Abstract-Quantum communication networks are a revolutionary approach to secure data transmission using quantum mechanics like entanglement and quantum key distribution. Nonetheless, the evolution of the quantum network infrastructure creates substantial problems related to secure data transmission, energy reduction, and efficient management of scarce quantum resources. The inefficiency of traditional approaches that show little flexibility regarding quantum channel dynamics and different traffic patterns leads to low communication efficiency and high operational cost. In order to tackle these issues, this paper presents Quantum-Inspired Energy-Aware Secure Deep Reinforcement Optimization (QESDRO). QESDRO is a novel approach combining quantum-inspired evolutionary optimization and Deep Reinforcement Learning (DRL) for intelligent routing, resource allocation, and energy-aware secure communication. The use of quantum-inspired operators improves global exploration abilities, while the DRL agent develops routing and scheduling strategies using the information about channel fidelity, available energy, congestion, and potential attacks. Multi-objective reward function maximizes quantum transmission fidelity and decreases latency and energy usage while making quantum communication resistant to malicious activities. The experimental analysis clearly shows that the QESDRO framework is capable of offering 98.9% reliability of communication, 97.5% secure routing correctness, and 96.6% resource utilization efficiency, as well as reducing the energy consumption to 52J and the transmission time to 18 ms when compared to the current optimization frameworks. The obtained outcomes indicate the feasibility of the presented framework for improving communication security and efficiency of resource management.

Quantum Communication Networks, Deep Reinforcement Learning, Quantum-Inspired Optimization, Energy Efficiency, Secure Resource Allocation