Skip to content
Conference

Adaptive Hybrid AI-Based Resource Management for Energy-Aware and Delay-Sensitive IoT Edge Computing Environments

Oct 2026 · 2026 6th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS) · pp. 1070-1076 · 0 citations · 15 references

Abstract

The high-paced development of the Internet of Things (IoT) currently in smart infrastructure, industry, healthcare, and smart transportation systems has even forced the need to demand lowlatency and low-energy computation. A new trend, edge computing has become a viable solution to the delay-sensitive processing needs by bringing the processing closer to the data source. Nevertheless, the heterogeneous nature of workload and dynamic state of the network, coupled with the scarcity of the edge resources, are major challenges to effective resource management. The traditional static or heuristicbased allocation algorithms usually cannot be used to optimize and achieve latency and energy use at varying rates of traffic. This paper will offer a proposal of Adaptive Hybrid AI-Based Resource Management (AH-AIRM) to solve these challenges in the energyaware and delay-sensitive IoT edge computing environments. The suggested model combines a monitored workload forecast and a reinforcement-based learning-based dynamic task assignment in order to succeed in the intelligent, context-sensitive optimization of edge layers and cloud levels. The formulation of the reward is energyconscious which guarantees trade-offs between the minimization of latency and power efficiency. Experimental analysis reveals significant reduction in response time, throughput, resource usage and energy used in comparison to traditional methods. The suggested AH-AIRM framework is based on a scalable, adaptive, and sustainability-focused solution to the next generation of IoT edge computing systems.

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.