AI-OPTIMIZED ENERGY-EFFICIENT RESOURCE ALLOCATION IN IOT-ENABLED WIRELESS NETWORKS

Abstract

The proliferation of IoT devices has created unprecedented demand for efficient wireless networks, requiring both high performance and low energy consumption. Traditional resource allocation methods struggle to adapt to dynamic network conditions, resulting in suboptimal energy usage and reduced qualityof-service (QoS). This paper proposes an AIoptimized framework for energy-efficient resource allocation in IoT wireless networks. Leveraging machine learning algorithms, the system dynamically allocates bandwidth and transmission power based on real-time traffic, channel conditions, and device requirements. Simulation results demonstrate significant improvements in network throughput, energy efficiency, and latency reduction compared to conventional methods. The proposed framework integrates predictive modeling and real-time feedback, providing scalable, sustainable, and QoS-aware IoT network operation. This approach supports future largescale deployments while minimizing energy consumption and operational costs.