• Home
  • Search
  • On the Feasibility Guarantees of Deep Reinforcement Learning Solutions for Distribution System Operation
  • Cite Icon22
  • https://doi.org/10.1109/tsg.2022.3233709Copy DOI Icon

On the Feasibility Guarantees of Deep Reinforcement Learning Solutions for Distribution System Operation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep reinforcement learning (DRL) has scored unprecedented success in finding near-optimal solutions in high-dimensional stochastic problems, leading to its extensive use in operational research, including the operation of power systems. However, in practice, it has been adopted with extreme caution because the standard DRL does not guarantee the satisfaction of operational constraints. In this paper, the feasibility of solutions given by a DRL agent trained to operate a distribution system is guaranteed by modifying the exploration process and optimality criterion of standard DRL. To that end, first, a convex feasibility set in the form of a multi-dimensional polyhedron, called feasibility diamond, is formed inside the region defined by the power flow constraints, using which the feasibility of solutions given by DRL is checked in real-time. Solutions outside the feasibility diamond are projected on the diamond’s surface, and the new modified action is used for DRL training. Further, the distance of infeasible solutions to their feasible projection is penalized in the DRL reward function. The impact of the proposed method on the feasibility and optimality of DRL solutions are tested on three test distribution systems, indicating that modifying the exploration process and a soft penalization of infeasibilities works best in achieving near-optimal and reliable DRL-trained operators.

Similar Papers
  • PDF
  • Research Article
  • Citations5

Deep imitation reinforcement learning with expert demonstration data

  • Oct 31, 2018
  • The Journal of Engineering
  • Menglong Yi +3
  • Research Article
  • Citations16

Real-Time Control of A2O Process in Wastewater Treatment Through Fast Deep Reinforcement Learning Based on Data-Driven Simulation Model

  • Dec 22, 2024
  • Water
  • Fukang Hu +3
  • Research Article
  • Citations2

Deep reinforcement learning for autonomous SideLink radio resource management in platoon-based C-V2X networks: An overview

  • Nov 12, 2024
  • Computer Networks
  • Nessrine Trabelsi +2
  • Research Article
  • Citations26

Surrogate model-based deep reinforcement learning for experimental study of active flow control of circular cylinder

  • Oct 01, 2023
  • Physics of Fluids
  • Xinhui Dong +4
  • Research Article
  • Citations19

Intelligent active flow control of long-span bridge deck using deep reinforcement learning integrated transfer learning

  • Dec 21, 2023
  • Journal of Wind Engineering and Industrial Aerodynamics
  • Xiaolong Deng +2
  • Research Article
  • Citations112

Distributed and Collective Deep Reinforcement Learning for Computation Offloading: A Practical Perspective

  • May 01, 2021
  • IEEE Transactions on Parallel and Distributed Systems
  • Xiaoyu Qiu +3
  • Conference Article
  • Citations1

Path following and obstacle avoidance of tracked vehicle via deep reinforcement learning with model predictive control as reference

  • Aug 09, 2023
  • Ting-Chien Chen +4
  • Research Article
  • Citations5

OmniDRL: An Energy-Efficient Deep Reinforcement Learning Processor With Dual-Mode Weight Compression and Sparse Weight Transposer

  • Apr 01, 2022
  • IEEE Journal of Solid-State Circuits
  • Juhyoung Lee +6
  • Conference Article
  • Citations4

Energy-Efficient Deep Reinforcement Learning Accelerator Designs for Mobile Autonomous Systems

  • Jun 06, 2021
  • Juhyoung Lee +5
  • Research Article
  • Citations8

RCM: A Neural Policy Model With Reconstruction Mechanism to Construct a Solution for the Agile Satellite Scheduling Problem.

  • Apr 01, 2025
  • IEEE transactions on cybernetics
  • Ming Chen +5
  • Research Article
  • Citations1

Online transfer learning (OTL) for accelerating deep reinforcement learning (DRL) for building energy management

  • Jun 03, 2025
  • Journal of Building Performance Simulation
  • Tran Van Quang +1
  • Conference Article

Safe Deep Reinforcement Learning Based on Sample Value Evaluation

  • Dec 02, 2022
  • Rongjun Ye +2
  • Research Article
  • Citations8

Blockchain-based crowdsourced deep reinforcement learning as a service

  • Jun 28, 2024
  • Information Sciences
  • Ahmed Alagha +4
  • Conference Article
  • Citations2

Robot Control in Human Environment using Deep Reinforcement Learning and Convolutional Neural Network

  • Dec 01, 2019
  • Chen Chen +5
  • Conference Article
  • Citations13

Augmenting Human Cognition with an AI-Mediated Intelligent Visual Feedback

  • Apr 19, 2023
  • Songlin Xu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.