Back to Search
Start Over
Application of multivariate time-series model for high performance computing (HPC) fault prediction.
- Source :
-
PloS one [PLoS One] 2023 Oct 17; Vol. 18 (10), pp. e0281519. Date of Electronic Publication: 2023 Oct 17 (Print Publication: 2023). - Publication Year :
- 2023
-
Abstract
- Aiming at the high reliability demand of increasingly large and complex supercomputing systems, this paper proposes a multidimensional fusion CBA-net (CNN-BiLSTAM-Attention) fault prediction model based on HDBSCAN clustering preprocessing classification data, which can effectively extract and learn the spatial and temporal features in the predecessor fault log. The model can effectively extract and learn the spatial and temporal features from the predecessor fault logs, and has the advantages of high sensitivity to time series features and sufficient extraction of local features, etc. The RMSE of the model for fault occurrence time prediction is 0.031, and the prediction accuracy of node location for fault occurrence is 93% on average, as demonstrated by experiments. The model can achieve fast convergence and improve the fine-grained and accurate fault prediction of large supercomputers.<br />Competing Interests: The authors have declared that no competing interests exist.<br /> (Copyright: © 2023 Pei et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
- Subjects :
- Time Factors
Reproducibility of Results
Cluster Analysis
Learning
Subjects
Details
- Language :
- English
- ISSN :
- 1932-6203
- Volume :
- 18
- Issue :
- 10
- Database :
- MEDLINE
- Journal :
- PloS one
- Publication Type :
- Academic Journal
- Accession number :
- 37847694
- Full Text :
- https://doi.org/10.1371/journal.pone.0281519