TY - GEN
T1 - Distribution Network Reconfiguration Using Deep Reinforcement Learning
AU - Gautam, Mukesh
AU - Benidris, Mohammed
N1 - Funding Information:
This work was supported by the U.S. National Science Foundation (NSF) under Grant NSF 1847578.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper proposes a deep reinforcement learning (DRL)-based framework for distribution network reconfiguration (DNR). The objective of the proposed framework is to minimize power losses in the network and various reliability indices including System Average Interruption Frequency Index (SAIFI), System Average Interruption Duration Index (SAIDI), and Average Curtailed Power (ACP). Constraints of the optimization problem are radial topology constraint and all nodes traversing constraint. The distribution network is modeled as a graph and the optimal network configuration is determined by searching for an optimal spanning tree. Contrary to existing analytical and population-based approaches, where the entire analysis and computation is to be repeated to find the optimal network configuration for each system operating state, DRL-based DNR, if properly trained, can determine optimal or near-optimal configuration quickly even with changes in system states. The Q-learning, a model-free reinforcement learning algorithm, is used by the proposed DRL-based framework to learn the action-value function. The effectiveness and efficacy of the proposed framework for DNR is demonstrated through a case study performed on 33-node distribution test system.
AB - This paper proposes a deep reinforcement learning (DRL)-based framework for distribution network reconfiguration (DNR). The objective of the proposed framework is to minimize power losses in the network and various reliability indices including System Average Interruption Frequency Index (SAIFI), System Average Interruption Duration Index (SAIDI), and Average Curtailed Power (ACP). Constraints of the optimization problem are radial topology constraint and all nodes traversing constraint. The distribution network is modeled as a graph and the optimal network configuration is determined by searching for an optimal spanning tree. Contrary to existing analytical and population-based approaches, where the entire analysis and computation is to be repeated to find the optimal network configuration for each system operating state, DRL-based DNR, if properly trained, can determine optimal or near-optimal configuration quickly even with changes in system states. The Q-learning, a model-free reinforcement learning algorithm, is used by the proposed DRL-based framework to learn the action-value function. The effectiveness and efficacy of the proposed framework for DNR is demonstrated through a case study performed on 33-node distribution test system.
KW - and spanning trees
KW - Deep Q Network
KW - distribution system reliability
KW - network reconfiguration
KW - reinforcement learning
UR - https://www.scopus.com/pages/publications/85135098436
UR - https://www.mendeley.com/catalogue/bbe8e4a4-4282-3121-bcd3-7fcfb338805b/
U2 - 10.1109/PMAPS53380.2022.9810652
DO - 10.1109/PMAPS53380.2022.9810652
M3 - Conference contribution
AN - SCOPUS:85135098436
T3 - 2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
BT - 2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
Y2 - 12 June 2022 through 15 June 2022
ER -