This paper deals with a minimum spanning tree problem where each edge weight is a random variable. In order to solve the uncertain network optimization, the concept of the alpha-optimistic cost spanning tree is proposed and a stochastic optimization model is constructed according to the theory of stochastic programming. We adopted an efficient method to convert the stochastic optimization problem into the deterministic equivalent, and use Kruskal's algorithm to solve the problem. Finally, a numerical experiment is given to show the effectiveness of the proposed method.