Show simple item record

dc.contributor.authorLi, J
dc.contributor.authorDeng, Y
dc.contributor.authorZhou, Y
dc.contributor.authorZhang, Z
dc.contributor.authorMin, G
dc.contributor.authorQin, X
dc.date.accessioned2022-05-31T08:04:17Z
dc.date.issued2022-03-16
dc.date.updated2022-05-30T16:05:12Z
dc.description.abstractIncreasing workload conditions lead to a significant surge in power consumption and computing node failures in data centers. Existing workload distribution strategies merely are focused on either thermal awareness or failure mitigation, overlooking the impact of node failures on the energy efficiency of cloud data centers. To address this issue, a holistic model is built to characterize the impacts of workloads, computing and cooling costs, heat recirculation, and node failure on the energy efficiency of cloud data centers. Leveraging such a holistic model, we propose a novel thermal-aware workload distribution strategy called HGSA to take into account node failure, thereby aiming to improve the energy efficiency of cloud data centers. Our empirical findings confirm that (i) faulty nodes lead to a large rise in power consumption, and (ii) failure locations play a vital role in the power consumption of data centers. Experimental results unveil that our HGSA is adroit at making near-optimal decisions in workload distribution strategies. In particular, HGSA cuts down the minimum inlet temperature by 5.2%-15%, improves the maximum air temperature of CRAC by 4.2%-26.5%, lowers the cooling cost by 15.4%-50% compared to the existing solutions. Furthermore, HGSA cuts back the total power consumption by 0.65%-78%.en_GB
dc.description.sponsorshipNational Natural Science Foundation of Chinaen_GB
dc.description.sponsorshipGuangdong Basic and Applied Basic Research Foundationen_GB
dc.description.sponsorshipInternational Cooperation Project of Guangdong Provinceen_GB
dc.description.sponsorshipOpen Project Program of Wuhan National Laboratory for Optoelectronicsen_GB
dc.format.extent1-1
dc.identifier.citationPublished online 16 March 2022en_GB
dc.identifier.doihttps://doi.org/10.1109/tc.2022.3158476
dc.identifier.grantnumber62072214en_GB
dc.identifier.grantnumber2021B1515120048en_GB
dc.identifier.grantnumber2020A0505100040en_GB
dc.identifier.grantnumber2020WNLOKF006en_GB
dc.identifier.urihttp://hdl.handle.net/10871/129783
dc.identifierORCID: 0000-0003-1395-7314 (Min, Geyong)
dc.language.isoenen_GB
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_GB
dc.rights© 2022 IEEEen_GB
dc.subjectData Centersen_GB
dc.subjectPower Consumptionen_GB
dc.subjectNode Failureen_GB
dc.subjectEnergy Efficiencyen_GB
dc.subjectWorkload Distributionen_GB
dc.subjectThermal-Awareen_GB
dc.titleTowards Thermal-Aware Workload Distribution in Cloud Data Centers Based on Failure Modelsen_GB
dc.typeArticleen_GB
dc.date.available2022-05-31T08:04:17Z
dc.identifier.issn0018-9340
dc.descriptionThis is the author accepted manuscript. The final version is available from IEEE via the DOI in this recorden_GB
dc.identifier.eissn1557-9956
dc.identifier.journalIEEE Transactions on Computersen_GB
dc.relation.ispartofIEEE Transactions on Computers, PP(99)
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserveden_GB
rioxxterms.versionAMen_GB
rioxxterms.licenseref.startdate2022-03-16
rioxxterms.typeJournal Article/Reviewen_GB
refterms.dateFCD2022-05-31T08:01:16Z
refterms.versionFCDAM
refterms.dateFOA2022-05-31T08:04:22Z
refterms.panelBen_GB


Files in this item

This item appears in the following Collection(s)

Show simple item record