Fusion of Model-free Reinforcement Learning with Microgrid Control: Review and Vision
arXiv:2206.11398 · doi:10.1109/TSG.2022.3222323
Abstract
Challenges and opportunities coexist in microgrids as a result of emerging large-scale distributed energy resources (DERs) and advanced control techniques. In this paper, a comprehensive review of microgrid control is presented with its fusion of model-free reinforcement learning (MFRL). A high-level research map of microgrid control is developed from six distinct perspectives, followed by bottom-level modularized control blocks illustrating the configurations of grid-following (GFL) and grid-forming (GFM) inverters. Then, mainstream MFRL algorithms are introduced with an explanation of how MFRL can be integrated into the existing control framework. Next, the application guideline of MFRL is summarized with a discussion of three fusing approaches, i.e., model identification and parameter tuning, supplementary signal generation, and controller substitution, with the existing control framework. Finally, the fundamental challenges associated with adopting MFRL in microgrid control and corresponding insights for addressing these concerns are fully discussed.
14 pages, 4 figures, published on IEEE Transaction on Smart Grid 2022 Nov 15. See: https://ieeexplore-ieee-org.utk.idm.oclc.org/stamp/stamp.jsp?arnumber=9951405
References in corpus (7)
- Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
- Robust Adversarial Reinforcement Learning
- Online Scheduling of a Residential Microgrid via Monte-Carlo Tree Search and a Learned Model
- Phasic Policy Gradient
- Decentralized and Coordinated Vf Control for Islanded Microgrids Considering DER Inadequacy and Demand Control
- Ensuring Transient Stability with Guaranteed Region of Attraction in DC Microgrids
- Virtual Inertia Scheduling for Power Systems with High Penetration of Inverter-based Resources
Cited by in corpus (3)
- Decentralized and Coordinated Vf Control for Islanded Microgrids Considering DER Inadequacy and Demand Control
- A Heterogeneous Multiscale Method for Efficient Simulation of Power Systems with Inverter-Based Resources
- A Data-Driven Method for Microgrid System Identification: Physically Consistent Sparse Identification of Nonlinear Dynamics