A Machine Learning based Context-aware Prediction Framework for Edge Computing Environments

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

A Context-aware Prediction Framework (CAPF) can be provided through a Self-adaptive System (SAS) resource manager to support the autoscaling decision in Edge Computing (EC) environments. However, EC dynamicity and workload fluctuation represent the main challenges to design a robust prediction framework. Machine Learning (ML) algorithms show a promising accuracy in workload forecasting problems which may vary according to the workload pattern. Therefore, the accuracy of such algorithms needs to be evaluated and compared in order to select the most suitable algorithm for EC workload prediction. In this paper, a thorough comparison is conducted focusing on the most popular ML algorithms which are Linear Regression (LR), Support Vector Regression (SVR), and Neural Networks (NN) using real EC dataset. The experimental results show that a robust prediction framework can be supported by more than one algorithm considering the EC contextual behavior. The results also reveal that the NN outperforms LR and SVR in most cases.

Original languageEnglish
Title of host publicationCLOSER 2021 - Proceedings of the 11th International Conference on Cloud Computing and Services Science
EditorsMarkus Helfert, Donald Ferguson, Claus Pahl
PublisherScience and Technology Publications, Lda
Pages143-150
Number of pages8
ISBN (Electronic)9789897585104
DOIs
StatePublished - 2021
Event11th International Conference on Cloud Computing and Services Science, CLOSER 2021 - Virtual, Online
Duration: 28 Apr 202130 Apr 2021

Publication series

NameInternational Conference on Cloud Computing and Services Science, CLOSER - Proceedings
Volume2021-April
ISSN (Electronic)2184-5042

Conference

Conference11th International Conference on Cloud Computing and Services Science, CLOSER 2021
CityVirtual, Online
Period28/04/2130/04/21

Keywords

  • Edge Computing
  • Linear Regression
  • Machine Learning
  • Neural Networks
  • Prediction Framework
  • Self-adaptive Systems
  • Sliding Window
  • Support Vector Regression

Fingerprint

Dive into the research topics of 'A Machine Learning based Context-aware Prediction Framework for Edge Computing Environments'. Together they form a unique fingerprint.

Cite this