PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 1, 2026International Journal of Electrical Power & Energy Systems0 citationsOpen Access

Transient voltage stability emergency control of power systems based on an integrated SAC-GAIL framework

View Full Paper
BQBoyu QinXi'an Jiaotong UniversityYWYue WangUniversity of StuttgartBYBaiqing YinInner Mongolia Electric Power (China)

Key Points

  • This research aims to improve voltage stability control in power systems using a novel SAC-GAIL framework.
  • Proposes an integrated SAC-GAIL framework for voltage stability control.
  • Develops an interactive training platform that links Deep Reinforcement Learning (DRL) with PSD-BPA simulator.
  • Evaluates performance and convergence speed against baseline methods.
  • Achieves 47% faster convergence compared to baseline methods.
  • Reaches 96.4% performance of conventional strategies with millisecond-level online decisions.
  • Demonstrates improved efficacy and stability in learning for voltage emergency control.

Abstract

• Proposes a SAC-GAIL framework for voltage stability control with 47% faster convergence and more stable learning than baselines. • Achieves 96.4% performance of pre-planned strategies with millisecond-level online decisions, balancing efficacy and speed. • Develops an interactive training platform bridging DRL with PSD-BPA simulator for voltage emergency control decision-making.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Qin et al. (2026) studied this question.

synapsesocial.com/papers/6a1d230d02fbce9130638c61https://doi.org/10.1016/j.ijepes.2026.111975
Ask AI
Helpful
Bookmark
Share
View Full Paper