关键词: 供应链网络, 复杂网络, 期望最大化算法, 连接规则, 演化规律

Abstract: Aiming at the problem that the stochastic connection of enterprises may have led to the decrease of network stability and operational efficiency in the evolution stage of the supply chain network, an improved connection algorithm of the supply chain network based on the expectation maximization algorithm was proposed. Firstly, the number of edges of network nodes was included in the algorithm as a new parameter to accurately determine the number of edges possessed by new nodes in the supply chain network. Secondly, given the predetermined number of edges, residual edge connection rules were introduced to enhance the selectivity and differentiation of nodes. By ensuring the smooth operation of the newly connected enterprise nodes in the network, the influence of different initial edge numbers on the network evolution was studied. Simulation results show that compared with the expectation maximization algorithm, the improved algorithm only needs 80 iterations to get stable results, and the number of connected edges is stable around 4 in the scale of 1000 nodes, which matches the evolution process of the actual supply chain network. It can be seen that the improved expectation maximization algorithm model is obviously better than the expectation maximization algorithm in fitting the actual supply chain network.

Key words: supply chain network, complex network, expectation maximization algorithm, connection rule, evolutionary law