Exploring quantum learning in the smart grid through the evolution of noisy finite fourier series

Frontiers in Energy Research

Energy Research

Marc-André Dubois¹  Deepa Kundur²  Andrew Nader² 

[1] Hydro-Québec Research Institute (IREQ) Hydro-Québec, Varennes, QC, Canada;The Edward S. Rogers Sr. Department of Electrical and Computer Engineering University of Toronto, Toronto, ON, Canada;

关键词: smart grids;    cyber-physical systems;    cybersecurity;    anomaly detection;    machine learning;    quantum machine learning;    quantum computing;   

DOI  :  10.3389/fenrg.2023.1061602

 received in 2022-10-04, accepted in 2023-09-20,  发布年份 2023

来源: Frontiers

【 摘 要 】

The decentralization and softwarization of modern industrial control systems such as the electric grid has resulted in greater efficiency, stability and reliability but these advantages come at a price of higher likelihood of cyberattacks due to the resulting increase in cyberattack surface. Traditional cyberattack detection techniques such as rule-based anomaly detection have an important role to play in first response. However, given the data-rich environment of the modern electric grid, current research thrusts are focused on integrating data-driven machine learning techniques that automatically learn to detect anomalous modes of operation and predict the presence of new attacks. Quantum machine learning (QML) is a subset of machine learning that aims to leverage quantum computers to obtain a learning advantage by means of a training speed-up, data-efficiency, or other form of performance benefit. Questions remain regarding the practical advantages of QML, with the vast majority of existing literature pointing to its greater utility when applied to quantum data rather than classical data, which within a smart grid environment include TCP/IP packets or telemetry measurements. In this paper, we explore a scenario where quantum data may arise in the smart grid, and exploit a quantum algorithmic primitive previously proposed in the literature to demonstrate that in the best-case, QML can provide accuracy advantages of >25 percentage points when predicting anomalies.

【 授权许可】

Unknown   
Copyright © 2023 Nader, Dubois and Kundur.