Primal-Dual Differentiable Programming for Distribution System Critical Load Restoration: Preprint

Xiangyu Zhang, Bernard Knueven, Ahmed Zamzam, Matthew Reynolds, Wesley Jones

Research output: Contribution to conferencePaper


Swift and reliable critical load restoration (CLR) can help make a distribution system resilient towards extreme events. To optimally achieve that, alongside practical concerns such as limiting online computational burden, some studies leverage model-free reinforcement learning (RL) to train control policies. Despite the advantages provided by RL algorithms, these approaches suffer from two issues: 1) the lack of a proper mechanism for constraint enforcement, and 2) poor sample efficiency. Therefore, in this paper, a primal-dual differentiable programming (PDDP) method is developed for guiding the training leading to a constraint-satisfying policy. Additionally, the model-based nature of the proposed method aims at improving sample efficiency. The experiment on a CLR problem demonstrates that PDDP can effectively train a control policy that both achieves desirable performance and satisfies required constraints.
Original languageAmerican English
Number of pages8
StatePublished - 2023
Event2023 IEEE Power & Energy Society General Meeting - Orlando, Florida
Duration: 16 Jul 202320 Jul 2023


Conference2023 IEEE Power & Energy Society General Meeting
CityOrlando, Florida

NREL Publication Number

  • NREL/CP-2C00-84635


  • differentiable programming
  • grid resilience
  • load restoration
  • primal-dual method
  • reinforcement learning


Dive into the research topics of 'Primal-Dual Differentiable Programming for Distribution System Critical Load Restoration: Preprint'. Together they form a unique fingerprint.

Cite this