A network function parallelism-enabled MEC framework for supporting low-latency services

Liu, M., Feng, G., Sun, Y. , Chen, N. and Tan, W. (2023) A network function parallelism-enabled MEC framework for supporting low-latency services. IEEE Transactions on Services Computing, 16(1), pp. 40-52. (doi: 10.1109/TSC.2021.3130247)

Abstract

Mobile edge computing (MEC) enables users to offload computing tasks to edge servers for provisioning low-latency and computation-intensive services. To manage heterogeneous resources and improve service flexibility, MEC is entailed by new technologies, \textit{i.e.}, software defined networking (SDN) and network function virtualization (NFV), which allow services running on common commodity hardware instead of proprietary hardware. However, data processing via software on commodity servers may induce high latency due to limited processing capacity, which impedes the quality of service. Meanwhile, MEC is a resource-sharing system and thus fairness should be considered. In this paper, we propose a network function parallelism (NFP)-enabled MEC (NFPMec) framework for supporting low-latency services. To reap the potential benefits of the NFPMec, we formulate the fairness-aware throughput maximization problem (FTMP) with aim of maximizing the fairness-aware system throughput while satisfying the QoS requirements. We propose a relaxation-based generalized benders algorithm (RGBA) to decouple the FTMP into two sub-problems based on the non-linear convex duality theory. After relaxation, the sub-problems are solved by the Karush-Kuhn-Tucker (KKT) approach. The convergence of the RGBA is theoretically proved. The simulation results demonstrate that the proposed NFPMec outperforms SDN-enabled MEC networks in terms of resource utilization, service latency and system throughput.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Sun, Dr Yao
• Authors: Liu, M., Feng, G., Sun, Y., Chen, N., and Tan, W.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
• Journal Name: IEEE Transactions on Services Computing
• Publisher: IEEE
• ISSN: 1939-1374
• ISSN (Online): 1939-1374
• Published Online: 24 November 2021
• Copyright Holders: Copyright © 2021 IEEE
• First Published: First published in IEEE Transactions on Services Computing 16(1): 40-52
• Publisher Policy: Reproduced in accordance with the publisher copyright policy