Adaptive Deep Reinforcement Learning Algorithm for Distribution System Cyber Attack Defense With High Penetration of DERs

Alaa Selim, Junbo Zhao, Fei Ding, Fei Miao, Sung-Yeul Park

Research output: Contribution to journalArticlepeer-review

Abstract

With grid modernization, smart inverters are increasingly used to execute advanced controls for distribution network reliability. However, this also increases the cyber-attack space. This paper focuses on the defense approaches to restore the system to normal operation circumstances in the presence of cyber-attacks. A unique deep reinforcement learning (DRL) method is developed to minimize voltage violations and reduce power losses for impacted feeders. The defense problem is reformulated as a Markov decision-making process to dynamically control DERs while minimizing load shedding. This is achieved via an improved soft actor-critic (SAC)-based DRL algorithm, which can govern DER set points and load-shedding scenarios in discrete and continuous modes via the auto-tune entropy and Gaussian policy features. Numerical comparison results on the modified IEEE 123-node system with other control approaches, such as Volt-VAR (VV), Volt-Watt (VW), and model predictive control (MPC) show that the proposed method can eliminate voltage violations and provide feasible control actions that perform complete mitigation of cyber-threats.
Original languageAmerican English
Pages (from-to)4077-4089
Number of pages13
JournalIEEE Transactions on Smart Grid
Volume15
Issue number4
DOIs
StatePublished - 2024

NREL Publication Number

  • NREL/JA-5D00-88726

Keywords

  • active distribution systems
  • cyber attack
  • deep reinforcement learning
  • renewable generation

Fingerprint

Dive into the research topics of 'Adaptive Deep Reinforcement Learning Algorithm for Distribution System Cyber Attack Defense With High Penetration of DERs'. Together they form a unique fingerprint.

Cite this