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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1080/17517575.2017.1390167 | ENTERPRISE INFORMATION SYSTEMS |
Keywords | Field | DocType |
Online failure prediction,machine learning,fault injection,enterprise architecture | Training set,Authentication,Enterprise architecture,Computer science,Human error,Software,Statistical learning,Reliability engineering,Fault injection,Web server | Journal |
Volume | Issue | ISSN |
12.0 | 5 | 1751-7575 |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paul L. Jordan | 1 | 0 | 0.68 |
Gilbert L. Peterson | 2 | 251 | 38.75 |
Alan C. Lin | 3 | 2 | 1.39 |
Michael J. Mendenhall | 4 | 122 | 13.14 |
Andrew J. Sellers | 5 | 0 | 0.34 |