Conference paper
Gaussian Process Regression for WDM System Performance Prediction
MLytico1
Department of Photonics Engineering, Technical University of Denmark2
Networks Technology and Service Platforms, Department of Photonics Engineering, Technical University of Denmark3
Ultra-fast Optical Communication, Department of Photonics Engineering, Technical University of Denmark4
Centre of Excellence for Silicon Photonics for Optical Communications, Centers, Technical University of Denmark5
Gaussian process regression is numerically and experimentally investigated to predict the bit error rate of a 24 x 28 CiBd QPSK WDM system. The proposed method produces accurate predictions from multi-dimensional and sparse measurement data.
| Language: | English |
|---|---|
| Publisher: | Optical Society of America (OSA) |
| Year: | 2017 |
| Pages: | 1-3 |
| Proceedings: | Optical Fiber Communication Conference 2017 |
| ISBN: | 1509062297 , 1943580235 , 9781509062294 and 9781943580231 |
| Types: | Conference paper |
| DOI: | 10.1364/OFC.2017.Tu3D.7 |
| ORCIDs: | Piels, Molly and Zibar, Darko |
Data models Gaussian process regression Gaussian processes Ground penetrating radar Predictive models QPSK WDM system System performance Training Wavelength division multiplexing bit error rate error statistics multidimensional measurement data quadrature phase shift keying regression analysis sparse measurement data wavelength division multiplexing
