TY - GEN
T1 - CNN based OSNR estimation method for long haul optical fiber communication systems
AU - Wang, Ziyi
AU - Yang, Aiying
AU - Guo, Peng
AU - Feng, Lihui
AU - He, Pinjing
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/28
Y1 - 2018/12/28
N2 - The optical signal-to-noise ratio (OSNR) is an critical factor in evaluating the performance of high speed optical fiber communication systems. In this work, we propose a convolutional neural network (CNN) and constellation diagrams based method to simultaneously estimate OSNR. In the training step, CNN extracts the essential features of the input constellation diagrams. Then, with the built model in the training step, the CNN outputs the OSNR of the signal under test. The simulation by VPI software is carried on a 9-channel long haul optical transmission system with the launched optical power of -3.0∼+3.0dBm per channel and transmission distance up to 1000 km. The accuracy of OSNR estimation is almost 100%. The results show that the maximum test error of OSNR is less than 1.0 dB with the reference OSNR varied in the range of 15∼30 dB (or 15.5∼29.5 dB) for QPSK, 8PSK, 16QAM, and 20∼35 dB (or 20.5∼34.5) for 64QAM signal.
AB - The optical signal-to-noise ratio (OSNR) is an critical factor in evaluating the performance of high speed optical fiber communication systems. In this work, we propose a convolutional neural network (CNN) and constellation diagrams based method to simultaneously estimate OSNR. In the training step, CNN extracts the essential features of the input constellation diagrams. Then, with the built model in the training step, the CNN outputs the OSNR of the signal under test. The simulation by VPI software is carried on a 9-channel long haul optical transmission system with the launched optical power of -3.0∼+3.0dBm per channel and transmission distance up to 1000 km. The accuracy of OSNR estimation is almost 100%. The results show that the maximum test error of OSNR is less than 1.0 dB with the reference OSNR varied in the range of 15∼30 dB (or 15.5∼29.5 dB) for QPSK, 8PSK, 16QAM, and 20∼35 dB (or 20.5∼34.5) for 64QAM signal.
KW - CNN
KW - OSNR
KW - constellation
UR - http://www.scopus.com/inward/record.url?scp=85061452530&partnerID=8YFLogxK
U2 - 10.1109/ACP.2018.8596136
DO - 10.1109/ACP.2018.8596136
M3 - Conference contribution
AN - SCOPUS:85061452530
T3 - Asia Communications and Photonics Conference, ACP
BT - 2018 Asia Communications and Photonics Conference, ACP 2018
PB - OSA - The Optical Society
T2 - 2018 Asia Communications and Photonics Conference, ACP 2018
Y2 - 26 October 2018 through 29 October 2018
ER -