Current studentsExisting staffContact us
 

On estimating bids for Amazon EC2 spot instances using time series forecasting

Simple item page
dc.contributor.authorChhetri, M.B.
dc.contributor.authorLumpe, M.
dc.contributor.authorVo, Q.B.
dc.contributor.authorKowalczyk, R.
dc.contributor.conference14th IEEE International Conference on Services Computing, SCC 2017 (25 Jun 2017 - 30 Jun 2017 : Honolulu, US)
dc.contributor.editorLiu, X.
dc.contributor.editorBellur, U.
dc.date.issued2017
dc.description.abstractOptimum Bid price estimation is crucial for Amazon Elastic Compute Cloud (EC2) consumers if they want to secure uninterrupted access to Spot instances at reduced costs. We recently reported that Bid price estimation is an implicit function of seasonal components and extreme spikes in the Spot price history. In this paper we apply time series forecasting to further substantiate this claim. In particular, we benchmark a number of standard forecasting techniques including Naive, Seasonal Naive, ARIMA, ETS, STL, and TBATS against Spot markets belonging to different market types based on pricing patterns including the presence of seasonal components, extremes, and trends. We run experiments using different look back and forecast horizons, and evaluate the forecasting techniques using three measures, namely Bid Success Rate (BSR), Bid Price Over/Underestimation (BPO/UE), and Root Mean Squared Error (RMSE). Experimental results confirm that successful estimation of Bid prices in EC2 Spot markets is indeed an implicit function of seasonal components and extreme spikes in the Spot price history. Furthermore, our experiments also indicate that for certain types of markets, it is possible to significantly improve BSR by applying a small correction to the estimated Bid price without causing any major disruptions to the market.
dc.identifier.citation2017 IEEE International Conference On Services Computing (SCC), 2017 / Liu, X., Bellur, U. (ed./s), pp.44-51
dc.identifier.doi10.1109/SCC.2017.14
dc.identifier.isbn9781538620052
dc.identifier.urihttps://hdl.handle.net/11541.2/27478
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers
dc.publisher.placeUS
dc.relation.fundingARC LP150100846
dc.rightsCopyright 2017 IEEE
dc.source.urihttp://dx.doi.org/10.1109/SCC.2017.14
dc.subjecttime series forecasting
dc.subjectAmazon EC2 spot markets
dc.subjectspot price prediction
dc.subjectbid price estimation
dc.titleOn estimating bids for Amazon EC2 spot instances using time series forecasting
dc.typeConference paper
pubs.publication-statusPublished
ror.mmsid9916612649201831

Files

Collections