Journal of Computer Technology and Software

Vol. 3 No. 7 (2024)
Articles

Time Series and Graph Structure Fusion for AI-Based Anomaly Detection in Microservice Environments

pdf
  • Zhimin Qiu
DOI: https://doi.org/10.5281/zenodo.18666213

Published 2024-10-30

How to Cite

Qiu, Z. (2024). Time Series and Graph Structure Fusion for AI-Based Anomaly Detection in Microservice Environments. Journal of Computer Technology and Software, 3(7). https://doi.org/10.5281/zenodo.18666213
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

This paper addresses the complexity of fault detection in microservice systems by proposing a modeling approach that integrates temporal features with graph structural information to enhance the accuracy of anomaly detection and fault localization. Multi-dimensional monitoring metrics are used as temporal inputs, where embeddings and attention mechanisms capture dynamic changes in service states, while service invocation relations are modeled as graphs in which graph convolution characterizes cross-node dependencies and propagation paths. A cross-modal fusion module is then designed to unify temporal features and graph embeddings, achieving a balance between local details and global dependencies. Sensitivity experiments on key factors such as temporal window length, graph convolution depth, sampling frequency, and scheduling frequency reveal their significant impact on performance and show that proper configurations can improve fault detection. Comparative experiments further demonstrate that the proposed method outperforms several baselines in recall, accuracy, F1-score, and precision, maintaining high stability and robustness under diverse conditions. The results indicate that the fusion of temporal and graph-based representations enables efficient identification of anomalies in complex microservice scenarios and provides strong technical support for system operation and maintenance in practical applications.

pdf

References

  1. Zhao C, Ma M, Zhong Z, et al. Robust multimodal failure detection for microservice systems[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2023: 5639-5649.
  2. He S, Li G, Xie K, et al. Fusion graph structure learning-based multivariate time series anomaly detection with structured prior knowledge[J]. IEEE Transactions on Information Forensics and Security, 2024.
  3. S. Nedelkoski, J. Cardoso and O. Kao, "Anomaly detection and classification using distributed tracing and deep learning," 2019 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), pp. 241-250, 2019.
  4. Huang J, Yang Y, Yu H, et al. Twin graph-based anomaly detection via attentive multi-modal learning for microservice system[C]//2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE). IEEE, 2023: 66-78.
  5. M. Du, F. Li, G. Zheng and V. Srikumar, “DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning,” in Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 1285-1298, Oct. 2017.
  6. Y. Su, Y. Zhao, C. Niu, R. Liu, W. Sun and D. Pei, “Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2828-2837, Jul. 2019.
  7. K. Hundman, V. Constantinou, C. Laporte, I. Colwell and T. Soderstrom, “Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 387-395, Jul. 2018.
  8. Y. Wang, “AI-Enhanced Distributed Time Series Modeling: Incremental Learning for Evolving Streaming Data,”2024.
  9. Z. Cheng, “Hierarchical Attention-Based Modeling for Intelligent Scheduling Delay Prediction in Complex Backend Systems,”2024.
  10. Y. Kang, “Deep Learning-Based Multi-Scale Temporal and Structure-Aware Modeling for Metric Anomaly Detection in Microservice Systems,”2024.
  11. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio and Y. Bengio, “Graph Attention Networks,” arXiv preprint arXiv:1710.10903, 2017.
  12. L. Akoglu, M. McGlohon and C. Faloutsos, “Oddball: Spotting Anomalies in Weighted Graphs,” in Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 410-421, Jun. 2010.
  13. F. Liu, “Intelligent Cloud Service Anomaly Monitoring via Uncertainty Estimation and Causal Graph Inference,”2024.
  14. D. Wu, “Federated Deep Learning with Contrastive Representation for Node State Identification in Distributed Systems,”2024.
  15. Zhang X, Xu M, Zhou X. Realnet: A feature selection network with realistic synthetic anomaly for anomaly detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024: 16699-16708.
  16. He H, Bai Y, Zhang J, et al. Mambaad: Exploring state space models for multi-class unsupervised anomaly detection[J]. Advances in Neural Information Processing Systems, 2024, 37: 71162-71187.
  17. Wang C, Zhu W, Gao B B, et al. Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 22883-22892.
  18. Li X, Zhang Z, Tan X, et al. Promptad: Learning prompts with only normal samples for few-shot anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 16838-16848.