fig1

Figure 1. The framework includes four components: (1) a PCA-enhanced K-means clustering model for identifying load patterns; (2) a DTW-DBSCAN method for extracting representative renewable generation days; (3) a DDPG algorithm for optimizing dispatch strategies; and (4) HESS integration for long-duration energy balancing. PCA: Principal Component Analysis; DTW: Dynamic Time Warping; DBSCAN: Density-Based Spatial Clustering of Applications with Noise; DDPG: Deep Deterministic Policy Gradient; HESS: hydrogen energy storage system.