With the rapid development of information and communication technology, 5G base stations (5G BS), as high-density and high-energy-consuming load nodes, present both opportunities and challenges in the expansion planning of active distribution network (ADN). An ADN expansion planning method considering the dispatchable potential of 5G BS is proposed. Firstly, based on the communication load rate of 5G BS, the backup battery of the 5G BS is dynamically divided into minimum backup capacity and dispatchable capacity. Secondly, to address the uncertainty of distributed generation (DG) output and load demand, a clustering algorithm based on variational Bayesian Gaussian mixture model is used to construct typical daily scenarios. On this basis, with the minimum annual comprehensive cost as the objective function, an ADN expansion planning model considering 5G BS dispatchable potential is established. To improve the efficiency of model solving, the second-order cone relaxation method and the Big-M method are used to transform the model into a mixed-integer second-order cone programming problem. Finally, based on the Portugal 54-node simulation analysis, the feasibility and effectiveness of the proposed method are verified.