Document Type
Article
Publication Date
5-28-2018
Abstract
As society becomes more dependent upon computer systems to perform increasingly critical tasks, ensuring that those systems do not fail becomes increasingly important. Many organizations depend heavily on desktop computers for day-to-day operations. Unfortunately, the software that runs on these computers is written by humans and, as such, is still subject to human error and consequent failure. A natural solution is to use statistical machine learning to predict failure. However, since failure is still a relatively rare event, obtaining labelled training data to train these models is not a trivial task. This work presents new simulated fault-inducing loads that extend the focus of traditional fault injection techniques to predict failure in the Microsoft enterprise authentication service and Apache web server. These new fault loads were successful in creating failure conditions that were identifiable using statistical learning methods, with fewer irrelevant faults being created.
Source Publication
Enterprise Information Systems
Recommended Citation
Jordan, P. L., Peterson, G. L., Lin, A. C., Mendenhall, M. J., & Sellers, A. J. (2018). Narrowing the scope of failure prediction using targeted fault load injection. Enterprise Information Systems, 12(5), 587–602. https://doi.org/10.1080/17517575.2017.1390167
Comments
AFIT Scholar furnishes the draft version of this article. The published version of record appears in Enterprise Information Systems, as cited, and is available by subscription through the DOI link below.