Multi-timescale optimization scheduling of regional integrated energy system based on source-load joint forecasting

The uncertainty of renewable energy output randomness and multiple load demand uncertainty significantly increases the complexity of optimization and scheduling in regional integrated energy systems (RIES), rendering traditional optimization methods insufficient. This paper proposes a multi-scale optimization and scheduling strategy for RIES based on source-load forecasting. Firstly, considering the coupling characteristics of sources and loads, we construct a Multi-Task Multi-Head-based Source-Load Joint Forecasting Model (MTMH-MTL), which provides effective predictive data for optimization and scheduling. Secondly, to further mitigate the impacts of source and load randomness, we develop a multi-time scale optimization model, which plans unit output in two stages, namely, day-ahead and intra-day, through a rolling mechanism. Finally, case simulations confirm that the proposed approach flexibly reduces the influence of randomness on system operations. Compared to traditional methods, our approach reduces economic indicators by 9.17%, environmental indicators by 5.66%, significantly enhances RIES energy utilization, ensures dynamic user demand fulfillment, and strengthens energy stability.