ew 18: e34

Research Article

Efficient Power Management in Mobile Computing with Edge Server Offloading Using Multi-Objective Optimization

Download45 downloads
  • @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: Online First},
        volume={},
        number={},
        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
P. Anusha1,*, R.V. Siva Balan1
  • 1: Department of Computer Applications, Noorul Islam Centre for Higher Education, Kumaracoil, Thucklay, Kanyakumari (Dt), Tamil Nadu, India-629 180
*Contact email: anushajournals@gmail.com

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.