SYSTEMLENS: Integrating Performance Prediction, Anomaly Prediction and Root-Cause Localization for Self-Healing Software Systems
Bibliographic record
Abstract
Engineering self-adaptive systems for software applications necessitates accurate predictions about the state of the underlying application. These predictions can then be used to enable automated cloud operations, such as scaling services in microservices architectures. However, designing an effective selfadaptive system for software applications requires simultaneous predictions across multiple dimensions, including performance, anomalies, and their root causes. While numerous algorithms have been proposed to address performance prediction and anomaly detection, these models typically focus on a single dimension. In this paper, we propose SYSTEMLENS, a novel approach that integrates performance prediction, anomaly detection, and root-cause localization within a unified framework for microservice applications. SYSTEMLENS utilizes Graph Neural Networks (GNNs) and Gated Recurrent Units (GRUs) to first predict latency distributions for traces and the microservice calls involved in generating those traces. These latency distributions are further processed to identify trace-based anomalies and their root causes. By consolidating these tasks into a single model, SYSTEMLENS facilitates comprehensive system monitoring with improved correlations between predictions. We evaluate SYSTEMLENS on benchmark datasets from the domains of performance modeling and anomaly detection, demonstrating its effectiveness in providing an integrated and proactive monitoring solution.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".