Predicting cloud resource utilization

Publikationstyp
Conference Paper
Date Issued
2016-12
Sprache
English
Author(s)
Borkowski, Michael  
Schulte, Stefan  
Hochreiner, Christoph  
TORE-URI
http://hdl.handle.net/11420/11871
Start Page
37
End Page
42
Citation
9th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2016)
Contribution to Conference
9th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2016  
Publisher DOI
10.1145/2996890.2996907
Scopus ID
2-s2.0-85009062524
A major challenge in Cloud computing is resource provisioning for computational tasks. Not surprisingly, previous work has established a number of solutions to provide Cloud resources in an efficient manner. However, in order to realize a holistic resource provisioning model, a prediction of the future resource consumption of upcoming computational tasks is necessary. Nevertheless, the topic of prediction of Cloud resource utilization is still in its infancy stage. In this paper, we present an approach for predicting Cloud resource utilization on a per-task and per-resource level. For this, we apply machine learning-based prediction models. Based on extensive evaluation, we show that we can reduce the prediction error by 20% in a typical case, and improvements above 89% are among the best cases.
Subjects
Cloud computing
Machine learning
Resource usage
Usage prediction