Volume 18, No. 6, 2021
Optimised Delay And Basic Safety Messages In Fog Computing Using Extended Grey Wolf Optimisation (Egwo)
Savita Lohat , Rajender Kumar and Sheilza Jain
Next generation of Fog computing is regarded to be armed with Advanced Fog Node (AFN) along with powerful Artificial Intelligence (AI) and Deep Learning (DL) module. AFN are flexible and energy proficient but the performance is critically affected by inherent frequent data advertisements and overheads for tracking vehicles also termed as basic safety messages. Projected work shows a faster method to select Fog Node for maximum coverage. Grey Wolf Optimisation (GWO) is carefully investigated and particle swarm optimisation (PSO) is projected as an extension to the GWO. The extended GWO is anticipated to accommodate the merits of both the algorithms. EGWO module is capable of addressing receptive and multitude approaches. AFN is selected from the pool of FN’s geographically distributed in a given region by the projected optimiser. The problem of optimum FN selection is to maximize coverage considering stationary and random vehicles mapped as a GWO-PSO Optimization (GWO) problem. The results show that the projected fusion algorithm could indeed reduce the computational time and converge very fast by an order, during vehicle tracking.
Keywords: Fog nodes, pso, gwo, optimisation, iterations, coverage and vehicle