Distributed and load adaptive energy management algorithm for ethernet green routers

Mohamad Khattar Awad, Phone Lin, Gi-Ren Liu

Research output: Contribution to journalArticle

Abstract

The existing Ethernet networks are designed with high redundancy and over-dimensioning so they can provide reliable services during peak traffic demand periods. However, this has increased the total energy consumption and operational cost. In this paper, we propose an energy saving algorithm (ESA) to reduce the energy consumption of green routers by considering the buffer status and the traffic load. We develop a Network Simulator, version 2, (NS-2)-based simulation model for ESA to evaluate its performance with respect to real traffic traces. Performance bounds of the proposed algorithm are derived. Numerical evaluations are conducted to verify the accuracy of the simulation model against derived bounds. Performance evaluations demonstrate that the proposed algorithm outperforms candidate algorithms, thereby providing greater energy savings with an acceptable packet delay and loss. We show that the introduced delay is bounded by an upper bound that is slightly larger than half of the sleep timer. Furthermore, performance comparisons are extensive and detailed, thus providing insights into the performance of different energy saving functions considered by the candidate algorithms.

Original languageEnglish
Pages (from-to)781-794
Number of pages14
JournalJournal of Internet Technology
Volume19
Issue number3
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Energy management
Ethernet
Routers
Energy conservation
Energy utilization
Redundancy
Simulators
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Networks and Communications

Cite this

@article{548964054dc34516b0e067cd24991986,
title = "Distributed and load adaptive energy management algorithm for ethernet green routers",
abstract = "The existing Ethernet networks are designed with high redundancy and over-dimensioning so they can provide reliable services during peak traffic demand periods. However, this has increased the total energy consumption and operational cost. In this paper, we propose an energy saving algorithm (ESA) to reduce the energy consumption of green routers by considering the buffer status and the traffic load. We develop a Network Simulator, version 2, (NS-2)-based simulation model for ESA to evaluate its performance with respect to real traffic traces. Performance bounds of the proposed algorithm are derived. Numerical evaluations are conducted to verify the accuracy of the simulation model against derived bounds. Performance evaluations demonstrate that the proposed algorithm outperforms candidate algorithms, thereby providing greater energy savings with an acceptable packet delay and loss. We show that the introduced delay is bounded by an upper bound that is slightly larger than half of the sleep timer. Furthermore, performance comparisons are extensive and detailed, thus providing insights into the performance of different energy saving functions considered by the candidate algorithms.",
author = "Awad, {Mohamad Khattar} and Phone Lin and Gi-Ren Liu",
year = "2018",
month = "1",
day = "1",
doi = "10.3966/160792642018051903014",
language = "English",
volume = "19",
pages = "781--794",
journal = "Journal of Internet Technology",
issn = "1607-9264",
publisher = "Taiwan Academic Network Management Committee",
number = "3",

}

Distributed and load adaptive energy management algorithm for ethernet green routers. / Awad, Mohamad Khattar; Lin, Phone; Liu, Gi-Ren.

In: Journal of Internet Technology, Vol. 19, No. 3, 01.01.2018, p. 781-794.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Distributed and load adaptive energy management algorithm for ethernet green routers

AU - Awad, Mohamad Khattar

AU - Lin, Phone

AU - Liu, Gi-Ren

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The existing Ethernet networks are designed with high redundancy and over-dimensioning so they can provide reliable services during peak traffic demand periods. However, this has increased the total energy consumption and operational cost. In this paper, we propose an energy saving algorithm (ESA) to reduce the energy consumption of green routers by considering the buffer status and the traffic load. We develop a Network Simulator, version 2, (NS-2)-based simulation model for ESA to evaluate its performance with respect to real traffic traces. Performance bounds of the proposed algorithm are derived. Numerical evaluations are conducted to verify the accuracy of the simulation model against derived bounds. Performance evaluations demonstrate that the proposed algorithm outperforms candidate algorithms, thereby providing greater energy savings with an acceptable packet delay and loss. We show that the introduced delay is bounded by an upper bound that is slightly larger than half of the sleep timer. Furthermore, performance comparisons are extensive and detailed, thus providing insights into the performance of different energy saving functions considered by the candidate algorithms.

AB - The existing Ethernet networks are designed with high redundancy and over-dimensioning so they can provide reliable services during peak traffic demand periods. However, this has increased the total energy consumption and operational cost. In this paper, we propose an energy saving algorithm (ESA) to reduce the energy consumption of green routers by considering the buffer status and the traffic load. We develop a Network Simulator, version 2, (NS-2)-based simulation model for ESA to evaluate its performance with respect to real traffic traces. Performance bounds of the proposed algorithm are derived. Numerical evaluations are conducted to verify the accuracy of the simulation model against derived bounds. Performance evaluations demonstrate that the proposed algorithm outperforms candidate algorithms, thereby providing greater energy savings with an acceptable packet delay and loss. We show that the introduced delay is bounded by an upper bound that is slightly larger than half of the sleep timer. Furthermore, performance comparisons are extensive and detailed, thus providing insights into the performance of different energy saving functions considered by the candidate algorithms.

UR - http://www.scopus.com/inward/record.url?scp=85048881695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048881695&partnerID=8YFLogxK

U2 - 10.3966/160792642018051903014

DO - 10.3966/160792642018051903014

M3 - Article

VL - 19

SP - 781

EP - 794

JO - Journal of Internet Technology

JF - Journal of Internet Technology

SN - 1607-9264

IS - 3

ER -