In this paper, we propose an algorithm that can be efficiently used to search through scale-free networks. The algorithm uses local information such as the identities and connectedness of a nodepsilas neighbours, and its neighbours, but not the targetpsilas global position. We demonstrate that our search algorithm work well on a simulative networks, scale with the number of nodes, and may help reduce the network search traffic that tends to cripple such networks. We have studied how optimize nodes on a scale-free network using an association rules mining based on a novel genetic algorithm, we ...