Home // IMMM 2016, The Sixth International Conference on Advances in Information Mining and Management // View article

Machine Learning in Cloud Environments Considering External Information

Authors:
Matthias Lermer
Stefan Frey
Christoph Reich

Keywords: Machine Learning; Support Vector Machines; Neural Network; Linear Regression; Cloud Computing; SLA.

Abstract:
Machine learning applied to cloud environments can lead to many advantages. One example is the possibility of improved Quality of Service (QoS) by predicting future workloads and reacting dynamically with automated scaling. In reality however, there are cases where the use of machine learning algorithms is not as efficient as imagined. One current problem is the disregard of external information, whose inclusion could help to create better models of the reality. The approach of this paper shows that different machine learning algorithms like Neural Networks (NN), Support Vector Machines (SVM) and Linear Regression can be successfully used to predict the response time of Virtual Machines (VM) within cloud environments. The performed application of those algorithms to different cloud usage scenarios and following evaluation enables to gain insight into the strengths and weaknesses of each algorithm. Furthermore, a work in progress architecture is proposed to deal with the two big challenges, inclusion of external information and handling live data streams.

Pages: 11 to 17

Copyright: Copyright (c) IARIA, 2016

Publication date: May 22, 2016

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-477-0

Location: Valencia, Spain

Dates: from May 22, 2016 to May 26, 2016