Research Area:  Machine Learning
Multi-agent reinforcement learning (MARL) with “centralized training & decentralized execution” framework has been widely investigated to implement decentralized voltage control for distribution networks (DNs). However, a centralized training solution encounters privacy and scalability issues for large-scale DNs with multiple virtual power plants. In this letter, a decomposition & coordination reinforcement learning algorithm is proposed based on a federated framework. This decentralized training algorithm not only enhances scalability and privacy but also has a similar learning convergence with centralized ones.
Keywords:  
Voltage control
Training
Reinforcement learning
Distribution networks
Optimization
Privacy
Entropy
Author(s) Name:  Haotian Liu; Wenchuan Wu
Journal name:   IEEE Transactions on Smart Grid
Conferrence name:  
Publisher name:  IEEE
DOI:  10.1109/TSG.2022.3169361
Volume Information:  Volume: 13
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9761229