Skip to content

A Review of Safe Reinforcement Learning Methods for Modern Power Systems

License

Notifications You must be signed in to change notification settings

eetongsu/SafeRL-Power-System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

65 Commits
 
 
 
 

Repository files navigation

SafeRL-Power-System

The repository is for Safe Reinforcement Learning (RL) in power system applications, based on the paper A Review of Safe Reinforcement Learning Methods for Modern Power Systems, where we explore various safe RL baselines, benchmarks, applications, and real-world deployments.

If any papers are missing from this list, or if any authors prefer not to have their work included here, please feel free to contact tong.su.th@dartmouth.edu. (This repository is under active development. We welcome and appreciate any constructive comments and suggestions.)


The README is organized as follows:


1. RL/DRL/Safe RL Base

1.1 General Safe RL Repositories

1.2 General RL/DRL Review

1.3 RL Review for Power System

1.4 General Safe RL Review

2. Benchmark Environments, Algorithms, and Software

2.1. General Benchmark Environments and Algorithms

2.2 Power System Benchmark Software

2.2.1 Commercial Software
2.2.2 Open-Source and Free Software

2.3 Tailored Benchmarks for Power System

3 Power System Applications of Safe RL

3.1 Security Control

3.1.1 Voltage Control
3.1.2 Stability Control

3.2 Real-Time Operation

3.2.1 Economic Dispatch
3.2.2 System Restoration

3.3 Operational Planning

3.3.1 Unit Commitment
3.3.2 Electricity Market

3.4 Emerging Areas

3.4.1 EV Charging
3.4.2 Building Energy Management

4 Real-World Deployment Cases

Publication

If you find the repository useful, please cite the paper:

Proceedings of the IEEE:

@article{su2025review,
  title={A review of safe reinforcement learning methods for modern power systems},
  author={Su, Tong and Wu, Tong and Zhao, Junbo and Scaglione, Anna and Xie, Le},
  journal={Proceedings of the IEEE},
  year={2025},
  volume={113},
  number={3},
  pages={213-255},
  doi={10.1109/JPROC.2025.3584656}
}

Arxiv:

@article{su2024review,
  title={A review of safe reinforcement learning methods for modern power systems},
  author={Su, Tong and Wu, Tong and Zhao, Junbo and Scaglione, Anna and Xie, Le},
  journal={arXiv preprint arXiv:2407.00304},
  year={2024}
}

About

A Review of Safe Reinforcement Learning Methods for Modern Power Systems

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published