An Efficient Discrete Invasive Weed Optimization Algorithm for Web Services Selection

Abstract

Efficient algorithm is required to select component services with end-to-end QoS constraints in dynamic composition of Web Services while optimizing the QoS of the composite service. In this paper, the services selection probelm is modeled as a nonlinear optimization with constraints, then a novel discrete invasive weed optimization web services selection algorithm is proposed. The proposed solution consists of two steps:first, a set of randomly generated feasible solutions are transformed into decimal code. Second, We utilize Gaussian diffusion to guide the population to spread in the solution space. The mutation probability and mutation step size of individual is dynamically adjusted by changing the stantard deviation of Gaussian distribution. Accordingly, the population diversity is ensured in the early stage to expand the search space, while the local search nearby excellent individuals is focused in the latter stage to ensure the global convergence. Theoretical analysis and experiment results indicate the efficiency, robustness and feasibility of our approach.