Quantum Machine Learning DDPG for Digital Twin Semantic Vehicular Networks

The increasing complexity of Internet-of-Vehicles (IoV) networks, driven by the need for real-time decision-making and resource management, presents significant challenges, particularly in dynamic, time-varying environments. To address these limitations, we propose a novel framework that integrates the quantum-based deep deterministic policy gradient (Q-DDPG) with digital twin networks (DTN) for distributed semantic optimization in dynamic IoV environments. The framework leverages quantum computing, such as superposition and annealing, to enhance distributed semantic decisions. DTNs provide real-time modeling for efficient task offloading and adaptive resource allocation in decentralized IoV environments under varying conditions and uncertainties. The numerical results validate the robustness of the proposed approach, significantly reduce latency, and improve energy efficiency.