Modeling normal behavior in dynamic, high-dimensional temporal data is essential for effective anomaly detection. However, existing methods, such as nearest neighbor and clustering approaches, often rely on rigid assumptions, such as the presence of reliable neighbors or predefined cluster numbers, which often fail in complex scenarios. To address these limitations, we introduce the Granular-ball One-Class Network (GBOC), a novel approach based on a data-adaptive representation called Granular-ball Vector Data Description (GVDD). Granular-balls naturally position themselves between individual instances and clusters, preserving the local topological structure of the sample set. GVDD partitions the latent space into compact, high-density regions represented by granular-balls, which are generated through a density-guided hierarchical splitting process and refined by removing noisy structures. Each granular-ball acts as a prototype for local normal behavior. During training, GBOC improves the compactness of representations by aligning samples with their nearest granular-ball centers. During inference, anomaly scores are computed based on the distance to the nearest granular-ball. By focusing on dense, high-quality regions and significantly reducing the number of prototypes, GBOC delivers both robustness and efficiency in anomaly detection. Extensive experiments demonstrate the effectiveness and superiority of the proposed method.