A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems
Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are...
Gespeichert in:
| Veröffentlicht in: | IEEE communications letters 2018-08, Vol.22 (8), p.1612-1615 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1615 |
|---|---|
| container_issue | 8 |
| container_start_page | 1612 |
| container_title | IEEE communications letters |
| container_volume | 22 |
| creator | Hu, Xin Liu, Shuaijun Chen, Rong Wang, Weidong Wang, Chunting |
| description | Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are not practical due to the high computational complexity. To solve the problem of unknown dynamics and prohibitive computation, a deep reinforcement learning-based framework (DRLF) is proposed for DRA problems in MBS systems. A novel image-like tensor reformulation on the system environments is adopted to extract traffic spatial and temporal features. A use case of dynamic channel allocation in DRLF is simulated and shows the effectiveness of the proposed DRLF in time-varying scenarios. |
| doi_str_mv | 10.1109/LCOMM.2018.2844243 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_8372935</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8372935</ieee_id><sourcerecordid>2117130690</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-c1b70dbdc2b6f61179962582f6136517accd4fb264aeca3b7fe7b1fe484fd6643</originalsourceid><addsrcrecordid>eNo9kEtPwzAQhCMEEqXwB-BiiXOKH3nYx9JSQEpVicLZcpwNckmcYrtC_fe4tOKyO4f5ZleTJLcETwjB4qGarZbLCcWETyjPMpqxs2RE8pynNI7zqDEXaVkKfplceb_BGHOak1HSTdEcYIvewNh2cBp6sAFVoJw19jN9VB4atHCqh5_BfaFoQfO9Vb3REfHDLhJo2nWDVsEMFhmLlrsumBpUj9YqQNeZAGi99wF6f51ctKrzcHPa4-Rj8fQ-e0mr1fPrbFqlmoo8pJrUJW7qRtO6aAtCSiEKmnMaNStyUiqtm6ytaZEp0IrVZQtlTVrIeNY2RZGxcXJ_zN264XsHPshN_NTGk5LGOMJwIXB00aNLu8F7B63cOtMrt5cEy0Or8q9VeWhVnlqN0N0RMgDwD3BWUsFy9gtcWHTK</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2117130690</pqid></control><display><type>article</type><title>A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems</title><source>IEEE Electronic Library (IEL)</source><creator>Hu, Xin ; Liu, Shuaijun ; Chen, Rong ; Wang, Weidong ; Wang, Chunting</creator><creatorcontrib>Hu, Xin ; Liu, Shuaijun ; Chen, Rong ; Wang, Weidong ; Wang, Chunting</creatorcontrib><description>Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are not practical due to the high computational complexity. To solve the problem of unknown dynamics and prohibitive computation, a deep reinforcement learning-based framework (DRLF) is proposed for DRA problems in MBS systems. A novel image-like tensor reformulation on the system environments is adopted to extract traffic spatial and temporal features. A use case of dynamic channel allocation in DRLF is simulated and shows the effectiveness of the proposed DRLF in time-varying scenarios.</description><identifier>ISSN: 1089-7798</identifier><identifier>EISSN: 1558-2558</identifier><identifier>DOI: 10.1109/LCOMM.2018.2844243</identifier><identifier>CODEN: ICLEF6</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Computer simulation ; deep reinforcement learning (DRL) ; Dynamic resource allocation (DRA) ; Dynamic scheduling ; Feature extraction ; Heuristic algorithms ; Iterative methods ; multibeam satellite (MBS) ; Optimization ; Quality of service ; Resource allocation ; Resource management ; Satellites ; state reformulation ; Tensile stress</subject><ispartof>IEEE communications letters, 2018-08, Vol.22 (8), p.1612-1615</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-c1b70dbdc2b6f61179962582f6136517accd4fb264aeca3b7fe7b1fe484fd6643</citedby><cites>FETCH-LOGICAL-c295t-c1b70dbdc2b6f61179962582f6136517accd4fb264aeca3b7fe7b1fe484fd6643</cites><orcidid>0000-0002-5338-5464 ; 0000-0003-0221-8102</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8372935$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8372935$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hu, Xin</creatorcontrib><creatorcontrib>Liu, Shuaijun</creatorcontrib><creatorcontrib>Chen, Rong</creatorcontrib><creatorcontrib>Wang, Weidong</creatorcontrib><creatorcontrib>Wang, Chunting</creatorcontrib><title>A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems</title><title>IEEE communications letters</title><addtitle>COML</addtitle><description>Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are not practical due to the high computational complexity. To solve the problem of unknown dynamics and prohibitive computation, a deep reinforcement learning-based framework (DRLF) is proposed for DRA problems in MBS systems. A novel image-like tensor reformulation on the system environments is adopted to extract traffic spatial and temporal features. A use case of dynamic channel allocation in DRLF is simulated and shows the effectiveness of the proposed DRLF in time-varying scenarios.