A Hybrid Quantum-Driven Optimization Model for Congestion-Aware and Energy-Efficient Resource Allocation in IoT Networks

Introduction: The increasing expansions of IoT networks enforce the adoption of efficient resource allocation, energy management, and network congestion control. Method: In this regard, this paper proposes a brand-new hybrid quantum-driven optimization model integrating Pyramid Quantum Neural Network (Py-QNN), Deep Long Short-Term Memory (DLSTM), and Multi-fragmented Jaya Puzzle Optimization (FJPO). This optimizes energy consumption to the minimum, latency to the minimum, throughput to the maximum, and network lifetime by increasing the multi-layer architecture of cluster-based communication. A comparative study with models like LEACH, PEGASIS, and Direct Transmission shows better performance. Results: Simulation results show a reduction in energy consumption by up to 60%, 30-50% lower communication delay, and a throughput increase of 25%. Conclusion: The proposed model is scalable and adaptable in real-time. Hence, it is suitable for large-scale dynamic IoT environments.