AggreFlow: Achieving Power Efficiency, Load Balancing, and Quality of Service in Data Center Networks

Zehua Guo; Yang Xu; Ya Feng Liu; Sen Liu; H. Jonathan Chao; Zhi Li Zhang; Yuanqing Xia

doi:10.1109/TNET.2020.3026015

AggreFlow: Achieving Power Efficiency, Load Balancing, and Quality of Service in Data Center Networks

Zehua Guo, Yang Xu, Ya Feng Liu, Sen Liu, H. Jonathan Chao, Zhi Li Zhang, Yuanqing Xia

Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

18 Scopus citations

Abstract

Power-efficient Data Center Networks (DCNs) have been proposed to save power of DCNs using OpenFlow. In these DCNs, the OpenFlow controller adaptively turns on/off links and OpenFlow switches to form a minimum-power subnet that satisfies the traffic demand. As the subnet changes, flows are dynamically routed and rerouted to the routes composed of active switches and links. However, existing flow scheduling schemes could cause undesired results: (1) power inefficiency: due to unbalanced traffic allocation on active routes, extra switches and links may be activated to cater to bursty traffic surges on congested routes, and (2) Quality of Service (QoS) fluctuation: because of the limited flow entry processing ability, switches may not be able to timely install/delete/update flow entries to properly route/reroute flows. In this paper, we propose AggreFlow, a dynamic flow scheduling scheme that achieves power efficiency and QoS improvement using three techniques: Flow-set Routing, Lazy Rerouting, and Adaptive Rerouting. Flow-set Routing achieves load balancing with a small number of flow entry operations by routing flows in a coarse-grained flow-set fashion. Lazy Rerouting spreads rerouting operations over a relatively long period of time, reducing the burstiness of entry operation on switches. Adaptive Rerouting selectively reroutes flow-sets to maintain load balancing. We built an NS3 based fat-tree network simulation platform to evaluate AggreFlow's performance. The simulation results show that AggreFlow reduces power consumption by about 18%, yet achieving load balancing and improved QoS (low packet loss rate and reducing the number of processing entries for flow scheduling by 98%), compared with baseline schemes.

Original language	English (US)
Article number	9253693
Pages (from-to)	17-33
Number of pages	17
Journal	IEEE/ACM Transactions on Networking
Volume	29
Issue number	1
DOIs	https://doi.org/10.1109/TNET.2020.3026015
State	Published - Feb 2021

Bibliographical note

Funding Information:
Manuscript received September 5, 2019; revised March 22, 2020 and May 9, 2020; accepted August 22, 2020; approved by IEEE/ACM TRANSACTIONS ON NETWORKING Editor E. Uysal. Date of publication November 10, 2020; date of current version February 17, 2021. The work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1003700, in part by the Natural Science Foundation of China under Grant 62002019, Grant 11688101, Grant 11671419, Grant 11991021, and Grant 62002066, in part by the Beijing Institute of Technology Research Fund Program for Young Scholars, in part by the Project “PCL Future Greater-Bay Area Network Facilities for Large-scale Experiments and Applications (LZC0019)”, and in part by the U.S. NSF under Grant CNS-1618339, Grant CNS-1617729, and Grant CNS-1814322. This article was presented in part at IEEE/ACM IWQoS 2016. (Corresponding author: Yang Xu.) Zehua Guo and Yuanqing Xia are with the Beijing Institute of Technology, Beijing 100081, China.

Publisher Copyright:
© 1993-2012 IEEE.

