Machine Learning-Based Proactive Fault Monitoring and Prediction in GPON Networks
Bibliographic record
Abstract
Advanced fault management techniques beyond conventional reactive procedures are required due to the widespread use of Gigabit Passive Optical Networks (GPON) as essential infrastructure for high-speed internet services.  In order to anticipate connectivity problems before service degradation happens, this study introduces a revolutionary proactive fault detection and monitoring system that combines machine learning algorithms with real-time network analytics. Our hybrid technique addresses class imbalance issues while preserving real-world representativeness by combining meticulously vetted synthetic samples with real failure data from Telekom Malaysia's operational GPON infrastructure. In order to forecast five different fault categories—Line Disconnect, Intermittent Failures, Service Down, Frequent Disconnections, and Normal Operation—the system examines crucial network data such as optical power levels, signal-to-noise ratio, reflectance measures, and signal attenuation. Our Support Vector Machine solution achieved 97% classification accuracy with balanced precision and recall across all fault types after thorough evaluation utilizing several machine learning methods. During a six-month operational trial, the implementation of a web-based monitoring dashboard showed practical success with a mean time to fault resolution reduction of almost 60%. Crucially, this study clearly defines the parameters for model generalizability across various network topologies and operating situations and offers an open discussion of the constraints of synthetic data.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".