The large-scale access of distributed generation and electric vehicles has a great impact on the economic operation and power quality of distribution network. Distributed power and electric vehicle power have uncertainties. In order to realize the rational distribution of distributed power, this paper presents a distributed power optimization layout method considering the uncertainties of electric vehicles. First of all, the optimal model of distributed generation is established by using the opportunistic constrained programming method with the least network loss, the minimum voltage offset and the high stability of the system. The SVM algorithm and the multi-objective particle swarm optimization algorithm are used to solve the above model, Pareto solution set is obtained. Finally, the model proposed in this paper is validated by IEEE37 node distribution network. The results show that the model can effectively get a reasonable configuration scheme. This work is supported by National Nature Science Foundation of China (No. 51477070).