Bayesian uncertainty modelling for cloud workload prediction

Simple item page
dc.contributor.authorRossi, Andrea
dc.contributor.authorVisentin, Andrea
dc.contributor.authorPrestwich, Steven D.
dc.contributor.authorBrown, Kenneth N.
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.contributor.funderHorizon 2020 Framework Programmeen
dc.contributor.funderHorizon 2020en
dc.contributor.funderGoogleen
dc.date.accessioned2022-07-27T13:38:08Z
dc.date.available2022-07-27T13:38:08Z
dc.date.issued2022-07-10
dc.date.updated2022-07-27T13:21:43Z
dc.description.abstractProviders of cloud computing systems need to manage resources carefully to meet the desired Quality of Service and reduce waste due to overallocation. An accurate prediction of future demand is crucial to allocate resources to service requests without excessive delays. Current state-of-the-art methods such as Long Short-Term Memory-based models make only point forecasts of demand without considering the uncertainty in their predictions. Forecasting a distribution would provide a more comprehensive picture and inform resource scheduler decisions. We investigate Bayesian Neural Networks and deep learning models to predict workload distribution and evaluate them on the time series forecasting of CPU and memory workload of 8 clusters on the Google Cloud data centre. Experiments show that the proposed models provide accurate demand prediction and better estimations of resource usage bounds, reducing overprediction and total predicted resources, while avoiding underprediction. These approaches have good runtime performance making them applicable for practitioners.en
dc.description.sponsorshipScience Foundation Ireland (Grant Nos. 18/CRT/6223, 16/RC/3918 and 12/RC/2289-P2, co-funded under the European Regional Development Fund); EU Horizon 2020 (TAILOR (GA No. 952215)); Google (Google Cloud Research Credits program, award GCP203677602))en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRossi, A., Visentin, A., Prestwich, S. D. and Brown, K. N. (2022) 'Bayesian Uncertainty Modelling for Cloud Workload Prediction', 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), Barcelona, Spain, 10-16 July. doi: 10.1109/CLOUD55607.2022.00018en
dc.identifier.doi10.1109/CLOUD55607.2022.00018
dc.identifier.endpage11en
dc.identifier.isbn978-1-6654-8137-3
dc.identifier.isbn978-1-6654-8138-0
dc.identifier.issn2159-6190
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/13411
dc.language.isoenen
dc.publisherIEEEen
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/952215/EU/Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization/TAILORen
dc.relation.urihttps://doi.org/10.1109/CLOUD55607.2022.00018
dc.rightsFor the purpose of Open Access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. Copyright Published version of record: © 2022 IEEEen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectCloud Computingen
dc.subjectBayesian Neural Networken
dc.subjectWorkload Predictionen
dc.subjectDeep Learningen
dc.subjectTime Series Forecastingen
dc.titleBayesian uncertainty modelling for cloud workload predictionen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bayesian_Uncertainty_Modelling_for_Cloud_Workload_Prediction.pdf
Size:
2.61 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items
Insight Centre for Data Analytics - Conference Items