Quantum-Driven Intelligent Controller Design for DC–DC Boost Converters

This paper introduces a quantum-inspired control strategy for DC–DC boost converters feeding constant power loads (CPLs) based on variational quantum circuits (VQCs) integrated into a Twin Delayed Deep Deterministic Policy Gradient (TD3) reinforcement learning framework. The proposed quantum reinforcement learning based (QRL) controller leverages compact quantum circuit architectures to reduce parameter complexity while maintaining expressive control policies, offering a scalable alternative to deep neural networks for high-frequency control loops in Wide Bandgap (WBG) power electronics, a critical application in resource-constrained embedded platforms. The controller is trained offline and deployed on a real-time dSPACE DS1202 hardware platform for experimental validation. Comparative results against two neural network–based reinforcement learning controllers demonstrate that QRL controller achieves faster convergence in training, shorter settling times, smaller voltage deviations, and smoother current dynamics, all with significantly fewer trainable parameters. These findings highlight the potential of quantum-inspired reinforcement learning as a practical and efficient control solution for power electronic systems, paving the way toward real-time quantum-enhanced controllers in future energy applications.