Based on the network model of integrated service chains and evaluation index of candidate service resources, optimizing integrated service chain can be formally defined as a multi objective global optimization model with multiple constraints. We propose a multi objective global optimization algorithm based on improved multi objective genetic algorithms. The proposed algorithm uses a distance based nonparametric population diversity measurement operator, and diversity control is involved in the process of adaptive value assignment, elitist maintaining and selection operation. The proposed algorithm can optimize multiple objectives at the same time on the premise of meeting the constraints, and finally get a constrained Pareto optimum solution set which satisfy decision makers’ prefers. The simulation experiments indicate that the proposed algorithms can achieve global convergence and has better solution quality and distribution, which efficiently solve the problem of integrated service chain multi objective global optimization.