研究目的
To improve the accuracy of PV output prediction by combining gray correlation theory to select similar days with BP neural network.
研究成果
The method of selecting the similar day by adding the grey relational theory can improve the prediction accuracy of sunny and cloudy weather, especially in non-sunny weather with large fluctuations.
研究不足
The study does not mention the limitations explicitly, but potential areas for optimization could include the consideration of more weather factors and the improvement of the neural network model.
1：Experimental Design and Method Selection:
The study combines gray correlation analysis to select similar days and BP neural network for PV output prediction.
2：Sample Selection and Data Sources:
Actual data from a photovoltaic power plant in Northeast China was selected as experimental data.
3：List of Experimental Equipment and Materials:
MATLAB simulation platform was used for validation.
4：Experimental Procedures and Operational Workflow:
The model calculates the weather factors between sample days and forecast days to find similar days, assigns weights to historical data of similar days, and uses BP neural network for prediction.
5：Data Analysis Methods:
The accuracy of the method was judged by comparing the root mean square error (RMSE) and the mean absolute error (MAE) between the predicted and actual values.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
