The timing and uncertainty of distributed wind generation（DWG） and load output will result in the timing and uncertainty of outage power

which in turn will affect the power supply reliability of the distribution network. In this paper

the power outage loss index of the timing and uncertainty is introduced in the model based on Monte-Carlo stochastic simulation. A multi-objective optimal allocation model of DWG is established with consideration of minimum investment cost of DWG

minimum network loss and minimum power outage. For improving the convergence performance of the algorithm

an improved multi-objective particle swarm optimization algorithm is used for the calculation. In this algorithm

the multi-objective global optimization is performed by the niche technology and

at the same time

non-dominated sorting strategy and crowding distance is used to select optimal particles

which lead the particles to jump out of local optimum. As for the obtained Pareto solution

the final solution is selected with the shortest normalized distance method. Finally

the simulation experiment is carried out with IEEE 33 node distribution network

and the feasibility and effectiveness of the proposed model and algorithm are verified.