Rolling Horizon Robust Real-Time Economic Dispatch with Multi-Stage Dynamic Modeling

A multi-stage robust real-time economic dispatch model (MRRTD) for power systems is proposed in this paper. The MRRTD takes the dynamic form of optimization as framework to naturally simulate operation equipment that temporally coupled, e.g., utility-level energy storage systems. For normal systems, can work directly short time slots with a rolling horizon. large-scale expands time-slot scale and generates optimal policies. With guidance, decision be swiftly made thereafter. In addition, uncertainty set based on deep learning proposed, which dynamically refine covering ability probable occurred wind scenarios. To efficiently solve MRRTD, novel fast dual programming method employed. effectiveness solution algorithm, especially improved scalability compared several other methods, are demonstrated by simulation results from six benchmark test cases ranging modified IEEE 6-bus system 6495-bus system.