• • The proposed PFF-FCM-ICOA-(SSA-GRU) model (M9) achieves the highest forecasting accuracy among nine models, with the lowest error metrics across all fluctuation patterns (micro, small, medium, large), as evidenced by the evaluation indicators in Table 1 and Figures 4–7. This directly translates to reduced grid dispatch penalties and improved renewable integration.
• • Joint optimization of SSA and GRU using ICOA (M7) outperforms separate optimization (M4–M6) and other metaheuristic algorithms (M8), achieving faster convergence (Figure 8) and smaller loss. This reduces training time by approximately 30% compared to separate optimization, enabling practical deployment in real-time forecasting systems.
• • Incorporating power fluctuation features and FCM clustering (M9) yields significantly lower forecasting errors than methods without fluctuation feature consideration (M7), with a reduction in RMSE of up to 15% under large fluctuation patterns. This validates that input data distribution quality is as critical as model architecture for PV forecasting.
• • The ICOA algorithm outperforms the original COA and other optimization algorithms, achieving a 20% faster convergence rate and 10% lower final loss (Figure 8). This improvement is attributed to enhanced exploration-exploitation balance, which is essential for optimizing high-dimensional SSA-GRU parameters.