Quantum Neural Networks for Solving Power System Transient Simulation Problem
Mohammadreza Soltaninia, Junpeng Zhan
TL;DR
The paper tackles power-system transient simulation by solving DAEs with quantum Neural Networks, introducing SFQ and PFQ architectures tailored to oscillatory and polynomial-like dynamics. Using two small test systems (SMIB and WSCC 3-machine), it demonstrates that PFQ offers superior training speed and accuracy for complex, multi-machine scenarios, while SFQ effectively captures sinusoidal behavior in simpler cases. A generalized DAE framework guides the QNN design, with a two-segment quantum-classical workflow and a BFGS optimizer guiding parameter updates. The results indicate promising potential for quantum methods to enhance robustness and efficiency in power-system simulations, paving the way for broader quantum-accelerated engineering applications.
Abstract
Quantum computing, leveraging principles of quantum mechanics, represents a transformative approach in computational methodologies, offering significant enhancements over traditional classical systems. This study tackles the complex and computationally demanding task of simulating power system transients through solving differential algebraic equations (DAEs). We introduce two novel Quantum Neural Networks (QNNs): the Sinusoidal-Friendly QNN and the Polynomial-Friendly QNN, proposing them as effective alternatives to conventional simulation techniques. Our application of these QNNs successfully simulates two small power systems, demonstrating their potential to achieve good accuracy. We further explore various configurations, including time intervals, training points, and the selection of classical optimizers, to optimize the solving of DAEs using QNNs. This research not only marks a pioneering effort in applying quantum computing to power system simulations but also expands the potential of quantum technologies in addressing intricate engineering challenges.