Two-Stage Hybrid Deep Learning With Strong Adaptability for Detailed Day-Ahead Photovoltaic Power Forecasting

Abstract

Deep learning (DL) has been widely used in photovoltaic (PV) power forecasting due to its advantages in nonlinear processing and feature extraction. However, it faces an overfitting challenge when daily weather change, resulting in poor adaptability for practical applications. Conversely, the mapping strategy primarily applied in plant sacrifices the PV power fluctuation details for forecasting under complex weather conditions to improve adaptation. To keep long-term adaptations and accurately forecast fluctuation detail, this study proposes a novel two-stage hybrid DL (HDL) framework for day-ahead PV power forecasting with 15-min intervals. In the first numerical weather prediction (NWP) information mapping stage, motivated by forecasting strategies in plants, a mapping model is developed based on long short-term memory (LSTM) networks to forecast the general power trends with strong adaptation. Then, in the second stage of historical features (adjacency and similarity features) extraction, wavelet decomposition, LSTM, and a convolutional neural network are used to forecast more fluctuation details accurately. Moreover, a hyperparameter optimization method based on grid search and Bayesian optimization is proposed, which facilitates an unbiased development of DL. The developed framework is implemented on 10 MW and 100 kW plants and the results show that the proposed method can achieve correctness and adaptation among the rivals.