preprints.org > engineering > control and systems engineering > doi: 10.20944/preprints201909.0238.v1

Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Version 1 : Received: 19 September 2019 / Approved: 20 September 2019 / Online: 20 September 2019 (10:49:11 CEST)

With the development of computer science and software engineering, software becomes more and more complex. Traditional software reliability assurance techniques including software testing and evaluation can't ensure software reliable execution after being deployed. Software failure prediction techniques based on failure indicators can predict software failures according to abnormal indicator values. The latter can be collected using runtime monitoring techniques. An essential part of this method is finding proper indicators which have strong correlation with software failures. We propose a novel type of indicators in this work named software runtime entropy, which takes both software module execution time and call times into consideration. Three common open source software, grep, flex and gzip are used as study cases for finding the relationships between the indicators and software failures. Firstly, a series of fault injection experiments are conducted on those three software respectively. The decision tree algorithm is used to train those data to build the correlation models between software runtime entropy and software failures. Several common measures in machine learning domains such as accuracy, recall rates, and F-measure are used to evaluate the models. The decision tree models can be used as failure mechanisms to assist the failure prediction work. One can examine the value of runtime entropy and make a warning report when it ranges from the normal interval to abnormal one.

Software runtime entropy; failure prediction; indicator

Engineering, Control and Systems Engineering

* All users must log in before leaving a comment