Beyond Attention: Hierarchical Mamba Models for Scalable Spatiotemporal Traffic Forecasting

Traffic forecasting in cellular networks is a challenging spatiotemporal prediction problem due to strong temporal dependencies, spatial heterogeneity across cells, and the need for scalability to large network deployments. Traditional cell-specific models incur prohibitive training and maintenance costs, while global models often fail to capture heterogeneous spatial dynamics. Recent spatiotemporal architectures based on attention or graph neural networks improve accuracy but introduce high computational overhead, limiting their applicability in large-scale or real-time settings. We propose HiSTM (Hierarchical SpatioTemporal Mamba), a spatiotemporal forecasting architecture built on state-space modeling. HiSTM combines spatial convolutional encoding for local neighborhood interactions with Mamba-based temporal modeling to capture long-range dependencies, followed by attention-based temporal aggregation for prediction. The hierarchical design enables representation learning with linear computational complexity in sequence length and supports both grid-based and correlation-defined spatial structures. Cluster-aware extensions incorporate spatial regime information to handle heterogeneous traffic patterns. Experimental evaluation on large-scale real-world cellular datasets shows that HiSTM achieves state-of-the-art accuracy, with up to 29.4% MAE reduction over strong spatiotemporal baselines and 47.3% improvement on unseen datasets. HiSTM shows improved robustness to missing data and better stability in long-horizon autoregressive forecasting, showcasing its effectiveness for scalable 5/6G traffic prediction.