A data-based day-ahead scheduling optimization approach for regional integrated energy systems with varying operating conditions

Two of the most critical issues encountered in the day-ahead scheduling of regional integrated energy systems are the uncertainty of renewable energy resources and complexity of load demand. Furthermore, varying operating conditions also pose challenges for economical day-ahead scheduling. This paper proposes a scenario-based day-ahead scheduling approach for regional integrated energy systems to minimize operating costs by mining historical data. A hybrid dynamic energy hub model with variable efficiency that integrates an extreme gradient boosting (XGBoost) algorithm and analytical formulation is proposed. We developed a scenario-based scheduling optimization model in which climate data and load data are predicted using XGBoost and the probability distributions of their predicted errors are estimated using a Gaussian mixture model. Monte Carlo simulation and K-means clustering were used to generate and reduce scenarios and a success-history-based adaptive differential evolution algorithm was adopted to search for optimal solutions for day-ahead scheduling. Furthermore, a weighted average electricity purchasing strategy was adopted to address uncertainty and further improve operating economy by adjusting the output of gas turbines and electricity purchasing for actual scheduling. Case studies were conducted to verify that the proposed approach can reduce daily operating costs and enhance the operating economy of regional integrated energy systems.