Optimal power consumption analysis of a load-dependent server activation policy for a data service center

Chang, Chia‐Jung; Chang, Fu‐Min; Ke, Jau‐Chuan

doi:10.1016/j.cie.2019.03.024

Cited by 5 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These mechanisms either ignore the VM setup time or deal only with virtualized resources without considering resources from legacy systems. Although [27], [28], [30] derived optimal properties and presented a precise analysis for a queueing model, [28] ignores setup time and [27], [30] did not consider legacy servers. Therefore, the existing mechanisms and models are not applicable to non-standalone 5G networks, where eNBs and gNBs coexist.…”

Section: Related Workmentioning

confidence: 99%

Enabling Dynamic Autoscaling for NFV in a Non-Standalone Virtual EPC: Design and Analysis

Ren

Phung-Duc

Chen

et al. 2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

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 finegrained 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 nonstandalone 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.

show abstract