Adaptive provisioning of differentiated services networks based on reinforcement learning
The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks has received a lot of attention from researchers. However, most proposed methods need to determine the amount of bandwidth to provision at the time of connection admission. This a...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on human-machine systems 2003-11, Vol.33 (4), p.492-501 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 501 |
|---|---|
| container_issue | 4 |
| container_start_page | 492 |
| container_title | IEEE transactions on human-machine systems |
| container_volume | 33 |
| creator | Hui, T.C.-K. Chen-Khong Tham |
| description | The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks has received a lot of attention from researchers. However, most proposed methods need to determine the amount of bandwidth to provision at the time of connection admission. This assumes that traffic in admitted flows always conforms to predefined specifications, which would need some form of traffic shaping or admission control before reaching the ingress of the domain. This paper proposes an adaptive provisioning mechanism based on reinforcement-learning principles, which determines at regular intervals the amount of bandwidth to provision to each PHB aggregate. The mechanism adjusts to maximize the amount of revenue earned from a usage-based pricing model. The novel use of a continuous-space, gradient-based learning algorithm, enables the mechanism to require neither accurate traffic specifications nor rigid admission control. Using ns-2 simulations, we demonstrate using Weighted Fair Queuing, how our mechanism can be implemented in a DiffServ network. |
| doi_str_mv | 10.1109/TSMCC.2003.818472 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_28250152</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1243527</ieee_id><sourcerecordid>28250152</sourcerecordid><originalsourceid>FETCH-LOGICAL-c384t-da301a0876c1ae6e63a91f918745edfc6bf80e0147246a864203288b346454d13</originalsourceid><addsrcrecordid>eNqNkU1LAzEQhhdRsFZ_gHhZPOhpa743OZbiFygerAdPId2dSOp2U5NtxX9v1hUED-JphuGZd-blzbJjjCYYI3Uxf7yfzSYEITqRWLKS7GQjzLksCGNkN_VIsUKostzPDmJcIoQZU3SUPU9rs-7cFvJ18FsXnW9d-5J7m9fOWgjQds50UOcRwtZVEPMWuncfXmO-MDHNfZsHcK31oYJVovMGTOg1DrM9a5oIR991nD1dXc5nN8Xdw_XtbHpXVFSyrqgNRdggWYoKGxAgqFHYKixLxqG2lVhYiSC9WxImjBSMIEqkXFAmGGc1puPsfNBNBt42EDu9crGCpjEt-E3UCuHkmzCSyLM_SSJVOiPQP0DCEea94ukvcOk3oU12tZSMcKVImSA8QFXwMQaweh3cyoQPjZHuw9Nf4ek-PD2El3ZOhh0HAD88YZQnxU-CupVe</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>884259927</pqid></control><display><type>article</type><title>Adaptive provisioning of differentiated services networks based on reinforcement learning</title><source>IEEE Electronic Library (IEL)</source><creator>Hui, T.C.-K. ; Chen-Khong Tham</creator><creatorcontrib>Hui, T.C.-K. ; Chen-Khong Tham</creatorcontrib><description>The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks has received a lot of attention from researchers. However, most proposed methods need to determine the amount of bandwidth to provision at the time of connection admission. This assumes that traffic in admitted flows always conforms to predefined specifications, which would need some form of traffic shaping or admission control before reaching the ingress of the domain. This paper proposes an adaptive provisioning mechanism based on reinforcement-learning principles, which determines at regular intervals the amount of bandwidth to provision to each PHB aggregate. The mechanism adjusts to maximize the amount of revenue earned from a usage-based pricing model. The novel use of a continuous-space, gradient-based learning algorithm, enables the mechanism to require neither accurate traffic specifications nor rigid admission control. Using ns-2 simulations, we demonstrate using Weighted Fair Queuing, how our mechanism can be implemented in a DiffServ network.</description><identifier>ISSN: 1094-6977</identifier><identifier>ISSN: 2168-2291</identifier><identifier>EISSN: 1558-2442</identifier><identifier>EISSN: 2168-2305</identifier><identifier>DOI: 10.1109/TSMCC.2003.818472</identifier><identifier>CODEN: ITCRFH</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Admission control ; Aggregates ; Bandwidth ; Communication system traffic control ; Delay ; Diffserv networks ; Learning ; Networks ; Provisioning ; Quality of service ; Specifications ; Studies ; Telecommunication traffic ; Traffic control ; Traffic engineering ; Traffic flow</subject><ispartof>IEEE transactions on human-machine systems, 2003-11, Vol.33 (4), p.492-501</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2003</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c384t-da301a0876c1ae6e63a91f918745edfc6bf80e0147246a864203288b346454d13</citedby><cites>FETCH-LOGICAL-c384t-da301a0876c1ae6e63a91f918745edfc6bf80e0147246a864203288b346454d13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1243527$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1243527$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hui, T.C.-K.</creatorcontrib><creatorcontrib>Chen-Khong Tham</creatorcontrib><title>Adaptive provisioning of differentiated services networks based on reinforcement learning</title><title>IEEE transactions on human-machine systems</title><addtitle>TSMCC</addtitle><description>The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks has received a lot of attention from researchers. However, most proposed methods need to determine the amount of bandwidth to provision at the time of connection admission. This assumes that traffic in admitted flows always conforms to predefined specifications, which would need some form of traffic shaping or admission control before reaching the ingress of the domain. This paper proposes an adaptive provisioning mechanism based on reinforcement-learning principles, which determines at regular intervals the amount of bandwidth to provision to each PHB aggregate. The mechanism adjusts to maximize the amount of revenue earned from a usage-based pricing model. The novel use of a continuous-space, gradient-based learning algorithm, enables the mechanism to require neither accurate traffic specifications nor rigid admission control. Using ns-2 simulations, we demonstrate using Weighted Fair Queuing, how our mechanism can be implemented in a DiffServ network.