Improving Cloud Simulation using the Monte-Carlo Method - Archive ouverte HAL Access content directly
Book Sections Year : 2018

Improving Cloud Simulation using the Monte-Carlo Method

Abstract

In the cloud computing model, cloud providers invoice clients for resource consumption. Hence, tools helping the client to budget the cost of running his application are of pre-eminent importance. However, the opaque and multi-tenant nature of clouds make task runtimes variable and hard to predict, and hamper the creation of reliable simulation tools. In this paper, we propose an improved simulation framework that takes into account this variability using the Monte-Carlo method. We consider the execution of batch jobs on an actual platform, scheduled using typical heuristics based on the user estimates of task runtimes. We model the observed variability through simple random variables to use as inputs to the Monte-Carlo simulation. Based on this stochastic process, predictions are expressed as interval-based makespan and cost. We show that, our method can capture over 90% of the empirical observations of makespan while keeping the capture interval size below 5% of the average makespan.
Fichier principal
Vignette du fichier
montecarlo-simulation-euro.pdf (342.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02161784 , version 1 (21-06-2019)

Identifiers

  • HAL Id : hal-02161784 , version 1

Cite

Luke Bertot, Stéphane Genaud, Julien Gossa. Improving Cloud Simulation using the Monte-Carlo Method. Euro-Par 2018: Parallel Processing, 11014, pp.404-416, 2018. ⟨hal-02161784⟩
94 View
450 Download

Share

Gmail Facebook X LinkedIn More