File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Minimizing internal speedup for performance guaranteed switches with optical fabrics

TitleMinimizing internal speedup for performance guaranteed switches with optical fabrics
Authors
KeywordsOptical switch fabric
Performance guaranteed switching
Reconfiguration overhead
Scheduling
Speedup
Issue Date2009
PublisherI E E E. The Journal's web site is located at http://www.comsoc.org/livepubs/net
Citation
Ieee/Acm Transactions On Networking, 2009, v. 17 n. 2, p. 632-645 How to Cite?
AbstractWe consider traffic scheduling in an N × N packet switch with an optical switch fabric, where the fabric requires a reconfiguration overhead to change its switch configurations. To provide 100% throughput with bounded packet delay, a speedup in the switch fabric is necessary to compensate for both the reconfiguration overhead and the inefficiency of the scheduling algorithm. In order to reduce the implementation cost of the switch, we aim at minimizing the required speedup for a given packet delay bound. Conventional Birkhoff-von Neumann traffic matrix decomposition requires N 2 - 2N + 2 configurations in the schedule, which lead to a very large packet delay bound. The existing DOUBLE algorithm requires a fixed number of only 2N configurations, but it cannot adjust its schedule according to different switch parameters. In this paper, we first design a generic approach to decompose a traffic matrix into an arbitrary number of N S (N 2 - 2N + 2 > N S > N) configurations. Then, by taking the reconfiguration overhead into account, we formulate a speedup function. Minimizing the speedup function results in an efficient scheduling algorithm ADAPT. We further observe that the algorithmic efficiency of ADAPT can be improved by better utilizing the switch bandwidth. This leads to a more efficient algorithm SRF (Scheduling Residue First). ADAPT and SRF can automatically adjust the number of configurations in a schedule according to different switch parameters. We show that both algorithms outperform the existing DOUBLE algorithm. © 2008 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/58787
ISSN
2023 Impact Factor: 3.0
2023 SCImago Journal Rankings: 2.034
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorWu, Ben_HK
dc.contributor.authorYeung, KLen_HK
dc.contributor.authorHamdi, Men_HK
dc.contributor.authorLi, Xen_HK
dc.date.accessioned2010-05-31T03:36:54Z-
dc.date.available2010-05-31T03:36:54Z-
dc.date.issued2009en_HK
dc.identifier.citationIeee/Acm Transactions On Networking, 2009, v. 17 n. 2, p. 632-645en_HK
dc.identifier.issn1063-6692en_HK
dc.identifier.urihttp://hdl.handle.net/10722/58787-
dc.description.abstractWe consider traffic scheduling in an N × N packet switch with an optical switch fabric, where the fabric requires a reconfiguration overhead to change its switch configurations. To provide 100% throughput with bounded packet delay, a speedup in the switch fabric is necessary to compensate for both the reconfiguration overhead and the inefficiency of the scheduling algorithm. In order to reduce the implementation cost of the switch, we aim at minimizing the required speedup for a given packet delay bound. Conventional Birkhoff-von Neumann traffic matrix decomposition requires N 2 - 2N + 2 configurations in the schedule, which lead to a very large packet delay bound. The existing DOUBLE algorithm requires a fixed number of only 2N configurations, but it cannot adjust its schedule according to different switch parameters. In this paper, we first design a generic approach to decompose a traffic matrix into an arbitrary number of N S (N 2 - 2N + 2 > N S > N) configurations. Then, by taking the reconfiguration overhead into account, we formulate a speedup function. Minimizing the speedup function results in an efficient scheduling algorithm ADAPT. We further observe that the algorithmic efficiency of ADAPT can be improved by better utilizing the switch bandwidth. This leads to a more efficient algorithm SRF (Scheduling Residue First). ADAPT and SRF can automatically adjust the number of configurations in a schedule according to different switch parameters. We show that both algorithms outperform the existing DOUBLE algorithm. © 2008 IEEE.en_HK
dc.languageengen_HK
dc.publisherI E E E. The Journal's web site is located at http://www.comsoc.org/livepubs/neten_HK
dc.relation.ispartofIEEE/ACM Transactions on Networkingen_HK
dc.subjectOptical switch fabricen_HK
dc.subjectPerformance guaranteed switchingen_HK
dc.subjectReconfiguration overheaden_HK
dc.subjectSchedulingen_HK
dc.subjectSpeedupen_HK
dc.titleMinimizing internal speedup for performance guaranteed switches with optical fabricsen_HK
dc.typeArticleen_HK
dc.identifier.emailYeung, KL:kyeung@eee.hku.hken_HK
dc.identifier.authorityYeung, KL=rp00204en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TNET.2008.926501en_HK
dc.identifier.scopuseid_2-s2.0-67349206586en_HK
dc.identifier.hkuros150299en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-67349206586&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume17en_HK
dc.identifier.issue2en_HK
dc.identifier.spage632en_HK
dc.identifier.epage645en_HK
dc.identifier.isiWOS:000265437800021-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridWu, B=35231472500en_HK
dc.identifier.scopusauthoridYeung, KL=7202424908en_HK
dc.identifier.scopusauthoridHamdi, M=7103051480en_HK
dc.identifier.scopusauthoridLi, X=36062614100en_HK
dc.identifier.issnl1063-6692-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats