time data, and uses a prediction algorithm to predict the wind tower working data, environmental dynamic change data, power data, and the working status of wind power and photovoltaic units in a future period of time. These data are used to update the prediction model, thereby improving the prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of wind-solar integrated power generation, and in particular to a wind-solar integrated power generation power prediction system and method. Background Art

[0002] With the development of the new energy industry, improving the efficiency of power generation and the level of reliable output has become the key. Deep integration of technologies such as new energy resource assessment and power forecasting will help achieve this goal. With the development of the new energy industry, improving the efficiency of power generation and the level of reliable output has become the key. Deep integration of technologies such as new energy resource assessment and power forecasting will help achieve this goal.

[0003] For example, the Chinese patent publication number CN118040794A discloses a photovoltaic storage and charging integrated power conversion method, device, computer-readable medium and electronic device. The method includes: obtaining the current stored power; when it is detected that the stored power of the photovoltaic storage and charging integrated device is less than or equal to a set first threshold, determining the power generation power based on the stored power, so as to generate power based on the power generation power; when it is detected that the stored power is less than or equal to a set second threshold and greater than the first threshold, then controlling the photovoltaic storage and charging integrated device to be in an energy storage state; when it is detected that the stored power is greater than the second threshold, then determining the discharge power corresponding to the photovoltaic storage and charging integrated device based on the stored power and the battery parameters of the charging device. The technical solution of the present application evaluates the working state of the photovoltaic storage and charging integrated device based on the stored power of the photovoltaic storage and charging integrated device, and determines the power during the power generation and discharge process based on information such as the stored power, thereby improving the operating efficiency and energy application efficiency of the photovoltaic storage and charging system.

[0004] The existing technology has the following problems:

[0005] The uncertainty of existing wind and photovoltaic power generation will bring pressure to the stable operation of the power grid, resulting in poor economic benefits. It cannot fully predict and analyze future changes in electricity consumption, and the accuracy is low. It cannot be scientifically and effectively controlled and managed, resulting in overcapacity of power generation and electricity and insufficient electricity at peak times, affecting the effective distribution of electricity in some areas. Summary of the invention

[0006] The present invention provides a wind-solar integrated power generation prediction system and method to solve the problems raised in the above background technology.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0008] A wind-solar integrated power generation prediction system and method, comprising a data acquisition module, a function prediction module, a data processing and analysis module, and a result output and visualization module;

[0009] In the data acquisition module, the past data acquisition submodule is used: responsible for collecting historical data, including wind tower data, environmental monitoring data, power data, and working data of wind power and photovoltaic units;

[0010] At the same time, the real-time data acquisition submodule is used to collect the current wind tower data and environmental dynamic change data in real time, including wind speed, wind direction, temperature, humidity, air pressure, light intensity, sunshine duration, power data, and real-time working status data of wind power and photovoltaic units;

[0011] In the future data prediction submodule: combining past and real-time data, the prediction algorithm is used to predict the wind tower working data, environmental dynamic change data, power data, and the working status of wind power and photovoltaic units in the future.

[0012] Preferably, in the function prediction module, a time-sharing prediction submodule is used to divide a specified time period of the next day into multiple time periods, and predict and analyze the power of each time period;

[0013] Unified prediction submodule: predicts and analyzes power and electricity within a longer period of time (set as one month) to support long-term power generation plans and grid planning.

[0014] Preferably, the data processing and analysis module is responsible for data cleaning, preprocessing, feature extraction, and establishment of prediction models;

[0015] This module uses advanced algorithms such as machine learning and neural networks to conduct in-depth analysis of the collected data.

[0016] Preferably, the results are output in a visualization module, and the prediction results are displayed in the form of curve graphs, trend graphs, etc., to facilitate user understanding and decision-making; at the same time, the module can also upload the prediction results to the power grid dispatching system to achieve intelligent control of regional power supply.

