Enabling dynamic autoscaling for NFV in a non-standalone virtual EPC: Design and analysis

Ren, Yi ORCID: https://orcid.org/0000-0001-7423-6719, Phung-Duc, Tuan, Chen, Jyh-Cheng and Li, Frank Y. (2023) Enabling dynamic autoscaling for NFV in a non-standalone virtual EPC: Design and analysis. IEEE Transactions on Vehicular Technology, 72 (6). pp. 7743-7756. ISSN 0018-9545

[thumbnail of Enabling_Dynamic_Autoscaling_for_NFV_in_a_Non-Standalone_Virtual_EPC_Design_and_Analysis]
Preview
PDF (Enabling_Dynamic_Autoscaling_for_NFV_in_a_Non-Standalone_Virtual_EPC_Design_and_Analysis) - Accepted Version
Download (1MB) | Preview

Abstract

Network function virtualization (NFV) is a novel concept that enables an architectural transition from dedicated hardware to orchestrated resource and function management. As an integral part of the core network, NFV offers a fine-grained network capability to cellular operators by scaling out or scaling in network resources in an on-demand manner to meet the performance requirements. However, designing an autoscaling algorithm with low operation cost and low latency in non-standalone networks, where legacy network equipment coexists with a virtual evolved packet core (EPC), is a challenging task. In this paper, we propose a dynamic NFV instance autoscaling algorithm that considers the tradeoff between performance and operation cost. Furthermore, we develop an analytical framework to assess the performance of the scheme by modeling the hybrid network as a queueing system that includes both legacy network equipment and NFV instances. The virtualized network function (VNF) instances are powered on or off according to the number of job requests. Numerical results based on extensive simulations validate the correctness of the model and the effectiveness of the algorithm.

Item Type: Article
Additional Information: Funding Information: The work of Yi Ren was supported in part by EPSRC under Grants EP/T022566/1 and EP/T024593/1, and in part by the Royal Society IEC\R3\213100. The work of Tuan Phung-Duc was supported in part by JSPS KAKENHI under Grants 18K18006 and 21K11765. The work of Jyh-Cheng Chen’s was supported by the National Science and Technology Council of Taiwan under Grants 111-2221-E-A49-093-MY3, 111-2218-E-A49-023, and 111-3114-E-A49-001. The work of Frank Y. Li, was supported by the European Economic Area (EEA) Norway (NO) Grant 2014-2021, under Project Contract 42/2021, RO-NO-2019-0499-A Massive MIMO Enabled IoT Platform with Networking Slicing for Beyond 5G IoV/V2X and Maritime Services (SOLIDB5G).
Uncontrolled Keywords: 5g mobile communication,computational modeling,costs,epc,hardware,heuristic algorithms,nfv instance resource allocation,network function virtualization,resource management,dynamic autoscaling algorithm,modeling and analysis,network function virtualization,modeling,analysis,aerospace engineering,applied mathematics,electrical and electronic engineering,automotive engineering,computer networks and communications ,/dk/atira/pure/subjectarea/asjc/2200/2202
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Cyber Security Privacy and Trust Laboratory
Faculty of Science > Research Groups > Data Science and AI
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 16 Feb 2023 16:31
Last Modified: 19 Dec 2024 01:09
URI: https://ueaeprints.uea.ac.uk/id/eprint/91163
DOI: 10.1109/TVT.2023.3237698

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item