Modeling the effect of wavelength selective switch latency on optical flow switching performance

Ali Shakeri, Xue Wang, Miguel Razo, Miquel Garrich Alabarce, Eiji Oki, Naoaki Yamanaka, Andrea Fumagalli

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Optical networks are well suited to enable massive data exchanges between datacenters. Elephant data flows can be routed over custom provisioned and dedicated lightpaths (optical flows) while other (mice) flows, which are routed by electronic switches, are unaffected. In some solutions, wavelength-selective switch (WSS) devices are employed in the optical nodes to physically and individually route each lightpath toward its destination. WSS devices take time to be switched and consequently delay the lightpath setup completion time. In this paper, the authors present three approximate Markov chain models to account for three different WSS service policies. These models estimate the expected lightpath setup and teardown time across an optical node that makes use of WSS devices. The first and more conventional policy (model) assumes that each setup and teardown request is handled individually, while the other two policies (models) assume that groups of setup and/or teardown requests are handled together by the WSS. The models' estimates are compared against the results obtained from a computer-based simulator, where both analytical models and simulator account for experimentally measured WSS response times. The simulator is also used to investigate the end-to-end lightpath setup time across an arbitrary mesh network. Results obtained from the models and simulator show that the group-based service policies outperform the conventional policy at high loads. The group-based policies are especially useful in the presence of lightpaths that are frequently set up and have relatively short holding time (i.e., short duration of elephant-optical flows).

Original languageEnglish
Pages (from-to)924-935
Number of pages12
JournalJournal of Optical Communications and Networking
Volume10
Issue number12
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Optical flows
Switches
Wavelength
Simulators
Electronic data interchange
Fiber optic networks
Markov processes
Analytical models

Keywords

  • Circuit switching
  • Markov chain model
  • Optical networks
  • Wavelength selective switch

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Modeling the effect of wavelength selective switch latency on optical flow switching performance. / Shakeri, Ali; Wang, Xue; Razo, Miguel; Alabarce, Miquel Garrich; Oki, Eiji; Yamanaka, Naoaki; Fumagalli, Andrea.

In: Journal of Optical Communications and Networking, Vol. 10, No. 12, 01.12.2018, p. 924-935.

Research output: Contribution to journalArticle

Shakeri, Ali ; Wang, Xue ; Razo, Miguel ; Alabarce, Miquel Garrich ; Oki, Eiji ; Yamanaka, Naoaki ; Fumagalli, Andrea. / Modeling the effect of wavelength selective switch latency on optical flow switching performance. In: Journal of Optical Communications and Networking. 2018 ; Vol. 10, No. 12. pp. 924-935.
@article{9758f901ec3e4b1da00847983fdf333a,
title = "Modeling the effect of wavelength selective switch latency on optical flow switching performance",
abstract = "Optical networks are well suited to enable massive data exchanges between datacenters. Elephant data flows can be routed over custom provisioned and dedicated lightpaths (optical flows) while other (mice) flows, which are routed by electronic switches, are unaffected. In some solutions, wavelength-selective switch (WSS) devices are employed in the optical nodes to physically and individually route each lightpath toward its destination. WSS devices take time to be switched and consequently delay the lightpath setup completion time. In this paper, the authors present three approximate Markov chain models to account for three different WSS service policies. These models estimate the expected lightpath setup and teardown time across an optical node that makes use of WSS devices. The first and more conventional policy (model) assumes that each setup and teardown request is handled individually, while the other two policies (models) assume that groups of setup and/or teardown requests are handled together by the WSS. The models' estimates are compared against the results obtained from a computer-based simulator, where both analytical models and simulator account for experimentally measured WSS response times. The simulator is also used to investigate the end-to-end lightpath setup time across an arbitrary mesh network. Results obtained from the models and simulator show that the group-based service policies outperform the conventional policy at high loads. The group-based policies are especially useful in the presence of lightpaths that are frequently set up and have relatively short holding time (i.e., short duration of elephant-optical flows).",
keywords = "Circuit switching, Markov chain model, Optical networks, Wavelength selective switch",
author = "Ali Shakeri and Xue Wang and Miguel Razo and Alabarce, {Miquel Garrich} and Eiji Oki and Naoaki Yamanaka and Andrea Fumagalli",
year = "2018",
month = "12",
day = "1",
doi = "10.1364/JOCN.10.000924",
language = "English",
volume = "10",
pages = "924--935",
journal = "Journal of Optical Communications and Networking",
issn = "1943-0620",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - Modeling the effect of wavelength selective switch latency on optical flow switching performance

AU - Shakeri, Ali

AU - Wang, Xue

AU - Razo, Miguel

AU - Alabarce, Miquel Garrich

AU - Oki, Eiji

AU - Yamanaka, Naoaki

AU - Fumagalli, Andrea

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Optical networks are well suited to enable massive data exchanges between datacenters. Elephant data flows can be routed over custom provisioned and dedicated lightpaths (optical flows) while other (mice) flows, which are routed by electronic switches, are unaffected. In some solutions, wavelength-selective switch (WSS) devices are employed in the optical nodes to physically and individually route each lightpath toward its destination. WSS devices take time to be switched and consequently delay the lightpath setup completion time. In this paper, the authors present three approximate Markov chain models to account for three different WSS service policies. These models estimate the expected lightpath setup and teardown time across an optical node that makes use of WSS devices. The first and more conventional policy (model) assumes that each setup and teardown request is handled individually, while the other two policies (models) assume that groups of setup and/or teardown requests are handled together by the WSS. The models' estimates are compared against the results obtained from a computer-based simulator, where both analytical models and simulator account for experimentally measured WSS response times. The simulator is also used to investigate the end-to-end lightpath setup time across an arbitrary mesh network. Results obtained from the models and simulator show that the group-based service policies outperform the conventional policy at high loads. The group-based policies are especially useful in the presence of lightpaths that are frequently set up and have relatively short holding time (i.e., short duration of elephant-optical flows).

AB - Optical networks are well suited to enable massive data exchanges between datacenters. Elephant data flows can be routed over custom provisioned and dedicated lightpaths (optical flows) while other (mice) flows, which are routed by electronic switches, are unaffected. In some solutions, wavelength-selective switch (WSS) devices are employed in the optical nodes to physically and individually route each lightpath toward its destination. WSS devices take time to be switched and consequently delay the lightpath setup completion time. In this paper, the authors present three approximate Markov chain models to account for three different WSS service policies. These models estimate the expected lightpath setup and teardown time across an optical node that makes use of WSS devices. The first and more conventional policy (model) assumes that each setup and teardown request is handled individually, while the other two policies (models) assume that groups of setup and/or teardown requests are handled together by the WSS. The models' estimates are compared against the results obtained from a computer-based simulator, where both analytical models and simulator account for experimentally measured WSS response times. The simulator is also used to investigate the end-to-end lightpath setup time across an arbitrary mesh network. Results obtained from the models and simulator show that the group-based service policies outperform the conventional policy at high loads. The group-based policies are especially useful in the presence of lightpaths that are frequently set up and have relatively short holding time (i.e., short duration of elephant-optical flows).

KW - Circuit switching

KW - Markov chain model

KW - Optical networks

KW - Wavelength selective switch

UR - http://www.scopus.com/inward/record.url?scp=85058527195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058527195&partnerID=8YFLogxK

U2 - 10.1364/JOCN.10.000924

DO - 10.1364/JOCN.10.000924

M3 - Article

AN - SCOPUS:85058527195

VL - 10

SP - 924

EP - 935

JO - Journal of Optical Communications and Networking

JF - Journal of Optical Communications and Networking

SN - 1943-0620

IS - 12

ER -