A Failure Prediction Model for Large Scale Cloud Applications using Deep Learning
Bibliographic record
Abstract
Many cloud service providers face significant challenges in preventing hardware and software failure from occurring. Due to the large scale and heterogeneous nature of cloud computing, cloud services continue to experience failures in their components. A significant proportion of previous studies have focused on the characterization of failed jobs and understanding their behavior, while a few studies have focused on failure prediction, with a focus on increasing the accuracy of failure prediction models. This paper presents the development and implementation of a failure prediction model using a deep learning approach. The proposed model can identify and detect failed tasks early on before they occur. The key feature of the failure prediction model is to improve the performance of cloud applications by reducing the number of failed jobs. In order to investigate the behavior of failure and apply the prediction of failure to the large-scale environment, we used three different traces, namely Google Cluster Trace, Mustang and Trinity. Moreover, we have evaluated the proposed model performance using different evaluation metrics to ensure that the proposed model provides the highest accuracy of predicted values. The proposed model is designed and implemented to achieve high accuracy for failure prediction, regardless of whether the model uses a large or small trace size. The evaluation results show that our proposed model achieved a high precision, recall and f1 score.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".