ESCA: Evolution-strategy based Service Composition Algorithm for Multiple QoS Constrained Cloud Applications

Abstract

Web services have been widely applied in e-business or organizations to establish versatile applications. However, service composition with constraint to QoS constraints still remains as a challenging issue, because both the service performance and the QoS requirements of applications tend to be dynamically changed at runtime. To address this problem, in this paper we present a novel service composition framework, which takes advantage of flexibility provided by cloud systems and applies evolution strategy to solve the optimal programming problem of multiple QoS constrained service composition. Furthermore, a QoS negation mechanism is proposed to satisfy the dynamical and elastic cloud environments. Massive experiments are conducted to investigate the effectiveness of the proposed framework, and the results show that it can significantly reduce the costs of large-scale service-based application in terms of various QoS metrics.