SOC Dynamic Power Management Using Artificial Neural Network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We propo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lu, Huaxiang, Lu, Yan, Tang, Zhifang, Wang, Shoujue
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Algorithmics. Computability. Computer arithmetics Applied sciences Artificial Neural Network Back Propagation Network Computer science control theory systems Exact sciences and technology Idle Period Idle Time Power Management Theoretical computing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	564
container_issue
container_start_page	555
container_title
container_volume
creator	Lu, Huaxiang Lu, Yan Tang, Zhifang Wang, Shoujue
description	Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques — BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.
doi_str_mv	10.1007/11881070_76
format	Conference Proceeding
fullrecord	<record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_19970771</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>19970771</sourcerecordid><originalsourceid>FETCH-LOGICAL-p219t-4b43c6cbf49d7cf719a7131bcf9a126066b69847cc62f62da14c6b17ec6eaecd3</originalsourceid><addsrcrecordid>eNpVkL1OwzAYRc2fRFUy8QJZGBgC32e7diyxVOVXKhQJOluOY1emaVLZQVXfnkIZ4C53OFdnuIScI1whgLxGLEsECVqKA5IpWbIRBz5SQMUhGaBALBjj6ugfQ3VMBsCAFkpydkqylD5gF4YCqByQm7fZJL_dtmYVbP7abVzMn01rFm7l2j6fp9Au8nHsgw82mCZ_cZ_xp_pNF5dn5MSbJrnst4dkfn_3PnksprOHp8l4Wqwpqr7gFWdW2MpzVUvrJSojkWFlvTJIBQhRCVVyaa2gXtDaILeiQumscMbZmg3Jxd67NsmaxkfT2pD0OoaViVuNSkmQO-WQXO53aYfahYu66rpl0gj6-0H950H2BVMoXHU</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>SOC Dynamic Power Management Using Artificial Neural Network</title><source>Springer Books</source><creator>Lu, Huaxiang ; Lu, Yan ; Tang, Zhifang ; Wang, Shoujue</creator><contributor>Wu, Feng ; Liu, Jing ; Wang, Lipo ; Gao, Xin-bo ; Jiao, Licheng</contributor><creatorcontrib>Lu, Huaxiang ; Lu, Yan ; Tang, Zhifang ; Wang, Shoujue ; Wu, Feng ; Liu, Jing ; Wang, Lipo ; Gao, Xin-bo ; Jiao, Licheng</creatorcontrib><description>Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques — BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540459019</identifier><identifier>ISBN: 3540459014</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540459026</identifier><identifier>EISBN: 3540459022</identifier><identifier>DOI: 10.1007/11881070_76</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Algorithmics. Computability. Computer arithmetics ; Applied sciences ; Artificial Neural Network ; Back Propagation Network ; Computer science; control theory; systems ; Exact sciences and technology ; Idle Period ; Idle Time ; Power Management ; Theoretical computing</subject><ispartof>Advances in Natural Computation, 2006, p.555-564</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2008 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11881070_76$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11881070_76$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,775,776,780,785,786,789,4036,4037,27902,38232,41418,42487</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=19970771$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Wu, Feng</contributor><contributor>Liu, Jing</contributor><contributor>Wang, Lipo</contributor><contributor>Gao, Xin-bo</contributor><contributor>Jiao, Licheng</contributor><creatorcontrib>Lu, Huaxiang</creatorcontrib><creatorcontrib>Lu, Yan</creatorcontrib><creatorcontrib>Tang, Zhifang</creatorcontrib><creatorcontrib>Wang, Shoujue</creatorcontrib><title>SOC Dynamic Power Management Using Artificial Neural Network</title><title>Advances in Natural Computation</title><description>Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques — BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.</description><subject>Algorithmics. Computability. Computer arithmetics</subject><subject>Applied sciences</subject><subject>Artificial Neural Network</subject><subject>Back Propagation Network</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><subject>Idle Period</subject><subject>Idle Time</subject><subject>Power Management</subject><subject>Theoretical computing</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540459019</isbn><isbn>3540459014</isbn><isbn>9783540459026</isbn><isbn>3540459022</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpVkL1OwzAYRc2fRFUy8QJZGBgC32e7diyxVOVXKhQJOluOY1emaVLZQVXfnkIZ4C53OFdnuIScI1whgLxGLEsECVqKA5IpWbIRBz5SQMUhGaBALBjj6ugfQ3VMBsCAFkpydkqylD5gF4YCqByQm7fZJL_dtmYVbP7abVzMn01rFm7l2j6fp9Au8nHsgw82mCZ_cZ_xp_pNF5dn5MSbJrnst4dkfn_3PnksprOHp8l4Wqwpqr7gFWdW2MpzVUvrJSojkWFlvTJIBQhRCVVyaa2gXtDaILeiQumscMbZmg3Jxd67NsmaxkfT2pD0OoaViVuNSkmQO-WQXO53aYfahYu66rpl0gj6-0H950H2BVMoXHU</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Lu, Huaxiang</creator><creator>Lu, Yan</creator><creator>Tang, Zhifang</creator><creator>Wang, Shoujue</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2006</creationdate><title>SOC Dynamic Power Management Using Artificial Neural Network</title><author>Lu, Huaxiang ; Lu, Yan ; Tang, Zhifang ; Wang, Shoujue</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p219t-4b43c6cbf49d7cf719a7131bcf9a126066b69847cc62f62da14c6b17ec6eaecd3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Algorithmics. Computability. Computer arithmetics</topic><topic>Applied sciences</topic><topic>Artificial Neural Network</topic><topic>Back Propagation Network</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><topic>Idle Period</topic><topic>Idle Time</topic><topic>Power Management</topic><topic>Theoretical computing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lu, Huaxiang</creatorcontrib><creatorcontrib>Lu, Yan</creatorcontrib><creatorcontrib>Tang, Zhifang</creatorcontrib><creatorcontrib>Wang, Shoujue</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lu, Huaxiang</au><au>Lu, Yan</au><au>Tang, Zhifang</au><au>Wang, Shoujue</au><au>Wu, Feng</au><au>Liu, Jing</au><au>Wang, Lipo</au><au>Gao, Xin-bo</au><au>Jiao, Licheng</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>SOC Dynamic Power Management Using Artificial Neural Network</atitle><btitle>Advances in Natural Computation</btitle><date>2006</date><risdate>2006</risdate><spage>555</spage><epage>564</epage><pages>555-564</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540459019</isbn><isbn>3540459014</isbn><eisbn>9783540459026</eisbn><eisbn>3540459022</eisbn><abstract>Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques — BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11881070_76</doi><tpages>10</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 0302-9743
ispartof	Advances in Natural Computation, 2006, p.555-564
issn	0302-9743 1611-3349
language	eng
recordid	cdi_pascalfrancis_primary_19970771
source	Springer Books
subjects	Algorithmics. Computability. Computer arithmetics Applied sciences Artificial Neural Network Back Propagation Network Computer science control theory systems Exact sciences and technology Idle Period Idle Time Power Management Theoretical computing
title	SOC Dynamic Power Management Using Artificial Neural Network
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T22%3A49%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=SOC%20Dynamic%20Power%20Management%20Using%20Artificial%20Neural%20Network&rft.btitle=Advances%20in%20Natural%20Computation&rft.au=Lu,%20Huaxiang&rft.date=2006&rft.spage=555&rft.epage=564&rft.pages=555-564&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540459019&rft.isbn_list=3540459014&rft_id=info:doi/10.1007/11881070_76&rft_dat=%3Cpascalfrancis_sprin%3E19970771%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540459026&rft.eisbn_list=3540459022&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true