McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910307832561664 |
|---|---|
| author | Poenaru-Olaru, Lorena Cruz, Luis Rellermeyer, Jan van Deursen, Arie |
| author_facet | Poenaru-Olaru, Lorena Cruz, Luis Rellermeyer, Jan van Deursen, Arie |
| contents | Due to the continuous change in operational data, AIOps solutions suffer from performance degradation over time. Although periodic retraining is the state-of-the-art technique to preserve the failure prediction AIOps models' performance over time, this technique requires a considerable amount of labeled data to retrain. In AIOps obtaining label data is expensive since it requires the availability of domain experts to intensively annotate it. In this paper, we present McUDI, a model-centric unsupervised degradation indicator that is capable of detecting the exact moment the AIOps model requires retraining as a result of changes in data. We further show how employing McUDI in the maintenance pipeline of AIOps solutions can reduce the number of samples that require annotations with 30k for job failure prediction and 260k for disk failure prediction while achieving similar performance with periodic retraining. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14093 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutions Poenaru-Olaru, Lorena Cruz, Luis Rellermeyer, Jan van Deursen, Arie Software Engineering Machine Learning Due to the continuous change in operational data, AIOps solutions suffer from performance degradation over time. Although periodic retraining is the state-of-the-art technique to preserve the failure prediction AIOps models' performance over time, this technique requires a considerable amount of labeled data to retrain. In AIOps obtaining label data is expensive since it requires the availability of domain experts to intensively annotate it. In this paper, we present McUDI, a model-centric unsupervised degradation indicator that is capable of detecting the exact moment the AIOps model requires retraining as a result of changes in data. We further show how employing McUDI in the maintenance pipeline of AIOps solutions can reduce the number of samples that require annotations with 30k for job failure prediction and 260k for disk failure prediction while achieving similar performance with periodic retraining. |
| title | McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutions |
| topic | Software Engineering Machine Learning |
| url | https://arxiv.org/abs/2401.14093 |