With the accelerative development of modern society informationization, data and databases has rapidly increased. That demands the abroad application of distributed data mining (DDM) methods that can parallel to get the results in time. However the problem of minimizing the communications costs across limited bandwidth interconnection network in DDM is crucial now. Considering that, this paper proposes the architecture of distributed data mining, model of scheduling in distributed data mining and its algorithm to deal with it. To more optimize the result of the scheduling algorithm, genetic algorithm is also used in this paper.