Many-Objective Automatic Service Composition Based on Temporal Goal Decomposition

With the evolution of Web technologies, various services have become available in a pervasive network environment. Combining simple atomic services into sophisticated applications with a quality-of-service (QoS) guarantee has become a widely studied problem. Given the increasing number of QoS attributes to be considered, conventional service composition approaches with manual workflows and massive computational burdens are no longer effective. Therefore, this article first suggests an efficient many-objective (with four or more objectives) automatic service composition approach named MaSC. In particular, this article introduces a temporal goal decomposition mechanism based on a temporal model to divide an unwieldy problem into several fine-grained subproblems. Viewing this model as an individual representation, we employ an evolutionary process with a novel fitness function to explore the composition solution. The experimental results on the benchmarks show that our approach can simultaneously optimize up to six objectives and achieve a better trade-off between the computation cost and the QoS than two recently proposed automatic composition approaches.