QoT estimation for unestablished lighpaths using machine learning
Optical Fiber Communication Conference, 2017•opg.optica.org
… To this aim, different data mining techniques can be applied, ranging from network kriging [2]
to machine learning (ML) [3]. In this paper, we apply a ML-based classifier to predict the
probability that the Bit-Error-Rate (BER) of a candidate lightpath will not exceed the system
tolerance threshold, using as features the traffic volume to be served, the modulation format, the
lightpath total length, the length of its longest link and the number of lighpath links. To train the
… For our experiments we use a Random Forest (RF) classifier with 100 estimators [7], as it is …
to machine learning (ML) [3]. In this paper, we apply a ML-based classifier to predict the
probability that the Bit-Error-Rate (BER) of a candidate lightpath will not exceed the system
tolerance threshold, using as features the traffic volume to be served, the modulation format, the
lightpath total length, the length of its longest link and the number of lighpath links. To train the
… For our experiments we use a Random Forest (RF) classifier with 100 estimators [7], as it is …
Abstract
We investigate a machine-learning technique that predicts whether the bit-error-rate of unestablished lightpaths meets the required threshold based on traffic volume, desired route and modulation format. The system is trained and tested on synthetic data.
opg.optica.org
Showing the best result for this search. See all results