Cloud Computing, Smart Grid and Innovative Frontiers in Telecommunications. 9th EAI International Conference, CloudComp 2019, and 4th EAI International Conference, SmartGIFT 2019, Beijing, China, December 4-5, 2019, and December 21-22, 2019

Research Article

A Multi-objective Computation Offloading Method for Hybrid Workflow Applications in Mobile Edge Computing

Download
154 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-48513-9_4,
        author={Kai Peng and Bohai Zhao and Xingda Qian and Xiaolong Xu and Lixin Zheng and Victor Leung},
        title={A Multi-objective Computation Offloading Method for Hybrid Workflow Applications in Mobile Edge Computing},
        proceedings={Cloud Computing, Smart Grid and Innovative Frontiers in Telecommunications. 9th EAI International Conference, CloudComp 2019, and 4th EAI International Conference, SmartGIFT 2019, Beijing, China, December 4-5, 2019, and December 21-22, 2019},
        proceedings_a={CLOUDCOMP},
        year={2020},
        month={6},
        keywords={Mobile edge computing Hybrid workflow applications Multi-objective Time consumption Energy consumption},
        doi={10.1007/978-3-030-48513-9_4}
    }
    
  • Kai Peng
    Bohai Zhao
    Xingda Qian
    Xiaolong Xu
    Lixin Zheng
    Victor Leung
    Year: 2020
    A Multi-objective Computation Offloading Method for Hybrid Workflow Applications in Mobile Edge Computing
    CLOUDCOMP
    Springer
    DOI: 10.1007/978-3-030-48513-9_4
Kai Peng,*, Bohai Zhao1, Xingda Qian1, Xiaolong Xu2, Lixin Zheng3, Victor Leung4
  • 1: Huaqiao University
  • 2: Nanjing University of Science and Technology
  • 3: Fujian Provincial Academic Engineering Research Center in Industrial Intellectual Techniques and Systems
  • 4: The University of British Columbia
*Contact email: pkbupt@gmail.com

Abstract

Computation offloading has become a promising method to overcome intrinsic defects of portable smart devices, such as low operating speed and low battery capacity. However, it is a challenge to design an optimized strategy as the edge server is resource-constrained and the workflow application has timing constraints. In this paper, we investigated the hybrid workflow application computation offloading issue, which further increases the difficulty. According to the analysis of theory and consideration of time consumption and energy consumption, we establish a multi-objective optimization model to solve the issue. Furthermore, we propose a method based on particle swarm optimization algorithm for multi-objective computation offloading to get the optimal strategy for tasks offloading, which is suitable for all the hybrid workflow applications. Finally, extensive experiments have verified the effectiveness and efficiency of our proposed method.