Short-Term Photovoltaic Power Forecasting Based on Power Fluctuation Characteristics and Joint Optimization of SSA-GRU
The stochastic fluctuation of photovoltaic (PV) power output is a primary cause of low forecasting accuracy. This paper proposes a short-term PV power forecasting method that integrates PV power fluctuation characteristics with a jointly optimized singular spectrum analysis (SSA) and gated recurrent unit (GRU) model. First, four fluctuation feature models—number of power fluctuations (NPF), comprehensive fluctuation amplitude (AFA), mean, and standard deviation—are established, and a fuzzy C-means (FCM) clustering algorithm is employed to partition historical PV power data into sub-datasets with similar fluctuation patterns. Second, an SSA-GRU forecasting model is constructed, and an improved coati optimization algorithm (ICOA) is developed to jointly optimize the SSA decomposition parameters and GRU network hyperparameters. The proposed method, termed PFF-FCM-ICOA-(SSA-GRU), is validated using data from an actual PV plant in Ningxia. Comparative experiments against eight benchmark models (M1–M8) demonstrate that the proposed method achieves superior forecasting accuracy across all fluctuation patterns. The ICOA-based joint optimization yields faster convergence and lower loss than separate optimization or other metaheuristic algorithms. By clustering input data according to power fluctuation characteristics, the method effectively avoids the adverse effects of meteorological factors and enables the selection of appropriate forecasting models based on weather pattern types. The results confirm that the proposed approach significantly improves short-term PV power forecasting precision and robustness.