Automated Traces-based Anomaly Detection and Root Cause Analysis in Cloud Platforms
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Current cloud infrastructures and their applications are increasingly complex, with confounding relationships among application elements and cloud infrastructure components. This makes timely identification of the root causes for faults that occur in such systems an important-yet-challenging task. In this paper, we propose a solution that automatically builds a correlation model and an anomaly detection model using kernel traces of cloud servers. The correlation model is used to capture the dependencies between the various elements of the cloud system while the anomaly detection model is used to identify anomalies related to specific elements of the system. Upon detection of a fault, our framework computes a dependency graph of detected anomalies using the models, which in turn is used to perform the root cause analysis. Evaluation results of our proposed framework on a Kubernetes cloud show that it can effectively find root causes of injected faults with an accuracy rate between 80% and 99.3%, with a low false negative rate.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it