Feedback Control Approaches for Restoration of Power Grids from Blackouts

Joseph Miller, Hugo Villegas Pico, Ian Dobson, Andrey Bernstein, Bai Cui

Research output: Contribution to journalArticlepeer-review

3 Scopus Citations


The automated restoration of power systems with variable energy resources is a timely problem to tackle. Automated restoration advice can support operators in deciding on strategic actions to restore power grids from a blackout with a mix of conventional and renewable generation resources. To this end, this paper frames the restoration process of power grids with solar resources as a nonlinear dynamic model with algebraic constraints in discrete time which is steered by feedback control loops. We discuss two feedback-control strategies based on greedy and reinforcement learning algorithms, and contrast their performance with restoration plans generated by a mixed-integer linear program. We found that the reinforcement learning algorithm infers restoration actions faster than the greedy one. However, the tuning process of the reinforcement learning parameters is slower than for the greedy one.

Original languageAmerican English
Article number108414
Number of pages9
JournalElectric Power Systems Research
StatePublished - 2022

Bibliographical note

Publisher Copyright:
© 2022 Elsevier B.V.

NREL Publication Number

  • NREL/JA-5D00-84159


  • Machine learning
  • Optimization
  • Restoration


Dive into the research topics of 'Feedback Control Approaches for Restoration of Power Grids from Blackouts'. Together they form a unique fingerprint.

Cite this