ICT as Key Technology against Global Warming: Second International Conference, ICT-GLOW 2012, Vienna, Austria, September 6, 2012. Proceedings PDF
Preview ICT as Key Technology against Global Warming: Second International Conference, ICT-GLOW 2012, Vienna, Austria, September 6, 2012. Proceedings
Lecture Notes in Computer Science 7453 CommencedPublicationin1973 FoundingandFormerSeriesEditors: GerhardGoos,JurisHartmanis,andJanvanLeeuwen EditorialBoard DavidHutchison LancasterUniversity,UK TakeoKanade CarnegieMellonUniversity,Pittsburgh,PA,USA JosefKittler UniversityofSurrey,Guildford,UK JonM.Kleinberg CornellUniversity,Ithaca,NY,USA AlfredKobsa UniversityofCalifornia,Irvine,CA,USA FriedemannMattern ETHZurich,Switzerland JohnC.Mitchell StanfordUniversity,CA,USA MoniNaor WeizmannInstituteofScience,Rehovot,Israel OscarNierstrasz UniversityofBern,Switzerland C.PanduRangan IndianInstituteofTechnology,Madras,India BernhardSteffen TUDortmundUniversity,Germany MadhuSudan MicrosoftResearch,Cambridge,MA,USA DemetriTerzopoulos UniversityofCalifornia,LosAngeles,CA,USA DougTygar UniversityofCalifornia,Berkeley,CA,USA GerhardWeikum MaxPlanckInstituteforInformatics,Saarbruecken,Germany Axel Auweter Dieter Kranzlmüller Amirreza Tahamtan A Min Tjoa (Eds.) ICT as Key Technology against Global Warming Second International Conference, ICT-GLOW 2012 Vienna,Austria, September 6, 2012 Proceedings 1 3 VolumeEditors AxelAuweter LeibnizSupercomputingCentre(LRZ) BavarianAcademyofSciencesandHumanities Boltzmannstr.1,85748,Garching/Munich,Germany E-mail:[email protected] DieterKranzlmüller Ludwig-Maximilians-UniversitätMünchen MNM-Team Oettingenstr.67,80538Munich,Germany E-mail:kranzlmueller@ifi.lmu.de AmirrezaTahamtan AMinTjoa ViennaUniversityofTechnology InstituteofSoftwareTechnology&InteractiveSystems Favoritenstr.9-11/188,1040Vienna,Austria E-mail:{tahamtan,amin}@ifs.tuwien.ac.at ISSN0302-9743 e-ISSN1611-3349 ISBN978-3-642-32605-9 e-ISBN978-3-642-32606-6 DOI10.1007/978-3-642-32606-6 SpringerHeidelbergDordrechtLondonNewYork LibraryofCongressControlNumber:2012943989 CRSubjectClassification(1998):D,J.2,J.1,K.6,H.5 LNCSSublibrary:SL1–TheoreticalComputerScienceandGeneralIssues ©Springer-VerlagBerlinHeidelberg2012 Thisworkissubjecttocopyright.Allrightsarereserved,whetherthewholeorpartofthematerialis concerned,specificallytherightsoftranslation,reprinting,re-useofillustrations,recitation,broadcasting, reproductiononmicrofilmsorinanyotherway,andstorageindatabanks.Duplicationofthispublication orpartsthereofispermittedonlyundertheprovisionsoftheGermanCopyrightLawofSeptember9,1965, initscurrentversion,andpermissionforusemustalwaysbeobtainedfromSpringer.Violationsareliable toprosecutionundertheGermanCopyrightLaw. Theuseofgeneraldescriptivenames,registerednames,trademarks,etc.inthispublicationdoesnotimply, evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevantprotectivelaws andregulationsandthereforefreeforgeneraluse. Typesetting:Camera-readybyauthor,dataconversionbyScientificPublishingServices,Chennai,India Printedonacid-freepaper SpringerispartofSpringerScience+BusinessMedia(www.springer.com) Preface In 2010, a record 30.6 gigatons of carbon dioxide poured into the atmosphere, thehighestcarbonoutputinhistory.Preventingatemperatureriseisthebiggest challengeofourtime.TheICTsectorisarelevantcontributortogreenhousegas emissions and global warming due to its tremendous presence in our everyday life, but it is also a key technology for the fight against global warming in all other sectors. Consequently, reduction of CO2 emissions in ICT and with the support of ICT is a topic of outmost importance for society and our planet. The Second International Conference on ICT as a Key Technology Against GlobalWarming(ICT-GLOW2012)aimedatprovidinganinterdisciplinarysci- entificforumforin-depthdiscussionsonthe reductionofthecarbonfootprintin thedifferentsectorsincludingICTsystemsthemselves.EmphasiswithintheICT