A Bayesian Deep Reinforcement Learning-based Resilient Control for Multi-Energy Micro-gird

• Published in: IEEE transactions on power systems Vol. 38; no. 6; pp. 1 - 16
• Main Authors: Zhang, Tingqi, Sun, Mingyang, Qiu, Dawei, Zhang, Xi, Strbac, Goran, Kang, Chongqing
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bayes methods; Bayesian analysis; Bayesian Deep Learn-ing; Deep learning; Distributed generation; Extreme Events; Machine learning; Optimization; Power System Resilient Control; Power systems; Real-time systems; Reinforcement learning; Renewable energy sources; Resilience; Uncertainty
• ISSN: 0885-8950; 1558-0679
• DOI: 10.1109/TPWRS.2023.3233992

Aiming at a cleaner future power system, many regimes in the world have proposed their ambitious decarboniz-ing plan, with increasing penetration of renewable energy sources (RES) playing an alternative role to conventional energy. As a re-sult, power system tends to have less backup capacity and operate near their designed limit, thus exacerbating system vulnerability against extreme events. Under this reality, resilient control for the multi-energy micro-grid is facing the following challenges, which are: 1) the effect from the stochastic uncertainties of RES; 2) the need for a model-free and fast-reacting control scheme under extreme events; and 3) efficient exploration and robust performance with limited extreme events data . To deal with the aforementioned challenges, this paper pro-poses a novel Bayesian Deep Reinforcement Learning-based resilient control approach for multi-energy micro-grid. In partic-ular, the proposed approach replaces the deterministic network in traditional Reinforcement Learning with a Bayesian probabilistic network in order to obtain an approximation of the value function distribution, which effectively solves the Q-value overestimation issue. Compared with the naive Deep Deterministic Policy Gra-dient (DDPG) method and optimization method, the effectiveness and importance of employing the Bayesian Reinforcement Learn-ing approach are investigated and illustrated across different operating scenarios. Case studies have shown that by using the Monte Carlo posterior mean of the Bayesian value function distribution instead of a deterministic estimation, the proposed Bayesian Deep Deterministic Policy Gradient (BDDPG) method achieves a near-optimum policy in a more stable process, which verifies the robustness and the practicability of the proposed approach.