Neural Network based method for the analysis of stochastic load flow is presented in this paper. Stochastic load flow is a method for calculation of the effects of inaccuracies in input data on all output quantities through the load flow calculations. This gives a range of values for each output quantity, which represent the operative condition of the system, to a high degree of probability. It is desirable to know the state of the power system, with consideration of input data accuracies, on instant-to-instant basis and present method of neural network application to stochastic load flow problem is an effort in that direction. The proposed neural network model has been tested on a sample power system and simulation results are presented.