To address the challenges of strong volatility, pronounced non-stationarity, and the inability of single models to simultaneously capture local dynamics and global dependencies in photovoltaic (PV) power series under complex weather conditions, this study proposes a short-term PV power forecasting framework that integrates weather-based clustering, signal decomposition, parameter optimization, and hybrid neural networks. First, a density-based clustering algorithm, namely Density-Based Spatial Clustering of Applications with Noise (DBSCAN), is employed to partition historical samples into distinct weather regimes, thereby mitigating the impact of heterogeneous meteorological conditions on model stability. Second, to handle the strong non-stationarity of PV power series, Variational Mode Decomposition (VMD) is introduced to decompose the original signal into multiple intrinsic components. The Crested Porcupine Optimizer (CPO) is further utilized to adaptively optimize key VMD parameters, including the number of modes and the penalty factor, thereby improving decomposition quality. Finally, a hybrid LSTM–Transformer forecasting model is constructed to jointly capture local temporal dynamics and long-range dependencies. The Newton–Raphson-Based Optimizer (NRBO) is employed to optimize critical hyperparameters, including the learning rate, regularization coefficient, and the number of hidden units, thereby enhancing model performance. The proposed method is validated using real-world data from a PV power station in Alice Springs, Australia. Experimental results demonstrate that, compared with the LSTM–Transformer baseline, the proposed model achieves reductions in RMSE of 0.086, 0.082, and 0.097 kW, and reductions in MAE of 0.062, 0.082, and 0.081 kW under clear-sky, cloudy, and rainy/snowy conditions, respectively. The corresponding R2 values reach 0.993, 0.968, and 0.958. These results indicate that the proposed framework exhibits strong predictive performance across different weather scenarios and provides a reliable reference for short-term PV power forecasting and grid dispatching decisions.
Fan et al. (Thu,) studied this question.