Noise-Resilient Quantum Machine Learning for Stability Assessment of Power Systems

Transient stability assessment (TSA) is a cornerstone for resilient operations of today’s interconnected power grids. This paper confluence quantum computing, data science and machine learning to potentially address the system TSA issue. We devise (QTSA) method enable efficient data-driven transient prediction bulk systems, which first attempt tackle issue with computing. Our contributions are three-fold: 1) A high expressibility, low-depth circuit (HELD) designed accurate noise-resilient TSA; 2) natural gradient descent algorithm developed HELD training 3) systematical analysis on QTSA’s performance under various factors performed. QTSA underpins foundation learning-enabled grid analytics. It renders intractable straightforward effortless in Hilbert space, therefore provides information operations. Extensive experiments simulators real computers verify accuracy, noise-resilience, scalability universality QTSA.