To address the low accuracy and poor reliability of short-term photovoltaic (PV) power forecasting under complex weather conditions, this study proposes a multi-strategy synergistic optimization framework for point-interval prediction. The methodology integrates similar day classification (SDC) via RDP-DTW-DBA-K-means, a hybrid BiTCN-MAOBiGRU-AM model with a mutation-aware mechanism, and Dream Optimization Algorithm (DOA) for global hyperparameter tuning of six key parameters. For interval prediction, an adaptive bandwidth kernel density estimation (ABKDE) dynamically adjusts bandwidth based on local error density and weather scenarios. Experiments using data from a Guangxi PV station demonstrate that the synergistic model reduces RMSE by 29.58% (cloudy) and 32.37% (overcast/rainy) versus the baseline, and cuts RMSE by 16.2–19.0% under abrupt weather events and 22.4–40.2% under non-ideal input data. At the 95% confidence level, ABKDE improves prediction interval coverage probability by 3.9–5.4 percentage points and reduces normalized average width by 20.8–23.6% compared to conventional KDE. The proposed framework significantly enhances prediction accuracy, robustness, and generalization, offering a reliable solution for PV power forecasting in highly variable meteorological scenarios.
The high penetration of renewable energy has posed significant challenges to frequency regulation, primarily due to the scarcity of traditional regulation resources in these regions. To address this, a novel secondary frequency regulation control method utilizing voltage-sensitive flexible load (VSFL) clusters is proposed. The strategy leverages the voltage-active power coupling characteristics of composite loads. By regulating the load voltage, composite loads under 110/10 kV substations are transformed into controllable loads, which are then aggregated to collaborate with Automatic Generation Control (AGC) units in SFR. To tackle the inherent uncertainty in load regulation capacity, a load control signal correction strategy based on Tube-based Model Predictive Control (T-MPC) is designed. This strategy effectively compensates for calculation errors in control objectives caused by load uncertainty, achieving optimal control with minimal cost. Simulation results demonstrate that the proposed scheme enables the large-scale mining and flexible utilization of load-side regulation resources. Furthermore, the T-MPC approach exhibits superior robustness and frequency regulation performance compared to traditional MPC methods.