Predicting host CPU utilization in cloud computing using recurrent neural networks

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

85 Citations (Scopus)

Abstract

One of the major challenges facing cloud computing is to accurately predict future resource usage for future demands. Cloud resource consumption is constantly changing, which makes it difficult for forecasting algorithms to produce accurate predictions. This motivates the research presented in this paper which aims to predict host machines CPU consumption for a single time-step and multiple time-steps into the future. This research implements a Recurrent Neural Network to predict CPU utilisation, due to their ability to retain information and accurately make predictions for time series problems, making it a promising candidate to predict CPU utilization with greater accuracy when compared to traditional approaches.

Original languageEnglish
Title of host publication2017 12th International Conference for Internet Technology and Secured Transactions, ICITST 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages67-72
Number of pages6
ISBN (Electronic)9781908320933
DOIs
Publication statusPublished - 8 May 2018
Event12th International Conference for Internet Technology and Secured Transactions, ICITST 2017 - Cambridge, United Kingdom
Duration: 11 Dec 201714 Dec 2017

Publication series

Name2017 12th International Conference for Internet Technology and Secured Transactions, ICITST 2017

Conference

Conference12th International Conference for Internet Technology and Secured Transactions, ICITST 2017
Country/TerritoryUnited Kingdom
CityCambridge
Period11/12/1714/12/17

Keywords

  • Cloud Computing
  • CPU Prediction
  • Neural Networks

Fingerprint

Dive into the research topics of 'Predicting host CPU utilization in cloud computing using recurrent neural networks'. Together they form a unique fingerprint.

Cite this