Saved in:
Bibliographic Details
Main Authors: Chen, Zhengrong, Cai, Siyao, Meliopoulos, A. P. Sakis
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.18937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913521299619840
author Chen, Zhengrong
Cai, Siyao
Meliopoulos, A. P. Sakis
author_facet Chen, Zhengrong
Cai, Siyao
Meliopoulos, A. P. Sakis
contents The deep reinforcement learning (DRL) based Volt-VAR optimization (VVO) methods have been widely studied for active distribution networks (ADNs). However, most of them lack safety guarantees in terms of power injection uncertainties due to the increase in distributed energy resources (DERs) and load demand, such as electric vehicles. This article proposes a robust deep reinforcement learning (RDRL) framework for VVO via a robust deep deterministic policy gradient (DDPG) algorithm. This algorithm can effectively manage hybrid action spaces, considering control devices like capacitors, voltage regulators, and smart inverters. Additionally, it is designed to handle uncertainties by quantifying uncertainty sets with conformal prediction and modeling uncertainties as adversarial attacks to guarantee safe exploration across action spaces. Numerical results on three IEEE test cases demonstrate the sample efficiency and safety of the proposed robust DDPG against uncertainties compared to the benchmark algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18937
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty
Chen, Zhengrong
Cai, Siyao
Meliopoulos, A. P. Sakis
Systems and Control
The deep reinforcement learning (DRL) based Volt-VAR optimization (VVO) methods have been widely studied for active distribution networks (ADNs). However, most of them lack safety guarantees in terms of power injection uncertainties due to the increase in distributed energy resources (DERs) and load demand, such as electric vehicles. This article proposes a robust deep reinforcement learning (RDRL) framework for VVO via a robust deep deterministic policy gradient (DDPG) algorithm. This algorithm can effectively manage hybrid action spaces, considering control devices like capacitors, voltage regulators, and smart inverters. Additionally, it is designed to handle uncertainties by quantifying uncertainty sets with conformal prediction and modeling uncertainties as adversarial attacks to guarantee safe exploration across action spaces. Numerical results on three IEEE test cases demonstrate the sample efficiency and safety of the proposed robust DDPG against uncertainties compared to the benchmark algorithms.
title Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty
topic Systems and Control
url https://arxiv.org/abs/2409.18937