
Research Article
Collaborative Task Processing and Resource Allocation Based on Multiple MEC Servers
@INPROCEEDINGS{10.1007/978-3-031-54521-4_21, author={Lei Shi and Shilong Feng and Rui Ji and Juan Xu and Xu Ding and Baotong Zhan}, title={Collaborative Task Processing and Resource Allocation Based on Multiple MEC Servers}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part I}, proceedings_a={COLLABORATECOM}, year={2024}, month={2}, keywords={Mobile Edge Computing Lyapunov Optimization Collaborative Task Processing Resource Allocation}, doi={10.1007/978-3-031-54521-4_21} }
- Lei Shi
Shilong Feng
Rui Ji
Juan Xu
Xu Ding
Baotong Zhan
Year: 2024
Collaborative Task Processing and Resource Allocation Based on Multiple MEC Servers
COLLABORATECOM
Springer
DOI: 10.1007/978-3-031-54521-4_21
Abstract
Mobile Edge Computing (MEC), an emerging computing paradigm, shifts computing and storage capabilities from the cloud to the network edge, aiming to meet the delay requirements of emerging applications and save backhaul network bandwidth. However, compared to cloud servers, MEC servers have limited computing and storage capabilities, which cannot meet the massive offloading demands of users during high-load periods. In this context, this paper proposes a multi-ENs collaborative task processing model. The model aims to formulate optimal offloading decisions and allocate computing resources for tasks to minimize system delay and cost. To solve this problem, we propose an online algorithm based on Lyapunov optimization called OKMTA, which can work online without the need for predicting future information. Specifically, the problem is formulated as a mixed-integer nonlinear programming (MINLP) problem and decomposed into two subproblems for solution. By using the Lagrange multiplier method to solve the computing resource allocation problem of tasks, and by using matching theory to solve the offloading decision problem of tasks. The simulation results show that our algorithm can achieve near-optimal delay performance while satisfying the long-term system average cost constraint.