Beyond the Norm: Unsupervised Anomaly Detection in Telecommunications with Mahalanobis Distance
Bibliographic record
Abstract
Anomaly Detection (AD) in telecommunication networks is critical for maintaining service reliability and performance. However, operational networks present significant challenges: high-dimensional Key Performance Indicator (KPI) data collected from thousands of network elements must be processed in near real time to enable timely responses. This paper presents an unsupervised approach leveraging Mahalanobis Distance (MD) to identify network anomalies. The MD model offers a scalable solution that capitalizes on multivariate relationships among KPIs without requiring labeled data. Our methodology incorporates preprocessing steps to adjust KPI ratios, normalize feature distributions, and account for contextual factors like sample size. Aggregated anomaly scores are calculated across hierarchical network levels—cells, sectors, and sites—to localize issues effectively. Through experimental evaluations, the MD approach demonstrates consistent performance across datasets of varying sizes, achieving competitive Area Under the Receiver Operating Characteristic Curve (AUC) values while significantly reducing computational overhead compared to baseline AD methods: Isolation Forest (IF), Local Outlier Factor (LOF) and One-Class Support Vector Machines (SVM). Case studies illustrate the model’s practical application, pinpointing the Random Access Channel (RACH) success rate as a key anomaly contributor. The analysis highlights the importance of dimensionality reduction and tailored KPI adjustments in enhancing detection accuracy. This unsupervised framework empowers telecom operators to proactively identify and address network issues, optimizing their troubleshooting workflows. By focusing on interpretable metrics and efficient computation, the proposed approach bridges the gap between AD and actionable insights, offering a practical tool for improving network reliability and user experience.
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 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".