Resource Optimization in IoT Systems : A Hybrid AI-based Approach for Enhancing Computational Efficiency and Reducing Latency
N. Savitha, M Jayaprakash, T Elavarasi, E Shivakumar., K.C. Gayathri, Moorthy Agoramoorthy · 2025
With the rapid proliferation of IoT and smart devices, optimizing resource management in edge computing environments is critical to ensuring efficient computational performance and minimal latency. This study proposes a hybrid AI-based framework that integrates reinforcement learning with heuristic optimization techniques, including genetic algorithms, to dynamically predict and allocate resources based on real-time workload characteristics. The proposed model enhances computational efficiency by optimizing resource distribution, reducing latency, and improving system scalability. Comparative experiments indicate that the AI-driven approach achieves up to a 30% improvement in computational efficiency and scalability compared to conventional resource allocation methods. This adaptive framework provides a robust and scalable solution for real-time data processing in IoT networks, significantly reducing response time and enhancing overall system performance.