An Optimized Approach for Efficient-Power and Low-Latency Fog Environment Based on the PSO Algorithm

Fog Computing is an architecture that provides computing, storage, control and networking capacities for realizing Internet of Thing applications. Fog computing enhances the QoS Applications sensitive to delay, enable them to use fog computing's low latency instead of the large cloud latency. Tasks in different IoT applications should be correctly dispersed through fog nodes, improving service quality and reaction time. Many research papers have been published to investigate either latency or power consumption improvement. However, this new research area still further research. This article work seeks to examine how IoT services are placed and processing data in a Fog system with low latency and low power consumption in optimal way. The meta heuristics Particle Swarm Optimization (PSO) algorithm is suggested for the proposed approach to manage network resources (latency and power consumption). For testing purposes, the well-known “iFogSim” simulator is used to setup an experiment and to build a case study network in fog layer based on virtual reality EEG game. The simulation results for the suggested experiment show that the PSO algorithm has better performance than competitive approaches such as First Come First Serve (FCFS) and Greedy Knapsack -based Scheduling (GKS) algorithms. The simulated results that we get when applying PSO optimizer in power and latency outperforms other algorithms. The result of latency is (in FCFS =1.39ms, in GKS =1.23ms, in PSO=1.12ms) and the results of power consumption is (in FCFS =1.63mj, in GKS =1.13mj, in PSO=1.09mj).