Title: Improving network routing energy-efficiency for real-time workloads by stochastic service model
Authors: Peng Xiao; Dongbo Liu
Addresses: College of Computer and Communication, Hunan Institute of Engineering, Xiangtan City, Hunan Province, China ' College of Computer and Communication, Hunan Institute of Engineering, Xiangtan City, Hunan Province, China
Abstract: Recently, green networking has attracted more and more attentions due to the rapid growth of network energy consumption. Typically, some tradeoffs between energy consumption and performance have to be made when using many existing energy-efficient approaches. However, many popular applications require real-time responsiveness for attracting potential users, which makes it difficult to sacrifice execution performance for achieving energy-efficiency. In this paper, we present an energy-efficient routing mechanism for this kind of network applications. The proposed approach uses stochastic service model to evaluate the degree of deadline guarantee, by which the network links can be powered down without loss of application's real-time QoS requirement. Massive experiments are performed to investigate the effectiveness of the proposed approach, and the results show that it can improve about 35% energy-efficiency for network devices when the system is in presence of real-time workloads.
Keywords: green computing; energy efficiency; stochastic modelling; deadline guarantees; network routing; service models; green networking; QoS requirements; quality of service; real-time workloads.
International Journal of Information and Communication Technology, 2015 Vol.7 No.2/3, pp.302 - 315
Received: 18 Sep 2013
Accepted: 14 Jul 2014
Published online: 13 Mar 2015 *