Ultra-Short-Term Photovoltaic Power Forecasting Based on Causal Feature Extraction and an Improved Q-Learning Algorithm
Photovoltaic (PV) power forecasting is challenged by redundant meteorological features, insufficient multi-timescale dynamic response, and the lack of dynamic adaptability in hybrid models. This study proposes an ultra-short-term forecasting framework integrating causal feature extraction with an improved Q-learning (IQ-L) algorithm. First, an entropy-based causal feature extraction method quantifies nonlinear coupling between meteorological variables and PV power, filtering key factors. Second, a parallel prediction model combining bidirectional long short-term memory (BiLSTM) and TCN-Transformer captures short-term fluctuations, local patterns, and long-term dependencies, enabling multi-scale feature fusion. Third, an improved Q-learning algorithm with a dynamic reward-penalty mechanism, incorporating a cosine factor, iteratively adjusts the weights of sub-models to produce the final forecast. Validation under three typical weather conditions shows that the proposed model achieves stable performance. On rainy days, compared with a single BiLSTM model, the proposed method reduces ERMSE and EMAE by an average of 49.3% and 51.9%, respectively, demonstrating enhanced accuracy and generalization. The framework addresses the limitations of static weight allocation and single reward mechanisms in existing hybrid approaches, offering a robust solution for grid dispatch and energy storage optimization.