Fault Prediction in SOA-Based Systems Using Deep Learning Techniques

Guru Prasad Bhandari and Ratneshwer Gupta
Additional contact information
Guru Prasad Bhandari: Banaras Hindu University, India
Ratneshwer Gupta: Jawaharlal Nehru University, India

International Journal of Web Services Research (IJWSR), 2020, vol. 17, issue 3, 1-19

Abstract: Fault prediction in Service Oriented Architecture (SOA) based systems is one of the important tasks to minimize the computation cost and time of the software system development. Predicting the faults and discovering their locations in the early stage of the system development lifecycle makes maintenance processes easy and improves the resource utilization. In this paper, the authors proposed the fault prediction model for SOA-based systems by utilizing the deep learning techniques. Twenty-one source code metrics are applied to different web services projects. The web services datasets are constructed by injecting the faults into it, and metrics are extracted for both faulty and nonfaulty data for training and testing purpose. Moreover, different deep learning techniques are inspected for fault prediction of web services and performance of different methods are compared by using standard performance measures. From the experimental results, it is observed that deep learning techniques provide effective results and applicable to the real-world SOA-based systems.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/IJWSR.2020070101 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jwsr00:v:17:y:2020:i:3:p:1-19

Access Statistics for this article

International Journal of Web Services Research (IJWSR) is currently edited by Liang-Jie Zhang

More articles in International Journal of Web Services Research (IJWSR) from IGI Global
Bibliographic data for series maintained by Journal Editor ().