F-MOGP: A Novel Many-Objective Evolutionary Approach to QoS-aware Data Intensive Web Service Composition


QoS-aware web service composition has attracted increasing attention recently. Meanwhile, due to the explosion in the volume of data, providing efficient methods for composing data intensive services poses new challenges to the service composition problem. In this paper, a new search and optimisation approach based on a reduced space searching strategy, named F-MOGP, is presented to address the problem of QoS-aware data intensive service composition driven by four conflicting quality objectives. The experimental results show that the proposed approach is computationally efficient by search space reduction. Compared with the existing single-objective and multi-objective optimization methods, a set of higher-quality data intensive service compositions can be successfully generated to support decision makers by providing them with potential trade-offs among different objectives.