Two-Stage Stochastic Optimization of the Integrated Electricity-Gas System Considering Net Load Uncertainty Based on Contextual Optimization

The Integrated Electricity-Gas System (IEGS) plays a crucial role in the energy sector, combining both traditional and emerging energy sources. However, the uncertainty of renewable energy sources and load can cause instability in the system's energy supply and create challenges for its operation and planning. Recently, the researchers proposed a two-stage model that uses contextual optimization to tackle the uncertain net loads in the IEGS. The model adopts two contextual-based optimization methods: residual-based sample average approximation method and reweighted sample average approximation method. These methods provide more accurate estimates of operating costs by invoking the conditional distribution of uncertainty parameters under current external information. We compared the new methods with traditional methods through detailed case analysis and demonstrated their effectiveness in optimizing the IEGS. The results show that the proposed model and algorithm can significantly reduce the operating cost of the system and have high practical value.