PCGAT-Stab: An Explainable Temporal Graph Attention Network for PCIe Protocol Behavior Modeling and System Stability Prediction in Cloud-Native Microservices

Abstract

Cloud-native microservice architectures built on Kubernetes increasingly support AI SaaS platforms, financial-grade systems, and large-scale data centers, where high availability and low latency are critical requirements. However, while observability frameworks provide rich application- and orchestration-level metrics, they largely overlook the impact of low-level hardware behaviors, particularly PCIe protocol anomalies, on service stability. In modern GPU- and accelerator-intensive clusters, PCIe errors such as Completion Timeout, Replay Timer Expiration, and Link Retrain events can propagate across device topology and manifest as pod restarts, latency jitter, and SLA violations. To address this cross-layer visibility gap, we propose PCGAT-Stab, an explainable Temporal Graph Attention Network for PCIe protocol behavior modeling and system stability prediction in cloud-native microservices. The model constructs a dynamic PCIe topology graph, encodes protocol error propagation through multi-head graph attention, captures temporal accumulation effects via recurrent units, and maps hardware-level representations to pod-level risk embeddings using an explicit device–pod association mechanism. Furthermore, attention analysis and SHAP-based attribution provide interpretable insights into hardware-to-service causal relationships. Experiments on a real-world Kubernetes cluster dataset show that PCGAT-Stab achieves an AUC of 0.94 and an F1-score of 0.91 for instability classification, outperforming LSTM and Transformer baselines. For latency prediction, the model attains an RMSE of 5.72 and MAE of 4.68, demonstrating superior cross-layer modeling capability. These results confirm the effectiveness of topology-aware temporal graph attention for reliable system stability prediction in cloud-native microservices.