Publication:
AWS PredSpot: Machine Learning for Predicting the Price of Spot Instances in AWS Cloud

Simple item page
dc.contributor.authorBaldominos Gomez, Alejandro
dc.contributor.authorBaldominos Gómez, Alejandro
dc.contributor.authorSáez Achaerandio, Yago
dc.contributor.authorQuintana, David
dc.contributor.authorIsasi, Pedro
dc.contributor.funderComunidad de Madrides
dc.contributor.funderUniversidad Carlos III de Madrides
dc.date.accessioned2023-11-10T09:05:59Z
dc.date.available2023-11-10T09:05:59Z
dc.date.issued2022-01-01
dc.description.abstractElastic Cloud Compute (EC2) is one of the most well-known services provided by Amazon for provisioning cloud computing resources, also known as instances. Besides the classical on-demand scheme, where users purchase compute capacity at a fixed cost, EC2 supports so-called spot instances, which are offered following a bidding scheme, where users can save up to 90% of the cost of the on-demand instance. EC2 spot instances can be a useful alternative for attaining an important reduction in infrastructure cost, but designing bidding policies can be a difficult task, since bidding under their cost will either prevent users from provisioning instances or losing those that they already own. Towards this extent, accurate forecasting of spot instance prices can be of an outstanding interest for designing working bidding policies. In this paper, we propose the use of different machine learning techniques to estimate the future price of EC2 spot instances. These include linear, ridge and lasso regressions, multilayer perceptrons, K-nearest neighbors, extra trees and random forests. The obtained performance varies significantly between instances types, and root mean squared errors ranges between values very close to zero up to values over 60 in some of the most expensive instances. Still, we can see that for most of the instances, forecasting performance is remarkably good, encouraging further research in this field of studyen
dc.description.sponsorshipThis work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M in the line of Excellence of University Professors (EPUC3MXX), and in the context of the V PRICIT (Regional Programme of Research and Technological Innovation).en
dc.identifier.bibliographicCitationBaldominos, A., Saez, Y., Quintana, D., Isasi, P. (2022). AWS PredSpot: Machine Learning for Predicting the Price of Spot Instances in AWS Cloud. International Journal of Interactive Multimedia and Artificial Intelligence, 7 (3), 65-74en
dc.identifier.doihttp://dx.doi.org/10.9781/ijimai.2022.02.003
dc.identifier.issn1989-1660
dc.identifier.publicationfirstpage65
dc.identifier.publicationissue3
dc.identifier.publicationlastpage74
dc.identifier.publicationtitleInternational Journal of Interactive Multimedia and Artificial Intelligenceen
dc.identifier.publicationvolume7
dc.identifier.urihttps://hdl.handle.net/10016/38820
dc.identifier.uxxiAR/0000032647
dc.language.isoeng
dc.publisherUNIR La Universidad en Internetes
dc.rights© UNIR, 2022
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.ecienciaInformáticaes
dc.subject.ecienciaRobótica e Informática Industriales
dc.subject.othercloud computingen
dc.subject.othermachine learningen
dc.subject.otherpredictionen
dc.subject.otherprice forecastigen
dc.titleAWS PredSpot: Machine Learning for Predicting the Price of Spot Instances in AWS Clouden
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
AWS_IJIMAI_2022.pdf
Size:
2.8 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
DI - GCERN - Artículos de revistas científicas