Abstract
Power system corrective control is a great important strategy to ensure the safety of a grid; however, with the high penetration of distributed energy resources such as solar, wind, hydro, etc., the difficulty of control with active correction of power system dramatically increases. In the mean times, model-free methods such as Deep Reinforcement Learning (DRL) are being extensively studied by many research scholars to solve those decision and control problems with high complexity and uncertainty dimension in smart grids including corrective control area. But, hyperparameter in DRL is hard to find the optimal one. Therefore, we propose a self-evolving agent system for power system online corrective control based on the hyperparameter tuning method. In this paper, we test this algorithm on the 62-bus regional power system of a 300-bus provincial bulk power grid. Numerical simulation validates the excellent performance of this method in effectively eliminating line overload under auto Hyperparameter Optimization (HPO).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