</description><subject>Computer simulation</subject><subject>deep reinforcement learning (DRL)</subject><subject>Dynamic resource allocation (DRA)</subject><subject>Dynamic scheduling</subject><subject>Feature extraction</subject><subject>Heuristic algorithms</subject><subject>Iterative methods</subject><subject>multibeam satellite (MBS)</subject><subject>Optimization</subject><subject>Quality of service</subject><subject>Resource allocation</subject><subject>Resource management</subject><subject>Satellites</subject><subject>state reformulation</subject><subject>Tensile stress</subject><issn>1089-7798</issn><issn>1558-2558</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kEtPwzAQhCMEEqXwB-BiiXOKH3nYx9JSQEpVicLZcpwNckmcYrtC_fe4tOKyO4f5ZleTJLcETwjB4qGarZbLCcWETyjPMpqxs2RE8pynNI7zqDEXaVkKfplceb_BGHOak1HSTdEcYIvewNh2cBp6sAFVoJw19jN9VB4atHCqh5_BfaFoQfO9Vb3REfHDLhJo2nWDVsEMFhmLlrsumBpUj9YqQNeZAGi99wF6f51ctKrzcHPa4-Rj8fQ-e0mr1fPrbFqlmoo8pJrUJW7qRtO6aAtCSiEKmnMaNStyUiqtm6ytaZEp0IrVZQtlTVrIeNY2RZGxcXJ_zN264XsHPshN_NTGk5LGOMJwIXB00aNLu8F7B63cOtMrt5cEy0Or8q9VeWhVnlqN0N0RMgDwD3BWUsFy9gtcWHTK</recordid><startdate>20180801</startdate><enddate>20180801</enddate><creator>Hu, Xin</creator><creator>Liu, Shuaijun</creator><creator>Chen, Rong</creator><creator>Wang, Weidong</creator><creator>Wang, Chunting</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0002-5338-5464</orcidid><orcidid>https://orcid.org/0000-0003-0221-8102</orcidid></search><sort><creationdate>20180801</creationdate><title>A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems</title><author>Hu, Xin ; Liu, Shuaijun ; Chen, Rong ; Wang, Weidong ; Wang, Chunting</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-c1b70dbdc2b6f61179962582f6136517accd4fb264aeca3b7fe7b1fe484fd6643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer simulation</topic><topic>deep reinforcement learning (DRL)</topic><topic>Dynamic resource allocation (DRA)</topic><topic>Dynamic scheduling</topic><topic>Feature extraction</topic><topic>Heuristic algorithms</topic><topic>Iterative methods</topic><topic>multibeam satellite (MBS)</topic><topic>Optimization</topic><topic>Quality of service</topic><topic>Resource allocation</topic><topic>Resource management</topic><topic>Satellites</topic><topic>state reformulation</topic><topic>Tensile stress</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hu, Xin</creatorcontrib><creatorcontrib>Liu, Shuaijun</creatorcontrib><creatorcontrib>Chen, Rong</creatorcontrib><creatorcontrib>Wang, Weidong</creatorcontrib><creatorcontrib>Wang, Chunting</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE communications letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hu, Xin</au><au>Liu, Shuaijun</au><au>Chen, Rong</au><au>Wang, Weidong</au><au>Wang, Chunting</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems</atitle><jtitle>IEEE communications letters</jtitle><stitle>COML</stitle><date>2018-08-01</date><risdate>2018</risdate><volume>22</volume><issue>8</issue><spage>1612</spage><epage>1615</epage><pages>1612-1615</pages><issn>1089-7798</issn><eissn>1558-2558</eissn><coden>ICLEF6</coden><abstract>Dynamic resource allocation (DRA) is the key technology to improve the network performance in resource-limited multibeam satellite (MBS) systems. The aim is to find a policy that maximizes the expected long-term resource utilization. Existing iterative metaheuristics DRA optimization algorithms are not practical due to the high computational complexity. To solve the problem of unknown dynamics and prohibitive computation, a deep reinforcement learning-based framework (DRLF) is proposed for DRA problems in MBS systems. A novel image-like tensor reformulation on the system environments is adopted to extract traffic spatial and temporal features. A use case of dynamic channel allocation in DRLF is simulated and shows the effectiveness of the proposed DRLF in time-varying scenarios.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LCOMM.2018.2844243</doi><tpages>4</tpages><orcidid>https://orcid.org/0000-0002-5338-5464</orcidid><orcidid>https://orcid.org/0000-0003-0221-8102</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1089-7798 |
| ispartof | IEEE communications letters, 2018-08, Vol.22 (8), p.1612-1615 |
| issn | 1089-7798 1558-2558 |
| language | eng |
| recordid | cdi_ieee_primary_8372935 |
| source | IEEE Electronic Library (IEL) |
| subjects | Computer simulation deep reinforcement learning (DRL) Dynamic resource allocation (DRA) Dynamic scheduling Feature extraction Heuristic algorithms Iterative methods multibeam satellite (MBS) Optimization Quality of service Resource allocation Resource management Satellites state reformulation Tensile stress |
| title | A Deep Reinforcement Learning-Based Framework for Dynamic Resource Allocation in Multibeam Satellite Systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T04%3A47%3A53IST&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=A%20Deep%20Reinforcement%20Learning-Based%20Framework%20for%20Dynamic%20Resource%20Allocation%20in%20Multibeam%20Satellite%20Systems&rft.jtitle=IEEE%20communications%20letters&rft.au=Hu,%20Xin&rft.date=2018-08-01&rft.volume=22&rft.issue=8&rft.spage=1612&rft.epage=1615&rft.pages=1612-1615&rft.issn=1089-7798&rft.eissn=1558-2558&rft.coden=ICLEF6&rft_id=info:doi/10.1109/LCOMM.2018.2844243&rft_dat=%3Cproquest_RIE%3E2117130690%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=2117130690&rft_id=info:pmid/&rft_ieee_id=8372935&rfr_iscdi=true |