Keywords

Flow scheduling
OpenFlow
power saving
power-efficient data center networks

Access

10.1109/TNET.2020.3026015

OpenUrl availability

Full text

Cite this

@article{12a04011b2c24807bd25931ad9420071,

title = "AggreFlow: Achieving Power Efficiency, Load Balancing, and Quality of Service in Data Center Networks",

abstract = "Power-efficient Data Center Networks (DCNs) have been proposed to save power of DCNs using OpenFlow. In these DCNs, the OpenFlow controller adaptively turns on/off links and OpenFlow switches to form a minimum-power subnet that satisfies the traffic demand. As the subnet changes, flows are dynamically routed and rerouted to the routes composed of active switches and links. However, existing flow scheduling schemes could cause undesired results: (1) power inefficiency: due to unbalanced traffic allocation on active routes, extra switches and links may be activated to cater to bursty traffic surges on congested routes, and (2) Quality of Service (QoS) fluctuation: because of the limited flow entry processing ability, switches may not be able to timely install/delete/update flow entries to properly route/reroute flows. In this paper, we propose AggreFlow, a dynamic flow scheduling scheme that achieves power efficiency and QoS improvement using three techniques: Flow-set Routing, Lazy Rerouting, and Adaptive Rerouting. Flow-set Routing achieves load balancing with a small number of flow entry operations by routing flows in a coarse-grained flow-set fashion. Lazy Rerouting spreads rerouting operations over a relatively long period of time, reducing the burstiness of entry operation on switches. Adaptive Rerouting selectively reroutes flow-sets to maintain load balancing. We built an NS3 based fat-tree network simulation platform to evaluate AggreFlow's performance. The simulation results show that AggreFlow reduces power consumption by about 18%, yet achieving load balancing and improved QoS (low packet loss rate and reducing the number of processing entries for flow scheduling by 98%), compared with baseline schemes.",

keywords = "Flow scheduling, OpenFlow, power saving, power-efficient data center networks",

author = "Zehua Guo and Yang Xu and Liu, {Ya Feng} and Sen Liu and Chao, {H. Jonathan} and Zhang, {Zhi Li} and Yuanqing Xia",

note = "Funding Information: Manuscript received September 5, 2019; revised March 22, 2020 and May 9, 2020; accepted August 22, 2020; approved by IEEE/ACM TRANSACTIONS ON NETWORKING Editor E. Uysal. Date of publication November 10, 2020; date of current version February 17, 2021. The work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1003700, in part by the Natural Science Foundation of China under Grant 62002019, Grant 11688101, Grant 11671419, Grant 11991021, and Grant 62002066, in part by the Beijing Institute of Technology Research Fund Program for Young Scholars, in part by the Project “PCL Future Greater-Bay Area Network Facilities for Large-scale Experiments and Applications (LZC0019)”, and in part by the U.S. NSF under Grant CNS-1618339, Grant CNS-1617729, and Grant CNS-1814322. This article was presented in part at IEEE/ACM IWQoS 2016. (Corresponding author: Yang Xu.) Zehua Guo and Yuanqing Xia are with the Beijing Institute of Technology, Beijing 100081, China. Publisher Copyright: {\textcopyright} 1993-2012 IEEE.",

year = "2021",

month = feb,

doi = "10.1109/TNET.2020.3026015",

language = "English (US)",

volume = "29",

pages = "17--33",

journal = "IEEE/ACM Transactions on Networking",

issn = "1063-6692",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - AggreFlow

T2 - Achieving Power Efficiency, Load Balancing, and Quality of Service in Data Center Networks

AU - Guo, Zehua

AU - Xu, Yang

AU - Liu, Ya Feng

AU - Liu, Sen

AU - Chao, H. Jonathan

AU - Zhang, Zhi Li

AU - Xia, Yuanqing

N1 - Funding Information: Manuscript received September 5, 2019; revised March 22, 2020 and May 9, 2020; accepted August 22, 2020; approved by IEEE/ACM TRANSACTIONS ON NETWORKING Editor E. Uysal. Date of publication November 10, 2020; date of current version February 17, 2021. The work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB1003700, in part by the Natural Science Foundation of China under Grant 62002019, Grant 11688101, Grant 11671419, Grant 11991021, and Grant 62002066, in part by the Beijing Institute of Technology Research Fund Program for Young Scholars, in part by the Project “PCL Future Greater-Bay Area Network Facilities for Large-scale Experiments and Applications (LZC0019)”, and in part by the U.S. NSF under Grant CNS-1618339, Grant CNS-1617729, and Grant CNS-1814322. This article was presented in part at IEEE/ACM IWQoS 2016. (Corresponding author: Yang Xu.) Zehua Guo and Yuanqing Xia are with the Beijing Institute of Technology, Beijing 100081, China. Publisher Copyright: © 1993-2012 IEEE.

