Abstract: Distribution Network Reconfiguration（DNR） is an effective measure to determine the optimal topology of the distribution network and reduce network losses. Due to the massive access of distributed generation（DG） and electric vehicles（EV）, the power flow of the distribution network is probabilistic.The traditional reconstruction method can no longer quickly and accurately obtain the reconstruction optimal solution of probabilistic power flow. Proposes a reconstruction model that considers the randomness and uncertainty of distributed generation and electric vehicles, aims to reduce network losses and improve voltage quality, and adopts optimal power flow（OPF） and branch exchange method（BEM）in the heuristic algorithm to speed up reconstruction. The validity and correctness of the algorithm are verified by the IEEE136 test system. The results show that this algorithm achieves deep optimization and can effectively solve the problem of dynamic reconstruction of probabilistic power flow.