Integration of Parallel Genetic Algorithm and Q-learning for QoS-aware Web Service Composition

Web Service Composition (WSC) is the process of reusing atomic Web services and combining them together to satisfy users' requirements. The main objective of WSC is to develop composite services to satisfy the Functional Requirements (FR), as well as optimizing the Quality of Services (QoS) requirements. This has led to the emergence of QoS-aware WSC. Due to the increase in number of Web services with the same functionality but various QoS, it became difficult to find the optimal solution in QoS-aware WSC in a given time frame. In this paper we propose a new approach that integrates the use of the Parallel Genetic Algorithm (PGA) and Q-learning to find the optimal WSC within reasonable time. Q-learning is used to generate the initial population to enhance the effectiveness of PGA. PGA is utilized to make the algorithm as time efficient as possible. We implemented our approach over .NET Framework platform 4.7 using C# programming language. The experiment results show the effectiveness of our proposed approach compared to PGA or GA only.