Research Article
Efficient Power Management in Mobile Computing with Edge Server Offloading Using Multi-Objective Optimization
@ARTICLE{10.4108/eai.8-7-2021.170288, author={P. Anusha and R.V. Siva Balan}, title={Efficient Power Management in Mobile Computing with Edge Server Offloading Using Multi-Objective Optimization}, journal={EAI Endorsed Transactions on Energy Web}, volume={9}, number={37}, publisher={EAI}, journal_a={EW}, year={2021}, month={7}, keywords={Cloud-edge computing, Cloudlets, Fog nodes, Optimization}, doi={10.4108/eai.8-7-2021.170288} }- P. Anusha
R.V. Siva Balan
Year: 2021
Efficient Power Management in Mobile Computing with Edge Server Offloading Using Multi-Objective Optimization
EW
EAI
DOI: 10.4108/eai.8-7-2021.170288
Abstract
INTRODUCTION: The internet of mobile things is subjected to execute on data centers such as cloudlet, cloud servers and also on devices; it solves the problem of multi-objective optimization and tries to discover active scheduling with low energy consumption, execution time and cost.
OBJECTIVES: To alleviate the conflicts between the support constraint of ‘smart phones and customers' requests of diminishing idleness as well as extending battery life, it spikes a well-known wave of offloading portable application for execution to brought together server farms, for example, haze hubs and cloud workers.
METHODS: The test to develop the methodology for mobile phones, with enhanced IoT execution in cloud-edge registering. Then, to assess the feasibility of our proposed process, tests and simulations are carried out.
RESULTS: The simulator is used to test the algorithm, and the outcomes show that our calculations can lesser over 18% energy utilization.
CONCLUSION: The optimization approaches using PSO and GA based on simulation data, with the standard genetic algorithm providing the highest overall value for mission offloading in fog nodes using multi-objectives. With the assumption of various workflow models as single and multi-objective in data centers as cloud servers, fog nodes, and within computers, we extracted the analytic results of energy usage, delay efficiency, and cost. Then formulated the multi-objective problem with different constraints and solved it using various scheduling algorithms based on the obtained data.
Copyright © 2021 P.Anusha et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.
