Evaluating Machine Learning Models for QoT Estimation
| Autor: | Joao Pedro, Rui Manuel Morais |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry Generalization Provisioning 02 engineering and technology Machine learning computer.software_genre k-nearest neighbors algorithm Support vector machine 020210 optoelectronics & photonics Knowledge base Transmission (telecommunications) 0202 electrical engineering electronic engineering information engineering Artificial intelligence business Software-defined networking computer |
| Zdroj: | ICTON 2018 20th International Conference on Transparent Optical Networks (ICTON) |
| DOI: | 10.1109/icton.2018.8473941 |
| Popis: | This work evaluates the effectiveness of various machine learning (ML) models when used to predict the Quality of Transmission (QoT) of an unestablished lightpath, speeding up the process of lightpath provisioning. Three network scenarios to efficiently generate the knowledge database used to train the models are proposed as well as an overview of the most used ML models. The considered models are: K nearest neighbors (KNN), logistic regression, support vector machines (SVM), and artificial neural networks (ANN). Results show that, in general, all ML models are able to correctly predict the QoT of more than 95% of the lightpaths. However, ANN is the model presenting better generalization, correctly predicting the QoT of up to 99.9% of of the lightpaths. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|