Two-Stage Volt/Var Control in Active Distribution Networks With Multi-Agent Deep Reinforcement Learning Method.
Xianzhuo SunJing QiuPublished in: IEEE Trans. Smart Grid (2021)
Keyphrases
- reinforcement learning
- multi agent
- dynamic programming
- experimental evaluation
- significant improvement
- high accuracy
- segmentation method
- preprocessing
- high precision
- synthetic data
- detection method
- support vector machine
- data sets
- cost function
- control policy
- model free
- computational cost
- convergence rate
- pairwise
- image segmentation