The significance of traffic prediction in modern urban life has become increasingly prominent. Accurate traffic forecasting improves urban traffic management and enhances road resource utilization. In recent years, many models have introduced spatio-temporal contextual embeddings to distinguish between different time steps and spatial nodes. However, these models often overlook anomalous fluctuations in traffic data due to data imbalance. Consequently, performance declines when encountering uncommon situations, especially those caused by unexpected traffic accidents. To maintain overall performance while being aware of anomalous fluctuations, we propose STPDN, a dual-branch Spatio-Temporal Pattern Decomposition Graph Neural Network. Specifically, We introduce latent variables to characterize the distribution of latent patterns in traffic sequences, enabling the model to distinguish regular patterns and anomalous fluctuations without supervised information specifically targeting anomalies. Subsequently, we develop a resilient graph generator capable of producing dynamic spatio-temporal graphs, facilitating the propagation of impacts caused by dynamic fluctuations. Finally, we achieve more comprehensive and robust predictions by fusing regular patterns and anomalous fluctuations. Evaluation of real-world and simulated datasets shows that our model outperforms others, offering more reliable prediction solutions for urban traffic management systems, particularly in handling unforeseen traffic events. The code can be found at unmapped: uri https://github.com/dhxdla/PyTorch-implementation-of-the-STPDN.git.