Traffic Load Balancing based on Probabilistic Routing in Data Center Networks

Fu Wang; Fulong Yan; Xuwei Xue; Bo Liu; Lijia Zhang; Qi Zhang; Xiangjun Xin; Nicola Calabretta

doi:10.23919/ONDM48393.2020.9133002

Traffic Load Balancing based on Probabilistic Routing in Data Center Networks

Fu Wang, Fulong Yan, Xuwei Xue, Bo Liu, Lijia Zhang, Qi Zhang, Xiangjun Xin, Nicola Calabretta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We investigate a novel load-balancing algorithm exploiting probabilistic dynamic routing for OPSquare DCN. Results show that for 10240-server DCN, the proposed load-balancing decreases the ToR-to-ToR latency by 27.3% and packet loss by 56.45% at a load of 0.6.

Original language	English
Title of host publication	2020 24th International Conference on Optical Network Design and Modeling, ONDM 2020
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9783903176218
DOIs	https://doi.org/10.23919/ONDM48393.2020.9133002
Publication status	Published - May 2020
Event	24th International Conference on Optical Network Design and Modeling, ONDM 2020 - Castelldefels, Barcelona, Spain Duration: 18 May 2020 → 21 May 2020

Conference

Conference	24th International Conference on Optical Network Design and Modeling, ONDM 2020
Country	Spain
City	Castelldefels, Barcelona
Period	18/05/20 → 21/05/20

Keywords

data center networking
load balancing
OPSquare
probabilistic routing

Access to Document

10.23919/ONDM48393.2020.9133002

Fingerprint Dive into the research topics of 'Traffic Load Balancing based on Probabilistic Routing in Data Center Networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{22a354988e7f4285aceb044f90105b18,

title = "Traffic Load Balancing based on Probabilistic Routing in Data Center Networks",

abstract = "We investigate a novel load-balancing algorithm exploiting probabilistic dynamic routing for OPSquare DCN. Results show that for 10240-server DCN, the proposed load-balancing decreases the ToR-to-ToR latency by 27.3% and packet loss by 56.45% at a load of 0.6.",

keywords = "data center networking, load balancing, OPSquare, probabilistic routing",

author = "Fu Wang and Fulong Yan and Xuwei Xue and Bo Liu and Lijia Zhang and Qi Zhang and Xiangjun Xin and Nicola Calabretta",

year = "2020",

month = may,

doi = "10.23919/ONDM48393.2020.9133002",

language = "English",

booktitle = "2020 24th International Conference on Optical Network Design and Modeling, ONDM 2020",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "24th International Conference on Optical Network Design and Modeling, ONDM 2020 ; Conference date: 18-05-2020 Through 21-05-2020",

}

Wang, F, Yan, F , Xue, X, Liu, B, Zhang, L, Zhang, Q, Xin, X & Calabretta, N 2020, Traffic Load Balancing based on Probabilistic Routing in Data Center Networks. in 2020 24th International Conference on Optical Network Design and Modeling, ONDM 2020., 9133002, Institute of Electrical and Electronics Engineers, 24th International Conference on Optical Network Design and Modeling, ONDM 2020, Castelldefels, Barcelona, Spain, 18/05/20. https://doi.org/10.23919/ONDM48393.2020.9133002

Traffic Load Balancing based on Probabilistic Routing in Data Center Networks. / Wang, Fu; Yan, Fulong ; Xue, Xuwei; Liu, Bo; Zhang, Lijia; Zhang, Qi; Xin, Xiangjun; Calabretta, Nicola.

2020 24th International Conference on Optical Network Design and Modeling, ONDM 2020. Institute of Electrical and Electronics Engineers, 2020. 9133002.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Traffic Load Balancing based on Probabilistic Routing in Data Center Networks

AU - Wang, Fu

AU - Yan, Fulong

AU - Xue, Xuwei

AU - Liu, Bo

AU - Zhang, Lijia

AU - Zhang, Qi

AU - Xin, Xiangjun

AU - Calabretta, Nicola

PY - 2020/5

Y1 - 2020/5

N2 - We investigate a novel load-balancing algorithm exploiting probabilistic dynamic routing for OPSquare DCN. Results show that for 10240-server DCN, the proposed load-balancing decreases the ToR-to-ToR latency by 27.3% and packet loss by 56.45% at a load of 0.6.

AB - We investigate a novel load-balancing algorithm exploiting probabilistic dynamic routing for OPSquare DCN. Results show that for 10240-server DCN, the proposed load-balancing decreases the ToR-to-ToR latency by 27.3% and packet loss by 56.45% at a load of 0.6.

KW - data center networking

KW - load balancing

KW - OPSquare

KW - probabilistic routing

UR - http://www.scopus.com/inward/record.url?scp=85089754927&partnerID=8YFLogxK

U2 - 10.23919/ONDM48393.2020.9133002

DO - 10.23919/ONDM48393.2020.9133002

M3 - Conference contribution

AN - SCOPUS:85089754927

BT - 2020 24th International Conference on Optical Network Design and Modeling, ONDM 2020

PB - Institute of Electrical and Electronics Engineers

T2 - 24th International Conference on Optical Network Design and Modeling, ONDM 2020

Y2 - 18 May 2020 through 21 May 2020

ER -

Traffic Load Balancing based on Probabilistic Routing in Data Center Networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this