Power Theft Detection in Smart Grids Using Quantum Machine Learning

Konstantinos Blazakis

doi:10.1109/ACCESS.2025.3558143

Power Theft Detection in Smart Grids Using Quantum Machine Learning

2025-01-01

0

OA

AI

K

Konstantinos Blazakis *

Konstantinos Stavrakakis

G

G.S. Stavrakakis

DOI：10.1109/ACCESS.2025.3558143

Original

Original request for help

Save

Abstract

En 中文

Electricity theft can lead to enormous economic losses and cause operational and security problems for electricity networks and utilities. Most current research has focused on electricity theft detection in the consumption sector. However, the high penetration rate of distributed generation (DG) can lead to an increase in power theft attacks in this sector via smart meter manipulation. This study is an extension of prior works focused on electricity theft detection in the consumption and generation domains of a smart grid environment with DG. This study proposes a novel electricity theft detection framework based on quantum machine learning (QML). The elegant field of QML has been used to demonstrate that data classification becomes more efficient in higher-dimensional spaces. An extensive numerical study was conducted to determine the type of QML architecture that can perform well and efficiently in electricity theft detection cases. The technique presented here has not yet been extensively studied in the domain of energy theft detection. Extensive experiments were conducted to assess this approach, and an accuracy of 0.87 was achieved with respect to the classical consumption domain, whereas an accuracy of 0.977 was achieved with respect to the net metering domain.

Keywords:

Electricity

Smart grids

Qubit

Encoding

Noise measurement

Neural networks

Meters

Accuracy

Training

Smart meters

Distributed generation

net metering

photovoltaic (PV) electric energy

power theft detection

quantum machine learning

smart grid

Power Theft Detection in Smart Grids Using Quantum Machine Learning

Abstract

Journal

Organization