期刊
IEEE ACCESS
卷 8, 期 -, 页码 39758-39767出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2975733
关键词
Task analysis; Servers; Energy consumption; Edge computing; Genetic algorithms; Heuristic algorithms; Resource management; Probability preferred; workload; offloading; genetic algorithm; mobile edge computing
资金
- National Natural Science Foundation of China [61772454, 61811530332, 61811540410]
- Degree AMP
- Postgraduate Education Reform Project of Hunan Province
- Deanship of Scientific Research at King Saud University [RG-1438-070]
Mobile edge computing (MEC) can provide computation and storage capabilities via edge servers which are closer to user devices (UDs). The MEC offloading system can be viewed as a system where each UD is covered by single or multiple edge servers. Existing works prefer a posterior design when task offloads, which can lead to increased workloads. To investigate the task offloading of edge computing in multi-coverage scenario and to reduce the workload during task offloading, a probability preferred priori offloading mechanism with joint optimization of offloading proportion and transmission power is presented in this paper. We first set up an expectation value which is determined by the offloading probability of heterogeneous edge servers, and then we form a utility function to balance the delay performance and energy consumption. Next, a distributed PRiori Offloading Mechanism with joint Offloading proportion and Transmission (PROMOT) power algorithm based on Genetic Algorithm (GA) is proposed to maximize the utility of UD. Finally, simulation results verify the superiority of our proposed scheme as compared with other popular methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据