A Distance-based Genetic Algorithm for Robust Data-intensive Web Service Composition in Dynamic Bandwidth Environment

With the complex needs of the companies that cannot be met by a single service, Data-intensive Web Service Composition (DWSC) is required to compose multiple services in a distributed service environment. Compositions must satisfy functional specifications and non-functional requirements, i.e. Quality of Service (QoS). Existing approaches on DWSC make the underlying assumption that the participating Web services and communication networks are static so that their QoS and bandwidth seldom change. However, those approaches are impractical since network failures or dynamic bandwidth changes cause violations of user agreements. Additionally, they ignore the distribution of services in general, and therefore, variations in network attributes are not taken into account. In this paper, we address the problem of dynamic distributed DWSC (D2-DWSC), design a simulation model for bandwidth patterns, and propose an algorithm to generate robust solutions for D2-DWSC which can cope with the changes in dynamic environments. Experimental results verify the effectiveness of our method.