Quantum-Inspired Resource Allocation in Cloud-IoT Networks Using Hybrid Classical-Quantum Algorithms

Abstract

The rapid expansion of Cloud-IoT networks has created significant challenges in resource allocation, requiring advanced optimization techniques to efficiently manage computational power, storage, and bandwidth. The increasing demand for low-latency, high-efficiency allocation mechanisms necessitates adaptive and scalable solutions. Traditional resource management techniques, including heuristic-based algorithms and machine learning approaches, often struggle to handle dynamic workloads, heterogeneous IoT devices, and unpredictable traffic fluctuations. These conventional models suffer from limited adaptability, slower convergence rates, and suboptimal resource utilization, leading to higher operational costs and resource wastage. To address these limitations, this research introduces a hybrid classical-quantum model integrating the Quantum Approximate Optimization Algorithm (QAOA) to enhance real-time resource allocation. The proposed model combines classical computing for handling routine data processing with quantum-inspired optimization to solve complex allocation problems more efficiently. This approach ensures dynamic adaptability, minimizing latency and maximizing energy efficiency. The experimental evaluation was conducted using dynamic IoT workload scenarios, where key performance metrics such as accuracy, convergence speed, adaptation latency, energy efficiency, and operational cost reduction were analyzed. The results show that QAOA achieves 97.8% accuracy, significantly outperforming WOA (87.5%), HHO (85.2%), MPA (83.1%), and AHA (82.4%). Additionally, it reduces latency from 105 ms to 85 ms, increases energy efficiency from 1.82 to 2.48, and lowers resource wastage from 6.5% to 3.8%, demonstrating superior optimization capabilities. These findings confirm that the proposed hybrid model is highly effective in addressing resource allocation complexities, significantly improving cost efficiency, scalability, and computational performance in Cloud-IoT networks.