[0017] Preferably, a method for predicting wind-solar integrated power generation comprises the following steps:

[0018] S1, data collection and preprocessing;

[0019] S2, feature extraction;

[0020] S3, establishing a prediction model;

[0021] S4, model training and optimization;

[0022] S5. Output and application of prediction results.

[0023] Preferably, in step S1, past and real-time wind and solar power generation related data are collected, and cleaned and preprocessed to eliminate abnormal values ​​and missing values;

[0024] In step S2, key features such as wind speed, wind direction, light intensity, etc. are extracted from the preprocessed data. These features are crucial for establishing a prediction model.

[0025] Preferably, in step S3, a combined prediction model is established using machine learning (such as random forest, support vector machine, etc.), neural network (LSTM, CNN) and other algorithms. These models can predict future power generation based on historical data and real-time data; multi-model fusion technology can be used to integrate the prediction results of different models;

[0026] In step S4, the prediction model is trained using historical data, and the model performance is evaluated by methods such as cross-validation; the model is optimized based on the evaluation results.

[0027] Preferably, the prediction results in step S5 are output and applied: the prediction results are presented to the user in the form of curve graphs, trend graphs, etc., and corresponding power generation plans and grid dispatching plans are formulated based on the prediction results.

[0028] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0029] 1. The present invention provides a wind-solar integrated power generation prediction system and method. By combining past and real-time data, a prediction algorithm is used to predict the wind tower working data, environmental dynamic change data, power data, and the working status of wind power and photovoltaic units in the future. These data are used to update the prediction model to improve the prediction accuracy.

[0030] 2. The present invention provides a wind-solar integrated power generation prediction system and method. Through the combination of machine learning models and deep learning models, training is performed based on historical data to predict future power generation. In the deep learning model suitable for processing time series data, the prediction results of multiple algorithms are combined to achieve effective management and improve the robustness and accuracy of the prediction.

[0031] 3. The present invention provides a wind-solar integrated power generation prediction system and method, which trains the prediction model through historical data, evaluates the model performance through cross-validation and other methods, and optimizes the model according to the evaluation results to improve the prediction accuracy and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a structural schematic diagram of the wind-solar integrated power generation prediction system of the present invention;

[0033] Figure 2It is a schematic diagram of the structure of the steps of the wind-solar integrated power generation prediction method of the present invention. DETAILED DESCRIPTION

[0034] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0035] like Figure 1 As shown, a wind-solar integrated power generation prediction system and method includes a data acquisition module, a function prediction module, a data processing and analysis module, and a result output and visualization module;

[0036] In the data acquisition module, the past data acquisition submodule is used: responsible for collecting historical data, including wind tower data, environmental monitoring data, power data, and working data of wind power and photovoltaic units;

[0037] At the same time, the real-time data acquisition submodule is used to collect the current wind tower data and environmental dynamic change data in real time, including wind speed, wind direction, temperature, humidity, air pressure, light intensity, sunshine duration, power data, and real-time working status data of wind power and photovoltaic units;

[0038] In the future data prediction submodule: combining past and real-time data, the prediction algorithm is used to predict the wind tower working data, environmental dynamic change data, power data, and the working status of wind power and photovoltaic units in the future.

[0039] The data acquisition module is responsible for collecting meteorological data related to wind power generation and photovoltaic power generation as well as power station operation data from the external environment. These data are transmitted to the system for processing through the communication protocol. Accurate data collection is the key to improving power prediction accuracy. The data acquisition module also supports remote monitoring and debugging functions, allowing manufacturers or end users to obtain equipment operation information in real time, and make necessary adjustments and optimizations to improve the system's operating efficiency and stability.

[0040] like Figure 1 As shown, in the function prediction module, a time-sharing prediction submodule is used to divide the specified time period of the next day into multiple time periods, and predict and analyze the power of each time period;

[0041] Unified prediction submodule: predicts and analyzes power and electricity within a longer period of time (set as one month) to support long-term power generation plans and grid planning.

