Wide Area Measurement System-based Low Frequency Oscillation Damping Control through Reinforcement Learning (2001.07829v1)

Abstract: Ensuring the stability of power systems is gaining more attraction today than ever before, due to the rapid growth of uncertainties in load and renewable energy penetration. Lately, wide area measurement system-based centralized controlling techniques started providing a more flexible and robust control to keep the system stable. But, such a modernization of control philosophy faces pressing challenges due to the irregularities in delays of long-distance communication channels and response of equipment to control actions. Therefore, we propose an innovative approach that can revolutionize the control strategy for damping down low frequency oscillations in transmission systems. Proposed method is enriched with a potential of overcoming the challenges of communication delays and other non-linearities in wide area damping control by leveraging the capability of the reinforcement learning technique. Such a technique has a unique characteristic to learn on diverse scenarios and operating conditions by exploring the environment and devising an optimal control action policy by implementing policy gradient method. Our detailed analysis and systematically designed numerical validation prove the feasibility, scalability and interpretability of the carefully modelled low-frequency oscillation damping controller so that stability is ensured even with the uncertainties of load and generation are on the rise.