Deployment Of Fog Computing Devices In Mobile Edge Computing Environnment

Résumé: Fog Computing has emerged as a favorable technology that can bring Cloud applications closer to physical IoT devices at the network edge, but there is neither common fog Computing architecture or how it supports real-time internet. Execution of the service of objects (IoT). Peripherals such as peripherals such as the switch, router, gateway, mobile phones, smart car, etc., are the Candidates for deploying fog nodes, but the deployment differs by application. In this work, we took gateways as candidates for the deployment of fog nodes. The gateway collects data from smart sensors, but it does not have any pre￾processing or decision-making capabilities. Therefore, the Gateway is made smarter with Fog capabilities and named as Fog Smart Gateway (FSG). IoT traffic processing is supported by Virtual Machines (VMs) facilitated by distributed Fog nodes. We have optimized the number of fog nodes to reduce the total latency induced by traffic aggregation and Processing. Our results show that the optimal deployment of fog IoT network nodes could result in reduced latency compared to processing IoT data in a conventional Cloud system. Moving from theory to practice in fog networks poses the question of the optimal number of fog nodes that will be upgraded from existing nodes. This paper finds the optimal number of fog nodes for a total number of ordinary nodes residing in the area of interest for different channel conditions. Determining the optimal number of fog nodes is highly beneficial, as it can strongly affect the SINR, and thus the average data rate and transmission delay. The numerical results indicate that the average data rate increases by almost an order of magnitude for an optimized number of fog nodes under shading and fading. It is further shown that the optimal number of fog nodes does not increase in direct proportion to the increase in the total number of nodes. Moreover, the optimal number of fog nodes decreases when the channels have high path loss exponents. These results suggest that fog nodes should be selected among those with the highest computational capacity for densely deployed networks and channels with high path loss exponents. Index terms Fog networking, hierarchical networks, SINR, average throughput, transmission delay. This work investigates the weighted dynamic deployment of mobile fog-Computing devices to support a mobile edge Computing environment, in which each peripheral device is associated with a weight to reflect its importance depending on the application. Since peripheral devices are mobile and can be switched off, it is difficult to dynamically optimize the deployment to adapt to the dynamic currency. This work further models the problem mathematically and solves it with a bat-inspired (BA) algorithm, which finds the optimal solutions by simulating the foraging behavior of bats via echolocation. Moreover, three local search methods designed specifically for this problem are integrated into the BA, and a dynamic local search selection mechanism is proposed to adjust the probabilities of choosing the three local search methods iteratively in the main loop of BA. The simulation results show outperformance of the proposed BA compared to the BA without local search and the previous approach.

Publié dans la revue: