Multi-Dimensional Anomaly Detection and Fault Localization in Microservice Architectures: A Dual-Channel Deep Learning Approach with Causal Inference for Intelligent Sensing

Abstract

Modern data centers face increasing complexity with distributed microservice architectures, making anomaly detection and fault localization challenging yet critical. Traditional monitoring sensor tools struggle with heterogeneous metrics, temporal correlations, and precise root cause analysis in these environments. This paper proposes a dual-channel deep learning framework that integrates Temporal Convolutional Networks with Variational Autoencoders to address these challenges. Our approach employs contrastive learning to create unified representations of diverse service metrics and incorporates causal inference mechanisms to trace fault propagation paths. We evaluated our framework using a semi-supervised learning approach that leveraged both labeled anomalies and abundant normal data, achieving 95.4% detection accuracy, 93.8% F1-score, and 87.6% precision in fault component localization. The system reduced the average troubleshooting time by 43% and false localization rates by 31% compared to state-of-the-art methods, while maintaining a computational efficiency suitable for real-time monitoring. These results demonstrate the effectiveness of our approach in identifying and precisely localizing anomalies in complex microservice environments through intelligent sensing of system metrics, enabling proactive maintenance strategies that minimize service disruptions.