Research Article
Computation Offloading for Multi-user Sequential Tasks in Heterogeneous Mobile Edge Computing
@INPROCEEDINGS{10.1007/978-3-030-92635-9_41, author={Huanhuan Xu and Jingya Zhou and Fei Gu}, title={Computation Offloading for Multi-user Sequential Tasks in Heterogeneous Mobile Edge Computing}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 17th EAI International Conference, CollaborateCom 2021, Virtual Event, October 16-18, 2021, Proceedings, Part I}, proceedings_a={COLLABORATECOM}, year={2022}, month={1}, keywords={Mobile edge computing Computation offloading Sequential tasks Regular expression}, doi={10.1007/978-3-030-92635-9_41} }- Huanhuan Xu
Jingya Zhou
Fei Gu
Year: 2022
Computation Offloading for Multi-user Sequential Tasks in Heterogeneous Mobile Edge Computing
COLLABORATECOM
Springer
DOI: 10.1007/978-3-030-92635-9_41
Abstract
Currently, many computation offloading studies in Mobile Edge Computing (MEC) mainly focus on the multi-user and multi-task offloading, where the tasks are independent and inseparable. However, nowadays many mobile applications, such as Augmented Reality (AR) glasses, face recognition,etc., can be classified into sequential tasks. Dependencies among tasks and resource competition among multiple users in the heterogeneous edge environment make the offloading problem very challenging. In this paper, we propose a new multi-user sequential task (MUST) framework to address the above challenge. Specifically, we present a comprehensive analysis of the time cost of the task offloading process in the MUST framework and define the multi-user sequential task offloading problem. Moreover, we prove the problem is NP-hard and propose a reMUST algorithm based on regular expression to obtain the approximate optimal solution. Numerous experiments have shown that the proposed method is superior to existing alternatives in terms of cost and system scalability.