sector is laid on holistic and far-reaching approaches for green and eco-friendly solutions. The conference aims to bring together researchers and practitioners from multiple disciplines ranging from green maturity models in organizations to system level design and optimization. Thepaperspresentedatthis conferencewereselectedafterextensivereviews bytheProgramCommitteeandassociatedreviewers.Wewouldliketothankall Program Committee members and the reviewers for their valuable advice, and the authors for their contributions to ICT-GLOW 2012. Special thanks go to Gabriela Wagner for managing the submission and paper production process. September 2012 A Min Tjoa Dieter Kranzlmu¨ller Amirreza“Nick”Tahamtan Axel Auweter Organization General Chairs A Min Tjoa Vienna University of Technology, Austria Dieter Kranzlmu¨ller Ludwig-Maximilians-Universit¨atand Leibniz Supercomputing Centre, Germany Program Committee Co-chairs Amirreza“Nick”Tahamtan Vienna University of Technology, Austria Axel Auweter Leibniz Supercomputing Centre, Germany Program Committee Gul Agha University of Illinois at Urbana-Champaign, USA Ishfaq Ahmad University of Texas Arlington, USA Lachlan Andrew SwineburneUniversityofTechnology,Australia Cosimo Anglano Universita` del Piemonte Orientale, Italy Axel Auweter Leibniz Supercomputing Centre, Germany Rami Bahsoon The University of Birmingham, UK Riccardo Bettati Texas A&M University, USA Nguyen Thanh Binh International Institute for Applied Systems Analysis, Austria Davide Careglio Universitat Polit`ecnica de Catalunya, Spain Jian-Jia Chen Karlsruhe Institute of Technology,Germany Ayse Kivilcim Coskun Boston University, USA Georges Da Costa Universit´e Paul Sabatier, France Marco Di Girolamo HP Italy Innovation Centre, Italy Dominique Dudkowski NEC Laboratories Europe, Germany Carla Ellis Duke University, USA Karl Fu¨rlinger Ludwig-Maximilians-Universit¨at,Germany Erol Gelenbe Imperial College, UK Aditya Ghose University of Wollongong,Australia Keishiro Hara Osaka University, Japan Helmut Hlavacs University of Vienna, Austria Chun-Hsi Huang University of Connecticut, USA Karin Anna Hummel University of Vienna, Austria Omar Hussain Curtin University, Australia Vipul Jain Indian Institute of Technology Delhi, India Bahman Javadi The University of Melbourne, Australia VIII Organization Dahe Jiang Tongji University, China Samee u. Khan North Dakota State University, USA Harald Kosch Universit¨at Passau, Germany Dieter Kranzlmu¨ller Ludwig-Maximilians-Universit¨atand Leibniz Supercomputing Centre, Germany Laurent Lefevre The FrenchInstitute forResearchinComputer Science, France Thomas Ledoux l’E´cole des Mines de Nantes, France Jaime Lloret Mauri Universidad Polit`ecnica de Val`encia, Spain Yung-Hsiang Lu Purdue University, USA Thomas Ludwig Deutsches Klimarechenzentrum,Germany Made Mahendra Udayana University, Indonesia Michele Mazzucco University of Tartu, Estonia Jean-Marc Menaud l’E´cole des Mines de Nantes, France Daniel Mosse University of Pittsburgh, USA Hiroyuki Morikawa The University of Tokyo, Japan Binh Nguyen International Institute for Applied Systems Analysis, Austria Tjokorda Gde Tirta Nindhia Udayana University, Indonesia Manish Parashar Rutgers University, USA Barbara Pernici Politecnico di Milano, Italy Cathryn Peoples University of Ulster, UK Mario Pickavet Universiteit Gent, Belgium Jean-Marc Pierson Paul Sabatier University, France Wojciech Piotrowicz University of Oxford, UK Gang Qu University of Maryland, USA Toshinori Sato Fukuoka University, Japan Edwin Sha University of Texas at Dallas, USA Erich Schikuta University of Vienna, Austria Amirreza“Nick”Tahamtan Vienna University of Technology, Austria Domenico Talia Universit`a della Calabria, Italy A Min Tjoa Vienna University of Technology, Austria Jordi Torres Technical University of Catalonia, Spain Frank Teuteberg Universit¨at Osnabru¨ck, Germany Gregg Vesonder AT&T Labs, USA Vladimir Vlassov Royal Institute of Technology, Sweden Martijn Warnier TU Delft, The Netherlands Rongbo Zhu South-Central University for Nationalities, China Albert Zomaya University of Sydney, Australia Table of Contents Novel Implementations for Energy Awareness IT-Cooling Collaborative Control Methods for Battery-Aware IT-Systems Targeting India ....................................... 