Quantum neural networks for power flow analysis

This paper explores the potential application of quantum and hybrid quantum–classical neural networks in power flow analysis. Experiments are conducted using two datasets based on 4-bus and 33-bus test systems. A systematic performance comparison is also conducted among quantum, hybrid quantum–class...

Full description

Saved in:
Bibliographic Details
Published inElectric power systems research Vol. 235; p. 110677
Main Authors Kaseb, Zeynab, Möller, Matthias, Balducci, Giorgio Tosti, Palensky, Peter, Vergara, Pedro P.
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.10.2024
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:This paper explores the potential application of quantum and hybrid quantum–classical neural networks in power flow analysis. Experiments are conducted using two datasets based on 4-bus and 33-bus test systems. A systematic performance comparison is also conducted among quantum, hybrid quantum–classical, and classical neural networks. The comparison is based on (i) generalization ability, (ii) robustness, (iii) training dataset size needed, (iv) training error, and (v) training process stability. The results show that the developed hybrid quantum–classical neural network outperforms both quantum and classical neural networks, and hence can improve deep learning-based power flow analysis in the noisy-intermediate-scale quantum (NISQ) and fault-tolerant quantum (FTQ) era. •Quantum neural networks are used for deep learning-based power flow analysis.•The performance of quantum neural networks is systematically assessed.•The use of quantum neural networks can significantly improve generalization ability.•The experiments are performed using small-scale distribution networks.•Hybrid quantum–classical neural networks are recommended as models of choice.
ISSN:0378-7796
1873-2046
DOI:10.1016/j.epsr.2024.110677