A mobile communication network usually has a complex system composed of millions of connected mobile devices, each device can be regarded as a node, and the communication between them can be regarded as an edge. Because the structure of mobile communication networks always changes with time, such as the appearance or disappearance of device nodes or edges, the traditional method of researching mobile communication network structure modelling becomes a very challenging problem. This paper constructs a dynamic community detection model based on representation learning (DCDAL) based on graph autoencoding and the Gaussian mixture depth model in response to the above problems. Commonly used dynamic network evaluation indicators such as NMI and modularity are compared and analyzed in complex communication networks. The DCDAL model can outperform the optimal comparative models in NMI and other indicators, especially in large-scale mobile communication network datasets. The model can obtain robust results on multiple indicators Text for this section.