Cloud Feature Extraction and Fluctuation Pattern Recognition Based Ultrashort-Term Regional PV Power Forecasting

Regional photovoltaic(PV) power forecasting provides a foundation for grid management and trading in the power markets. To tackle the deficiency of conventional regional PV power modeling methods, such as the problem of challenging to select useful meteorological information and the problem that a single model cannot fully learn the complex and diverse fluctuation characteristics of power curves, an ultrashort-term regional PV power forecasting framework assembled by fusing fluctuation pattern recognition (FPR) and deep learning modeling under a fluctuation pattern prediction (FPP) model was proposed. First of all, the fluctuation characteristics of the regional PV power curves were extracted, including sampling loss area, mean value, standard deviation, and third derivative. Then, a K-means algorithm based FPR model was established to obtained three kinds of patterns. FPP model based on convolutional neural network is used to predict future PV power fluctuation patterns with historical satellite images as input. Finally, the convolutional autoencoder is used to extract cloud distribution features, and a long- and short-term memory network based on the combination of cloud distribution features and historical output is proposed to construct prediction models of the three models. Through the analysis of the simulation data, the prediction method proposed in this article has higher prediction accuracy than the traditional prediction model.

Automated summary

This article proposes a new framework for ultrashort-term regional PV power forecasting, which improves prediction accuracy by combining fluctuation pattern recognition and deep learning modeling.