Towards Risk-Aware Real-Time Security Constrained Economic Dispatch: A Tailored Deep Reinforcement Learning Approach

Abstract

In the presence of increasing uncertainties brought by intermittent renewable energy sources, security and risk management continue to be the most critical concern in modern power system operation. Risk-aware, real-time security constrained economic dispatch (RT-SCED) provides an efficient solution towards promptly, economically and robustly responding to the changes in the power system operating state. Despite different model-based methods have been developed to handle uncertainties, significant computation burden arise to incorporate <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$N$</tex-math></inline-formula> -1 contingency constraints with a higher temporal resolution in RT-SCED. Driven by similar computational challenges, risk evaluation is often overlooked in the current application of deep reinforcement learning (DRL) based data-driven methods in RT-SCED. This paper proposes a DRL-based risk-aware RT-SCED methodological framework by incorporating a novel data-driven risk evaluation model to foster efficient agent-environment interactions. The real-time dispatch policies are constructed with an improved twin delayed deep deterministic policy gradient method. The policy network features a residual network architecture and incorporates an active power allocation mechanism to integrate empirical dispatch knowledge, preventing early termination and fostering more efficient learning behavior. Case studies validate the superior performance of the proposed method in risk-aware RT-SCED on cost efficiency, uncertainty adaptability and computational efficiency, through benchmarking against model-based and data-driven baseline methods.