Mitigation of time-varying distortions in Nyquist-WDM systems using machine learning
Carregando...
Data
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal de Minas Gerais
Descrição
Tipo
Artigo de periódico
Título alternativo
Primeiro orientador
Membros da banca
Resumo
We propose a machine learning-based nonsymmetrical demodulation technique relying on clustering to mitigate time-varying distortions derived from several impairments such as IQ imbalance, bias drift, phase noise and interchannel interference. Experimental results show that those impairments cause centroid movements in the received constellations seen in time-windows of 10k symbols in controlled scenarios. In our demodulation technique, the k-means algorithm iteratively identifies the cluster centroids in the constellation of the received symbols in short time windows by means of the optimization of decision thresholds for a minimum BER. We experimentally verified the effectiveness of this computationally efficient technique in multicarrier 16QAM Nyquist-WDM systems over 270 km links. Our nonsymmetrical demodulation technique outperforms the conventional QAM demodulation technique, reducing the OSNR requirement up to ∼0.8 dB at a BER of 1 × 10−2 for signals affected by interchannel interference.
Abstract
Assunto
Aprendizado do computador, Sistemas de comunicação em banda larga
Palavras-chave
A nonsymmetrical demodulation technique based on the k-means algorithm is proposed. The proposed technique is experimentally validated in overlapped WDM channels., OSNR requirements are reduced in B2B and 270 km for different carrier spacings. The technique decreases the BER being agnostic to the type of distortion source.
Citação
Departamento
Curso
Endereço externo
https://www.sciencedirect.com/science/article/pii/S106852001730113X