</description><subject>Admission control</subject><subject>Aggregates</subject><subject>Bandwidth</subject><subject>Communication system traffic control</subject><subject>Delay</subject><subject>Diffserv networks</subject><subject>Learning</subject><subject>Networks</subject><subject>Provisioning</subject><subject>Quality of service</subject><subject>Specifications</subject><subject>Studies</subject><subject>Telecommunication traffic</subject><subject>Traffic control</subject><subject>Traffic engineering</subject><subject>Traffic flow</subject><issn>1094-6977</issn><issn>2168-2291</issn><issn>1558-2442</issn><issn>2168-2305</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqNkU1LAzEQhhdRsFZ_gHhZPOhpa743OZbiFygerAdPId2dSOp2U5NtxX9v1hUED-JphuGZd-blzbJjjCYYI3Uxf7yfzSYEITqRWLKS7GQjzLksCGNkN_VIsUKostzPDmJcIoQZU3SUPU9rs-7cFvJ18FsXnW9d-5J7m9fOWgjQds50UOcRwtZVEPMWuncfXmO-MDHNfZsHcK31oYJVovMGTOg1DrM9a5oIR991nD1dXc5nN8Xdw_XtbHpXVFSyrqgNRdggWYoKGxAgqFHYKixLxqG2lVhYiSC9WxImjBSMIEqkXFAmGGc1puPsfNBNBt42EDu9crGCpjEt-E3UCuHkmzCSyLM_SSJVOiPQP0DCEea94ukvcOk3oU12tZSMcKVImSA8QFXwMQaweh3cyoQPjZHuw9Nf4ek-PD2El3ZOhh0HAD88YZQnxU-CupVe</recordid><startdate>20031101</startdate><enddate>20031101</enddate><creator>Hui, T.C.-K.</creator><creator>Chen-Khong Tham</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>H8D</scope><scope>F28</scope></search><sort><creationdate>20031101</creationdate><title>Adaptive provisioning of differentiated services networks based on reinforcement learning</title><author>Hui, T.C.-K. ; Chen-Khong Tham</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c384t-da301a0876c1ae6e63a91f918745edfc6bf80e0147246a864203288b346454d13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Admission control</topic><topic>Aggregates</topic><topic>Bandwidth</topic><topic>Communication system traffic control</topic><topic>Delay</topic><topic>Diffserv networks</topic><topic>Learning</topic><topic>Networks</topic><topic>Provisioning</topic><topic>Quality of service</topic><topic>Specifications</topic><topic>Studies</topic><topic>Telecommunication traffic</topic><topic>Traffic control</topic><topic>Traffic engineering</topic><topic>Traffic flow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hui, T.C.-K.</creatorcontrib><creatorcontrib>Chen-Khong Tham</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Aerospace Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><jtitle>IEEE transactions on human-machine systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hui, T.C.-K.</au><au>Chen-Khong Tham</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adaptive provisioning of differentiated services networks based on reinforcement learning</atitle><jtitle>IEEE transactions on human-machine systems</jtitle><stitle>TSMCC</stitle><date>2003-11-01</date><risdate>2003</risdate><volume>33</volume><issue>4</issue><spage>492</spage><epage>501</epage><pages>492-501</pages><issn>1094-6977</issn><issn>2168-2291</issn><eissn>1558-2442</eissn><eissn>2168-2305</eissn><coden>ITCRFH</coden><abstract>The issue of bandwidth provisioning for Per Hop Behavior (PHB) aggregates in Differentiated Services (DiffServ) networks has received a lot of attention from researchers. However, most proposed methods need to determine the amount of bandwidth to provision at the time of connection admission. This assumes that traffic in admitted flows always conforms to predefined specifications, which would need some form of traffic shaping or admission control before reaching the ingress of the domain. This paper proposes an adaptive provisioning mechanism based on reinforcement-learning principles, which determines at regular intervals the amount of bandwidth to provision to each PHB aggregate. The mechanism adjusts to maximize the amount of revenue earned from a usage-based pricing model. The novel use of a continuous-space, gradient-based learning algorithm, enables the mechanism to require neither accurate traffic specifications nor rigid admission control. Using ns-2 simulations, we demonstrate using Weighted Fair Queuing, how our mechanism can be implemented in a DiffServ network.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TSMCC.2003.818472</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1094-6977 |
| ispartof | IEEE transactions on human-machine systems, 2003-11, Vol.33 (4), p.492-501 |
| issn | 1094-6977 2168-2291 1558-2442 2168-2305 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_28250152 |
| source | IEEE Electronic Library (IEL) |
| subjects | Admission control Aggregates Bandwidth Communication system traffic control Delay Diffserv networks Learning Networks Provisioning Quality of service Specifications Studies Telecommunication traffic Traffic control Traffic engineering Traffic flow |
| title | Adaptive provisioning of differentiated services networks based on reinforcement learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T07%3A47%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Adaptive%20provisioning%20of%20differentiated%20services%20networks%20based%20on%20reinforcement%20learning&rft.jtitle=IEEE%20transactions%20on%20human-machine%20systems&rft.au=Hui,%20T.C.-K.&rft.date=2003-11-01&rft.volume=33&rft.issue=4&rft.spage=492&rft.epage=501&rft.pages=492-501&rft.issn=1094-6977&rft.eissn=1558-2442&rft.coden=ITCRFH&rft_id=info:doi/10.1109/TSMCC.2003.818472&rft_dat=%3Cproquest_RIE%3E28250152%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=884259927&rft_id=info:pmid/&rft_ieee_id=1243527&rfr_iscdi=true |