Ad Hoc Networks. 11th EAI International Conference, ADHOCNETS 2019, Queenstown, New Zealand, November 18–21, 2019, Proceedings

Research Article

Delay Based Wireless Scheduling and Server Assignment for Fog Computing Systems

  • @INPROCEEDINGS{10.1007/978-3-030-37262-0_15,
        author={Yuan Zhang and Mingyang Xie and Qiang Guo and Wei Heng and Peng Du},
        title={Delay Based Wireless Scheduling and Server Assignment for Fog Computing Systems},
        proceedings={Ad Hoc Networks. 11th EAI International Conference, ADHOCNETS 2019, Queenstown, New Zealand, November 18--21, 2019, Proceedings},
        proceedings_a={ADHOCNETS},
        year={2020},
        month={1},
        keywords={Fog computing Resource allocation Delay Lyapunov},
        doi={10.1007/978-3-030-37262-0_15}
    }
    
  • Yuan Zhang
    Mingyang Xie
    Qiang Guo
    Wei Heng
    Peng Du
    Year: 2020
    Delay Based Wireless Scheduling and Server Assignment for Fog Computing Systems
    ADHOCNETS
    Springer
    DOI: 10.1007/978-3-030-37262-0_15
Yuan Zhang1,*, Mingyang Xie1,*, Qiang Guo1,*, Wei Heng1,*, Peng Du2,*
  • 1: Southeast University
  • 2: Nanjing University of Posts and Telecommunications
*Contact email: y.zhang@seu.edu.cn, 1090492123@qq.com, qguo@seu.edu.cn, wheng@seu.edu.cn, dupeng@njupt.edu.cn

Abstract

To further reduce the delay in fog computing systems, new resource allocation algorithms are needed. Firstly, we have derived the recursive expressions of the communication and computing delays in the fog computing system without assuming the knowledge of the statistics of user application arrival traffic. Based on these analytical formulas, an optimization problem of delay minimization is formulated directly, and then a novel wireless scheduling and server assignment algorithm is designed. The delay performance of the proposed algorithm is evaluated via simulation experiments. Under the considered simulation parameters, the proposed algorithm can achieve 13.5% less total delay, as compared to the traditional algorithm. The impact of the total number of subcarriers in the system and the average user application arrival rate on the percentage of delay reduction is evaluated. Therefore, compared with the queue length optimization based traditional resource allocation algorithms, the delay optimization based resource allocation algorithm proposed in this paper can further reduce delay.