Failure prediction using machine learning in a virtualised HPC system and application
- Submitting institution
-
The University of Bradford
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 46
- Type
- D - Journal article
- DOI
-
10.1007/s10586-019-02917-1
- Title of journal
- Cluster Computing
- Article number
- -
- First page
- 471
- Volume
- 22
- Issue
- 2
- ISSN
- 1386-7857
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- URL
-
https://link.springer.com/article/10.1007%2Fs10586-019-02917-1
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 8
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work leverages machine learning techniques to develop an efficient failure prediction model for cloud services. The proposed model is significant as on average it accurately predicts 90% failures and is very effective compared to other algorithms. This work has led to completion of a PhD and the findings of this research is being used by two more PhD students in their research work. It is envisaged that this work will become a very useful tool for cloud service providers to timely and proactively deal with the failures.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
