|
|
Digital
Library of the European Council for Modelling and Simulation |
|
Title: |
AWS EC2 Spot Instances
For Mission Critical Services |
|
Authors: |
Jerry
Danysz, Victor del Rosal,
Horacio Gonzalez-Velez |
|
Published in:
|
2020). ECMS 2020 Proceedings
Edited by: Mike Steglich, Christian Muller, Gaby
Neumann, Mathias Walther, European Council for Modeling and Simulation. DOI: http://doi.org/10.7148/2020 ISSN:
2522-2422 (ONLINE) ISSN:
2522-2414 (PRINT) ISSN:
2522-2430 (CD-ROM) ISBN: 978-3-937436-68-5 Communications of the ECMS , Volume 34, Issue 1, June 2020, United Kingdom |
|
Citation
format: |
Jerry Danysz,
Victor del Rosal, Horacio
Gonzalez-Velez (2020). AWS EC2 Spot Instances For Mission Critical Services, ECMS 2020 Proceedings Edited By: Mike Steglich, Christian Mueller, Gaby Neumann, Mathias
Walther European Council for Modeling and Simulation. doi: 10.7148/2020-0376 |
|
DOI: |
https://doi.org/10.7148/2020-0376 |
|
Abstract: |
For over a
decade now, Amazon Web Services (AWS) has offered its spare capacity at a
discounted price in the form of EC2 spot instances. This discount comes at
the price of variable pricing and sudden instance termination. In this paper,
we present a machine-learning solution to one of the challenges when using
AWS Spot Instances, namely the termination of the instance on short notice.
Our system, Spot Instance Management System (SimS),
can effectively manage spot instances and keep up the availability at the
desired level using 100-tree Random Forest Regression model. By using a risk
assessment mechanism and proactive actions, SimS
assures a three-nines SLA using AWS spot instances with lower running costs
on workloads for a major European financial institution. |
|
Full
text: |
|