1 Tadayuki Matsumura and Tetsuya Yamada Research for IT Driven Energy Efficiency Based on a Multidimensional Comfort Control ................................................. 18 Afef Denguir, Franc¸ois Trousset, and Jacky Montmain The ECOSGreenBuildings Project:Data Dramatization,Visualization and Manipulation................................................ 33 Deb Polson and Cassandra Selin Green Data Centers and Supercomputing Case Studies of Multi-core Energy Efficiency in Task Based Programs ....................................................... 44 Hallgeir Lien, Lasse Natvig, Abdullah Al Hasib, and Jan Christian Meyer Leveraging Task-Parallelismin Energy-EfficientILU Preconditioners ... 55 Jos´e I. Aliaga, Manuel F. Dolz, Alberto F. Mart´ın, Rafael Mayo, and Enrique S. Quintana-Ort´ı Evaluating Energy Consumption in CDN Servers..................... 64 Saif ul Islam and Jean-Marc Pierson Green Organization and Business Modelling Green Performance Indicators Aggregation through Composed Weighting System................................................ 79 Alexandre Mello Ferreira, Barbara Pernici, and Pierluigi Plebani EC4MACS – An Integrated Assessment Toolbox of Well-Established Modeling Tools to Explore the Synergies and Interactions between Climate Change, Air Quality and Other Policy Objectives............. 94 Thanh Binh Nguyen, Fabian Wagner, and Wolfgang Schoepp X Table of Contents Semantic Modelling of Dependency Relations between Life Cycle Analysis Processes ............................................... 109 Benjamin Bertin, Marian Scuturici, Jean-Marie Pinon, and Emmanuel Risler Author Index.................................................. 125 IT-Cooling Collaborative Control Methods for Battery-Aware IT-Systems Targeting India Tadayuki Matsumura and Tetsuya Yamada Central Research Laboratory, Hitachi Ltd. 1-280, Higashi-koigakubo, Kokubunji-shi,Tokyo,Japan {tadayuki.matsumura.bh,tetsuya.yamada.jh}@hitachi.com Abstract. Two IT-system control methods, which realize efficient bat- teryusageforbattery-poweredITsystemstargetingdevelopingcountries suchasIndia,areproposed.TheproposedmethodscontroltheITequip- mentandcoolingpowercollaborativelyonthebasisofaforecastofpower outage duration. To quantitatively evaluate these methods, power out- ages in Bangalore, India, were measured. The proposed methods were evaluated by using this measured power outage data. According to the evaluation results,theproposedmethodscan improveameasureofbat- tery efficiency, namely, IT-used-energy (Q )/battery-used-energy (Q ), t u by 39% compared to that of conventional ITsystems. 1 Introduction AsIT-systemmarketsindevelopedcountriesgrowandmature,thoseofdevelop- ing countries are becoming more important. Among such developing countries, India is one of the most promising. Specially, IT systems targeting small and medium sized business (SMB) markets are becoming more important because thatmarketisincreasinginIndia.InIndia,ITsystemsforsuchSMBsarenotso differentfromthoseofdevelopedcountries.However,thereisonecleardifference in terms ofthe power supply equipment used, thatis, use of anon-line-type un- interruptible power supply (UPS) and its add-on large capacity batteries. This state of affairs is due to poor power quality in India, where power supply prob- lems such as surges, dips, interruptions and long duration power outages are frequent. Surges, dips and interruptions can be solved by installing on-line-type UPS,whichsuppliespowerindirectlythroughbatteries.Similarly,longduration