AWS PredSpotMachine learning for predicting the price of spot instances in AWS cloud

  1. Alejandro Baldominos 1
  2. Yago Saez 1
  3. David Quintana 1
  4. Pedro Isasi 1
  1. 1 Universidad Carlos III de Madrid
    info

    Universidad Carlos III de Madrid

    Madrid, España

    ROR https://ror.org/03ths8210

Revista:
IJIMAI

ISSN: 1989-1660

Año de publicación: 2022

Volumen: 7

Número: 3

Páginas: 65-74

Tipo: Artículo

DOI: 10.9781/IJIMAI.2022.02.003 DIALNET GOOGLE SCHOLAR lock_openDialnet editor

Otras publicaciones en: IJIMAI

Resumen

Elastic 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 study