Efficient Task Offloading Processing in Edge Computing Using Grey Wolf Optimization and Graylag Goose Optimization Algorithms

Edge Computing (EC) has emerged as a pivotal paradigm, offering solutions to address challenges posed by latency-sensitive applications and to enhance overall network performance.However, existing optimization algorithms utilized for task offloading face challenges in adapting to dynamic workloads and the dynamic nature of edge networks.These challenges result in suboptimal resource allocation, leading to overloading of edge devices, increased latency and higher energy consumption.To overcome these limitations, a hybrid model based on Grey Wolf Optimization and Graylag Goose Optimization (GWO-GGO) is proposed in this research for efficient task offloading.The prey searching ability of GWO enhances resource availability recognition, bringing it closer to edge devices while satisfying the requirements of reduced energy consumption and minimum latency.The flocking behavior of the proposed GGO model mitigates the resource overloading issue by identifying the neighboring available resources for offloading in dynamic workload conditions.In the problem formulation section, this research addresses the challenges of adapting to dynamic conditions in edge computing and discusses strategies to overcome constraints such as energy consumption and latency in task offloading.The experimental results of the proposed hybrid optimization in task offloading consumes lesser energy of 0.81 J and 0.50 J under two scenarios, thereby proving efficiency over the existing optimization model namely, Hybrid Task offloading approach (Hybrid TO).