An accelerated deep reinforcement learning algorithm for voltage stability control via load shedding

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Signal Processing

EESS Systems and Control

An accelerated deep reinforcement learning algorithm for voltage stability control via load shedding

Accelerated Deep Reinforcement Learning Based Load Shedding for Emergency Voltage Control

An accelerated deep reinforcement learning (drl) algorithm named pars was developed and tailored for power system voltage stability control via load shedding.

The method features high scalability and easy to tune with only five main hyperparameters.

Test results show that compared to other methods including model-predictive control (model-predictive control) and proximal policy optimization(ppo)methods, pars shows better computational efficiency (faster convergence), more robustness in learning, excellent scalability and generalization capability.

Authors

Renke Huang, Yujiao Chen, Tianzhixi Yin, Xinya Li, Ang Li, Jie Tan, Wenhao Yu, Yuan Liu, Qiuhua Huang

◐ Recommended Members

◐ Latest Activity