Digital Twin-Empowered Voltage Control for Power Systems

TL;DR

This paper introduces a Gumbel-Consistency Digital Twin method that significantly improves voltage control efficiency in power systems by reducing computational load and enhancing sampling accuracy through innovative strategies.

Contribution

The paper presents a novel GC-DT approach that combines Gumbel-based sampling and a consistency loss to outperform existing digital twin methods in power system voltage control.

Findings

Outperforms state-of-the-art in efficiency

Reduces reliance on Monte Carlo simulations

Improves prediction accuracy in experiments

Abstract

Emerging digital twin technology has the potential to revolutionize voltage control in power systems. However, the state-of-the-art digital twin method suffers from low computational and sampling efficiency, which hinders its applications. To address this issue, we propose a Gumbel-Consistency Digital Twin (GC-DT) method that enhances voltage control with improved computational and sampling efficiency. First, the proposed method incorporates a Gumbel-based strategy improvement that leverages the Gumbel-top trick to enhance non-repetitive sampling actions and reduce the reliance on Monte Carlo Tree Search simulations, thereby improving computational efficiency. Second, a consistency loss function aligns predicted hidden states with actual hidden states in the latent space, which increases both prediction accuracy and sampling efficiency. Experiments on IEEE 123-bus, 34-bus, and 13-bus systems demonstrate that the proposed GC-DT outperforms the state-of-the-art DT method in both computational and sampling efficiency.