power outages can be solved by installing large capacity batteries. In general, thelead-acidbatteryisusedforUPS.This,however,posesaproblembecauseof its largeareaandheavyweight.Forexample, tocoveratwohourpoweroutage, batteriesweighingabout600kgareneededfor4-kWclassIT-systems.Moreover, a special floor construction is needed to support such a heavy weight. In light of the above described circumstances, it can be said that there is uniqueandnovelresearchareaforITsystemstargetingIndia,thatis,developing a battery-aware IT system. In the mobile systems field, battery-aware systems have been commonly researched, and there are a lot of related works [1]-[5]. These previous works mainly apply some optimization process before system A.Auweteretal.(Eds.):ICT-GLOW2012,LNCS7453,pp.1–17,2012. (cid:2)c Springer-VerlagBerlinHeidelberg2012 2 T. Matsumura and T. Yamada runtime. Such optimization is feasible because the task set and the timing of the task input of an embedded system are known in the system design phase. In the case of server applications other than embedded systems, however, the task set is not known at the system design phase. Moreover, task input timing depends on the server user. Because of these reasons, it is difficult to apply an optimization process for server applications in advance of the runtime. In response to the above described issues, the authors propose two runtime dynamicIT-systemcontrolmethodsbasedonforecasting.Theproposedmethods make power control guidelines on the basis of a power outage duration forecast andIT-loadforecast.TheITsystemandcoolerpoweraredynamicallycontrolled collaboratively at runtime. According to the forecast, the IT system can be cooled in advance. The power outage forecast and advanced cooling are the novelties concerning the proposed method. To the authors’ knowledge, there have been no papers about power outage duration forecasting and utilizing the forecast for advanced cooling of battery-awareIT systems. 2 Related Works In the mobile-application field, design of battery-aware systems has been well researchedsincebatterycapacityisstrictlyrestricted[1,2].Amongsuchprevious researchworks, task scheduling and dynamic voltage scheduling (DVS) are well known [3,4]. It is known that due to a battery feature called the rate capacity effect, the power-consumption profile of a battery can affect battery efficiency even if total energy consumption is the same. These previous works aim to optimize the power profile by controlling the voltage or task-execution order so as to maximize battery efficiency. The rate capacity effect is more significant in the case of the lead-acid battery used in current UPSs than in the case of the lithium-ion battery used in mobile systems. These previous works can therefore also be expected to be more effective for IT systems than for mobile systems. In the meantime, unlike designers of embedded systems (such as mobile ap- plications), designers of IT systems do not know task sets at the system design time. Moreover,taskinputtimingdepends onthe user.Asaresult,itisdifficult to schedule an IT-system task in advance. Given that difficultly, in the current work, two runtime dynamic IT-system power-controltechniques, based on fore- casting instead of in-advance scheduling, are proposed. With these techniques, power-outage duration is forecasted by analyzing power-outage history statisti- cally. In the field of mobile applications, a battery-awaretechnique that utilizes forecastinghasalsobeenproposed[5]. Withthis technique,thetimetothe next chargingopportunityisforecastedbyanalyzingusagehistorystatistically.Meth- ods for forecasting IT load have also been reported [6,7]. Forecasting of power- outageoccurrencesisalsopossible,andsummaryofpower-outagepredictionhas been published [8]. However, to the authors’ knowledge, power-outage-duration forecasting has not yet been reported.
The list of books you might like
