A RECOMMENDER SYSTEM FOR FAULT RECOVERY STRATEGIES IN WEB SERVICES COMPOSITION TESTING | ||
| International Journal of Intelligent Computing and Information Sciences | ||
| Volume 23, Issue 3, September 2023, Pages 95-113 PDF (515.03 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/ijicis.2023.217108.1279 | ||
| Authors | ||
| Roaa ElGhondakly1; Sherin Moussa* 2; Nagwa Badr1 | ||
| 1Department of Information Systems, Faculty of Computer and Information Sciences | ||
| 2Department of Information Systems, Faculty of Computer and Information Scences | ||
| Abstract | ||
| Faults recovery has recently emerged as an important aspect of web service composition (WSC) testing, as it aims to minimize the impact of faults on system functionality through restoring the system's operation after a fault has occurred. However, most of the existing recommendation systems (RSs) tend to recommend frequently used services, which lack diversity and face inaccuracies due to incomplete or biased historical data. In addition, the focus of the existing RSs is on proposing fault handling models rather than recommending the best recovery strategy for handling faults, with most being code-based, thus not suitable for WSCs. Accordingly, due to the opaque nature of WSCs with hidden source code, model-based recovery methods are preferred. In this paper, the Fault Recovery Strategies RS for WSCs (F2RS-WSC) is proposed to recommend the best recovery strategy for handling emerging faults in the WSCs paradigm. The proposed system is a model-based system that recommends the best strategy for recovering faulty paths generated from service dependency graphs based on the faults` types, severity levels, faults` location, as well as the time at which faults may occur. The experimental results show that the time consumed by F2RS-WSC to recommend the optimum recovery strategy represents less than 3% of the SDG parsing time and 4% of the path validation time. In addition, its superior performance assures its accuracy and efficiency. Thus, it achieves accuracy levels between 70% and 88 % among multiple datasets. Moreover, its average precision, recall and f-measure values are 0.85,0.81 and 0.86 respectively. | ||
| Keywords | ||
| Fault recovery strategies; fault handling; service-oriented computing; web service composition; service dependency graph | ||
|
Statistics Article View: 126 PDF Download: 115 |
||