[0042] The functional prediction module is the core of the wind-solar integrated power generation prediction system. It uses advanced algorithms and models, such as LSTM multi-port long short-term memory network and chaotic phase space reconstruction neural network method, to predict the future output power of wind power and photovoltaic power generation. Accurate power prediction results help grid dispatchers to reasonably arrange power dispatch, optimize grid operation mode, and ensure the safe, high-quality, economical, environmentally friendly and stable operation of the power system.

[0043] like Figure 1 As shown, the data processing and analysis module is responsible for data cleaning, preprocessing, feature extraction, and establishing a prediction model;

[0044] This module uses advanced algorithms such as machine learning and neural networks to conduct in-depth analysis of the collected data to improve prediction accuracy.

[0045] Responsible for collecting and processing public data, wind power module data and photovoltaic module data, including wind speed, ambient temperature, humidity, equipment installed capacity, etc., improving data quality through noise reduction, normalization and other steps, providing an accurate basis for subsequent analysis, using the processed data to train prediction models such as LSTM multi-port long short-term memory network, and selecting the most appropriate prediction model based on data characteristics to improve prediction accuracy, analyzing the prediction results, evaluating the prediction accuracy, and continuously optimizing the prediction model and algorithm by comparing past data, real-time data and predicted data to improve the performance of the prediction system.

[0046] like Figure 1 As shown, in the result output and visualization module, the prediction results are displayed in the form of curve graphs, trend graphs, etc., which are convenient for users to understand and make decisions; at the same time, the module can also upload the prediction results to the power grid dispatching system to realize intelligent control of regional power supply.

[0047] This module is responsible for outputting the prediction results generated by the prediction system data analysis module, including the future output power of wind power and photovoltaic power generation, etc., to provide a decision-making basis for power grid dispatching. According to the prediction results, it generates corresponding curve model diagrams and reports, such as past data curve model diagrams, real-time curve model diagrams and future prediction analysis curve model diagrams, which are convenient for users to conduct intuitive analysis and comparison. Through visual display, dispatchers can have a clearer understanding of the output power of wind and solar power stations, so as to reasonably arrange dispatching plans, optimize the operation mode of the power grid, and ensure the safe, high-quality, economical, environmentally friendly and stable operation of the power system; at the same time, the prediction results can also be analyzed, and the prediction models and algorithms can be continuously optimized to improve the performance of the prediction system.

[0048] like Figure 2 As shown, a method for predicting wind-solar integrated power generation includes the following steps:

[0049] S1, data collection and preprocessing;

[0050] S2, feature extraction;

[0051] S3, establishing a prediction model;

[0052] S4, model training and optimization;

[0053] S5. Output and application of prediction results.

[0054] like Figure 2 As shown, in step S1, past and real-time wind and solar power generation related data are collected, and cleaned and preprocessed to eliminate abnormal values ​​and missing values ​​and improve data quality;

[0055] In step S2, key features such as wind speed, wind direction, light intensity, etc. are extracted from the preprocessed data. These features are crucial for establishing a prediction model.

[0056] like Figure 2 As shown, in step S3, a combined prediction model is established by using machine learning (such as random forest, support vector machine, etc.), neural network (LSTM, CNN) and other algorithms. These models can predict future power generation based on historical data and real-time data; in order to improve robustness and prediction accuracy, multi-model fusion technology can be used to integrate the prediction results of different models;

[0057] In step S4, the prediction model is trained using historical data, and the model performance is evaluated by methods such as cross-validation; the model is optimized based on the evaluation results to improve the prediction accuracy and stability.

[0058] like Figure 2 As shown, the prediction results in step S5 are output and applied: the prediction results are displayed to the user in the form of curve graphs, trend graphs, etc., and corresponding power generation plans and power grid scheduling plans are formulated based on the prediction results; these plans help to optimize the operation mode of the power grid and improve power generation efficiency and stability.

