EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Anomaly Detection Based on LLM for Heterogeneous Multivariate Time Series in the Intelligent Computing Center

Xingguo Jiang, Yue Wang, Chunpeng Wu, Xiaohui Wang, Hongyin Chen, Zhenying Tai, Hao Yue, Chang Liu

IET Communications · 2026-01 · 20 (1)

DOI: 10.1049/cmu2.70154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Communications, online erschienen am 30.03.2026. Verfasst von Xingguo Jiang und 7 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of the intelligent computing centers, multivariate time series generated from many heterogeneous devices with non‐independent and identically distributed (non‐IID) characteristic, posed a significant challenge to traditional anomaly detection models. These challenges primarily arise from the difficulty in aligning and unifying heterogeneous data and the significant reduction in model generalization due to non‐IID data distributions. Therefore, this paper proposes a novel anomaly detection framework for non‐IID data from heterogeneous devices. First, we introduce a chain of thought metric alignment and ranking mechanism based on a large language model to meet the data heterogeneity challenge. Second, we design a variational recurrent neural network model augmented with global factors to capture spatiotemporal correlation patterns across devices, effectively addressing the impact of non‐IID data distributions. Experiments on multiple real‐world datasets demonstrate that this approach achieves optimal F1‐scores across various heterogeneous datasets. And because of the metric ranking, the model communication efficiency and inference efficiency have been greatly optimized.

Zitieren

APA

Jiang, X., Wang, Y., Wu, C., Wang, X., Chen, H., Tai, Z., Yue, H., & Liu, C. (2026). Unsupervised Anomaly Detection Based on LLM for Heterogeneous Multivariate Time Series in the Intelligent Computing Center. IET Communications, 20(1). https://doi.org/10.1049/cmu2.70154

Vancouver

Jiang X, Wang Y, Wu C, Wang X, Chen H, Tai Z, et al. Unsupervised Anomaly Detection Based on LLM for Heterogeneous Multivariate Time Series in the Intelligent Computing Center. IET Communications. 2026;20(1). doi:10.1049/cmu2.70154

BibTeX
@article{Jiang2026,
  author = {Jiang, Xingguo and Wang, Yue and Wu, Chunpeng and Wang, Xiaohui and Chen, Hongyin and Tai, Zhenying and Yue, Hao and Liu, Chang},
  title = {Unsupervised Anomaly Detection Based on LLM for Heterogeneous Multivariate Time Series in the Intelligent Computing Center},
  journal = {IET Communications},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/cmu2.70154}
}
Kostenlos starten →