Data-Driven Surrogate-Assisted Acceleration Approach for Long-Term Stochastic Chronological Operation Simulation

Abstract

Stochastic chronological operation simulation (S-COS) is essential for analysing long-term supply-demand balance in power systems with high penetration of renewable energy. However, conventional methods face significant computational challenges due to inter-temporal constraints and numerous binary variables in multi-scenario annual simulations. This paper presents a novel data-driven, surrogate-assisted approach to accelerate year-round, scenario-based operation simulations. The proposed approach employs a temporal decomposition method to decouple the annual stochastic optimization problem into an inter-day scheduling model and multiple intra-day power dispatch models, which are efficiently solved using a data-driven surrogate model. Case studies on modified six-bus and IEEE 118-bus systems demonstrate the approach's adaptability to various scenarios and its scalability across different network scales. Results show that this approach improves computational efficiency by at least 100 times compared to conventional methods, with even faster performance in larger systems. It also maintains high accuracy, achieving an average annual operating cost error of only 1.35% relative to benchmarks.