An Overview of Quantum Machine Learning and its Applications in Power Systems
Taha Hammadia, Ahmad Mohammad Saber, Marthe Kassouf +1 more
Machine Learning (ML) is a promising avenue for developing data-driven tools to plan, analyze, operate, and control power system infrastructure. Recently, the field of Quantum Machine Learning (QML), which combines quantum information principles, such as quantum superposition and entanglement, with ML principles, has emerged as a novel direction for learning-based solutions. This paper overviews QML, including various QML architectures and their applications in power systems. It introduces quantum information and quantum computing, giving necessary background and intuition. The QML framework is then introduced, along with common QML models, which are compared and contrasted to identify suitable QML architectures for different power system problems. Afterwards, previous works that studied the application of QML to power systems are presented and analyzed. Lastly, challenges, limitations, and open questions concerning the use of QML for power systems are discussed.
IEEE/IAS Industrial and Commercial Power Systems Technical Conference•May 1, 2026•0 citations