Machine learning applied to accelerate energy consumption models in computing simulators Articles uri icon

publication date

  • July 2020

start page

  • 102012 -1

end page

  • 102012-16


  • 102

International Standard Serial Number (ISSN)

  • 1569-190X

Electronic International Standard Serial Number (EISSN)

  • 1878-1462


  • The ever-increasing growth of data centres and fog resources makes difficult for current simu-lation frameworks to model large computing infrastructures. Therefore, a major trade-off forsimulators is the balance between abstraction level of the models, the scalability, and the performance of the executions. In order to balance better these, early forays can be found in theliterature in which AI techniques are applied, but either lack of generality or are tailored tospecific simulation frameworks.This paper describes the methodology to integrate memoization as a technique of supervisedlearning into any computing simulators framework. In this process, a bespoke kernel was con-structed for the analysis of the energy models used in most well known computing simulators-cloud and fog-, but also to avoid simulation overhead. Finally, a detailed evaluation of energymodels and its performance is presented showing the impact of applying supervised learning tocomputing simulator, showing performance improvements when models are more accurate andcomputations are dense.


  • simulation; computer simulation; machine learning; memoization