Quantum Reinforcement Learning Driven Adaptive Resource Allocation for Internet of Things Devices

Abstract

The high rate of Internet of Things (IoT) networks development has posed a serious problem of effective resource allocation because devices are heterogeneous, the traffic conditions are dynamic, and the energy and latency requirements are severe. Traditional resource allocation methods and classical reinforcement learning methods are not always the best methods to perform in a highly dynamic environment because they lack the adaptability and reduce convergence. The proposed paper introduces a Quantum Reinforcement Learning (QRL)-motivated adaptive resource allocation model which uses quantum-inspired state representation, as well as quantum-classical policy optimization, to optimize resource allocation. The proposed model is a dynamic distribution of bandwidth, transmission power, and computational resources the real-time state of network. Experimental assessment shows better performance than the traditional and classical reinforcement learning techniques. The proposed QRL framework attains the average accuracy of resource allocation 97.84%, lessens the communication latency by 43%, escalates the throughput by 64%, and lessens the energy usage by 37%. The system also has better convergence and stability exception when applied to different network load. Combination of quantum feature encoding improves efficacy in decision and learning. The findings affirm that the suggested framework offers a powerful and scalable system of smart resource management in the next-generation IoT systems.