PY - 2021/2

Y1 - 2021/2

N2 - Power-efficient Data Center Networks (DCNs) have been proposed to save power of DCNs using OpenFlow. In these DCNs, the OpenFlow controller adaptively turns on/off links and OpenFlow switches to form a minimum-power subnet that satisfies the traffic demand. As the subnet changes, flows are dynamically routed and rerouted to the routes composed of active switches and links. However, existing flow scheduling schemes could cause undesired results: (1) power inefficiency: due to unbalanced traffic allocation on active routes, extra switches and links may be activated to cater to bursty traffic surges on congested routes, and (2) Quality of Service (QoS) fluctuation: because of the limited flow entry processing ability, switches may not be able to timely install/delete/update flow entries to properly route/reroute flows. In this paper, we propose AggreFlow, a dynamic flow scheduling scheme that achieves power efficiency and QoS improvement using three techniques: Flow-set Routing, Lazy Rerouting, and Adaptive Rerouting. Flow-set Routing achieves load balancing with a small number of flow entry operations by routing flows in a coarse-grained flow-set fashion. Lazy Rerouting spreads rerouting operations over a relatively long period of time, reducing the burstiness of entry operation on switches. Adaptive Rerouting selectively reroutes flow-sets to maintain load balancing. We built an NS3 based fat-tree network simulation platform to evaluate AggreFlow's performance. The simulation results show that AggreFlow reduces power consumption by about 18%, yet achieving load balancing and improved QoS (low packet loss rate and reducing the number of processing entries for flow scheduling by 98%), compared with baseline schemes.

AB - Power-efficient Data Center Networks (DCNs) have been proposed to save power of DCNs using OpenFlow. In these DCNs, the OpenFlow controller adaptively turns on/off links and OpenFlow switches to form a minimum-power subnet that satisfies the traffic demand. As the subnet changes, flows are dynamically routed and rerouted to the routes composed of active switches and links. However, existing flow scheduling schemes could cause undesired results: (1) power inefficiency: due to unbalanced traffic allocation on active routes, extra switches and links may be activated to cater to bursty traffic surges on congested routes, and (2) Quality of Service (QoS) fluctuation: because of the limited flow entry processing ability, switches may not be able to timely install/delete/update flow entries to properly route/reroute flows. In this paper, we propose AggreFlow, a dynamic flow scheduling scheme that achieves power efficiency and QoS improvement using three techniques: Flow-set Routing, Lazy Rerouting, and Adaptive Rerouting. Flow-set Routing achieves load balancing with a small number of flow entry operations by routing flows in a coarse-grained flow-set fashion. Lazy Rerouting spreads rerouting operations over a relatively long period of time, reducing the burstiness of entry operation on switches. Adaptive Rerouting selectively reroutes flow-sets to maintain load balancing. We built an NS3 based fat-tree network simulation platform to evaluate AggreFlow's performance. The simulation results show that AggreFlow reduces power consumption by about 18%, yet achieving load balancing and improved QoS (low packet loss rate and reducing the number of processing entries for flow scheduling by 98%), compared with baseline schemes.

KW - Flow scheduling

KW - OpenFlow

KW - power saving

KW - power-efficient data center networks

UR - http://www.scopus.com/inward/record.url?scp=85096847427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85096847427&partnerID=8YFLogxK

U2 - 10.1109/TNET.2020.3026015

DO - 10.1109/TNET.2020.3026015

M3 - Article

AN - SCOPUS:85096847427

SN - 1063-6692

VL - 29

SP - 17

EP - 33

JO - IEEE/ACM Transactions on Networking

JF - IEEE/ACM Transactions on Networking

IS - 1

M1 - 9253693

ER -

AggreFlow: Achieving Power Efficiency, Load Balancing, and Quality of Service in Data Center Networks

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this