Qos-Based Web Service Discovery And Selection Using Machine Learning

TL;DR

This paper proposes a machine learning-based architecture for web service discovery and selection that predicts QoS properties from source code metrics and considers provider reputation, addressing issues of data scarcity and reliability.

Contribution

It introduces a novel architecture utilizing machine learning to predict QoS and assess provider reputation, improving service selection accuracy.

Findings

Machine learning effectively predicts QoS properties from source code metrics.

Reputation metrics enhance the reliability of service selection.

The approach addresses data scarcity in QoS evaluation.

Abstract

In service computing, the same target functions can be achieved by multiple Web services from different providers. Due to the functional similarities, the client needs to consider the non-functional criteria. However, Quality of Service provided by the developer suffers from scarcity and lack of reliability. In addition, the reputation of the service providers is an important factor, especially those with little experience, to select a service. Most of the previous studies were focused on the user's feedbacks for justifying the selection. Unfortunately, not all the users provide the feedback unless they had extremely good or bad experience with the service. In this vision paper, we propose a novel architecture for the web service discovery and selection. The core component is a machine learning based methodology to predict the QoS properties using source code metrics. The credibility value and previous usage count are used to determine the reputation of the service.