Bi-xLSTM-Informer for Short-Term Photovoltaic Forecasting: Leveraging Temporal Symmetry and Feature Optimization

Exploiting inherent symmetries in data and models is crucial for accurate renewable energy forecasting. To address limited accuracy improvements under complex temporal dependencies, this study proposes a hybrid Bi-xLSTM-Informer model that incorporates temporal symmetry via bidirectional processing of time-flipped sequences. First, key features are screened using the Boruta algorithm, followed by PCA dimensionality reduction to construct an optimal feature subset with orthogonal transformation properties. Second, a Bi-xLSTM-Informer hybrid forecasting model is constructed. In the xLSTM model, the mLSTM is modified into a bidirectional network structure to capture short-term fluctuation patterns via forward and time-reversed propagation; Informer then analyzes global dependencies via ProbSparse attention. Validated on data from the photovoltaic (PV) Power Plant AI Competition, the experimental results demonstrate that the Bi-xLSTM-Informer model achieves the best prediction performance and the lowest error among all compared models, with an R² of 98.76% and an RMSE of 0.3776. This work proves that explicitly modeling temporal symmetry and feature orthogonality significantly enhances PV forecasting, providing an effective solution for renewable energy utilization.