PreSAC-Net: A Hybrid Deep Reinforcement Learning Framework for Short-Term Household Load Forecasting and Energy Scheduling Optimization

In the power grid scheduling process, load forecasting serves as the foundation for ensuring stability and economic dispatch. It not only optimizes resource allocation but also strengthens the system’s productivity and stability, helps prevent potential risks, and ensures the reliability and safety of power supply. Therefore, a predictive soft actor–critic network (PreSAC-Net) algorithm is proposed, which aims to reduce grid operating costs and enhance system stability through an enhanced load forecasting model and an optimized scheduling strategy. First, the load forecasting is performed using a sequential feature fusion model with gated recurrent attention and diffusion (SeqFusion-GRAD), which integrates gated recurrent units (GRU), attention mechanisms, and generative diffusion models to strengthen time-series modeling and accurately predict household electricity loads. Second, a multidimensional data fusion technique incorporates meteorological and other relevant factors into household load data, improving the forecast accuracy and robustness. Furthermore, the scheduling optimization is conducted with the soft actor–critic (SAC) algorithm, which explores scheduling schemes to minimize cost under multiple constraints. The integrated approach not only balances the electricity supply and demand effectively but also supports the sustainable development of intelligent grids. Based on the experimental results, the proposed method significantly enhances power system operational efficiency and stability.