A Machine Learning-Based Framework for Fast Prediction of Wide-Area Remedial Control Actions in Interconnected Power Systems

Abstract

This paper presents a novel real-time machinelearning-based framework for remedial control action (RCA) prediction to prevent transient instability in interconnected power systems. Due to the fast dynamics of rotor angle oscillations and considering communication latencies, there is limited time to compute RCA, making RCA calculation impractical in events quickly evolving into transient instability. The proposed algorithm predicts RCA based on pre-fault and post-fault voltage values of generator buses. To cover credible scenarios, reduce prediction complexities, and increase accuracy, a micro model strategy is employed in which independent models are built for each transmission line of the system. The proposed framework consists of three main modules: stability prediction, coherency prediction, and RCA prediction. In the coherency prediction module, a time-varying algorithm is developed that determines the optimal number of generator groups and prevents unnecessarily overestimated RCAs. For each of the considered scenarios and obtained coherency patterns, a mixed-integer linear programming (MILP) model is utilized to extract the islanding and load shedding patterns considering transient stability constraints. The effectiveness of the proposed approach is demonstrated on the IEEE 39-bus system and the 74-bus Nordic test system, followed by a discussion of results.