[0059] The working principle of the present invention is as follows: the data acquisition module is responsible for collecting historical data in the past and collecting current wind tower data and environmental dynamic change data in real time, and the prediction algorithm is used to predict the wind tower working data, environmental dynamic change data, power data and working status of wind power and photovoltaic units in the future period of time by combining the past and real-time data; then the time-sharing prediction submodule in the function prediction module is used to divide the specified time period of the next day into multiple time periods, and the power of each time period is predicted and analyzed, and the unified prediction submodule is used to predict and analyze the power and electricity within a month to support long-term power generation plans and power grid planning; in the data processing and analysis module, the module is responsible for data cleaning, preprocessing, feature extraction and establishment of prediction models, and the module uses machine learning, neural networks and other advanced algorithms to conduct in-depth analysis of the collected data; then in the result output and visualization module, the prediction results are displayed in the form of curve graphs, trend graphs, etc., which is convenient for users to understand and make decisions. At the same time, the module can also upload the prediction results to the power grid dispatching system to realize intelligent control of regional power supply.

[0060] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A wind-solar integrated power generation prediction system, characterized by: It includes data acquisition module, function prediction module, data processing and analysis module, result output and visualization module; In the data acquisition module, the past data acquisition submodule is used: responsible for collecting historical data, including wind tower data, environmental monitoring data, power data, and working data of wind power and photovoltaic units; At the same time, the real-time data acquisition submodule is used to collect the current wind tower data and environmental dynamic change data in real time, including wind speed, wind direction, temperature, humidity, air pressure, light intensity, sunshine duration, power data, and real-time working status data of wind power and photovoltaic units; In the future data prediction submodule: combining past and real-time data, the prediction algorithm is used to predict the wind tower working data, environmental dynamic change data, power data, and the working status of wind power and photovoltaic units in the future.

2. The wind-solar integrated power generation prediction system according to claim 1, characterized in that: In the function prediction module, a time-sharing prediction submodule is used to divide the specified time period of the next day into multiple time periods, and predict and analyze the power of each time period; Unified prediction submodule: predicts and analyzes power and electricity over a longer period of time to support long-term power generation plans and grid planning.

3. The wind-solar integrated power generation prediction system according to claim 1, characterized in that: The data processing and analysis module is responsible for data cleaning, preprocessing, feature extraction, and establishing prediction models; This module uses advanced algorithms such as machine learning and neural networks to conduct in-depth analysis of the collected data.

4. The wind-solar integrated power generation prediction system according to claim 1, characterized in that: The results are output in the visualization module, and the prediction results are displayed in the form of curve graphs, trend graphs, etc., which are convenient for users to understand and make decisions; at the same time, the module can also upload the prediction results to the power grid dispatching system to realize intelligent control of regional power supply.

5. A wind-solar integrated power generation prediction method according to claim 1, based on a wind-solar integrated power generation prediction system according to any one of claims 1-4, characterized in that: The steps include: S1, data collection and preprocessing; S2, feature extraction; S3, establishing a prediction model; S4, model training and optimization; S5. Output and application of prediction results.

6. A method for predicting wind-solar integrated power generation according to claim 5, characterized in that: In step S1, past and real-time wind and solar power generation related data are collected, and cleaned and preprocessed to eliminate abnormal values ​​and missing values; In step S2, key features such as wind speed, wind direction, light intensity, etc. are extracted from the preprocessed data. These features are crucial for establishing a prediction model.

7. The method for predicting wind-solar integrated power generation according to claim 5, characterized in that: In step S3, a combined prediction model is established using machine learning and neural network algorithms. These models can predict future power generation based on historical data and real-time data. Multi-model fusion technology can be used to integrate the prediction results of different models. In step S4, the prediction model is trained using historical data, and the model performance is evaluated by methods such as cross-validation; the model is optimized based on the evaluation results.

8. The method for predicting wind-solar integrated power generation according to claim 5, characterized in that: Output and application of prediction results in step S5: The prediction results are presented to the user in the form of curve graphs, trend graphs, etc., and corresponding power generation plans and grid dispatching plans are formulated based on the prediction results.

Images