中国邮电高校学报(英文版) ›› 2022, Vol. 29 ›› Issue (6): 36-45.doi: 10.19682/j.cnki.1005-8885.2022.1022

• Special Topic: Optical Communication and Artificial Intelligence • 上一篇    下一篇

Deep learning-based symbol detection algorithm in IMDD-OOFDM system

Zhang Huibin, Li Tianzhu, Liu Haojiang, Li Zhuotong   

  1. Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • 收稿日期:2022-09-07 修回日期:2022-10-18 出版日期:2022-12-30 发布日期:2022-12-30
  • 通讯作者: Zhang Huibin E-mail:zhanghuibin@bupt.edu.cn
  • 基金资助:

    This work was supported by the National Natural Science Foundation of China (61831003).

Deep learning-based symbol detection algorithm in IMDD-OOFDM system

Zhang Huibin, Li Tianzhu, Liu Haojiang, Li Zhuotong   

  1. Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2022-09-07 Revised:2022-10-18 Online:2022-12-30 Published:2022-12-30
  • Contact: Zhang Huibin E-mail:zhanghuibin@bupt.edu.cn
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61831003).

摘要:

In the current research on intensity-modulation and direct-detection optical orthogonal frequency division multiplexing ( IMDD-OOFDM ) system, effective channel compensation is a key factor to improve system performance. In order to improve the efficiency of channel compensation, a deep learning-based symbol detection algorithm is proposed in this paper for IMDD-OOFDM system. Firstly, a high-speed data streams symbol synchronization algorithm based on a training sequence is used to ensure accurate symbol synchronization. Then the traditional channel estimation and channel compensation are replaced by an echo state network (ESN) to restore the transmitted signal. Finally, we collect the data from the system experiment and calculate the signal-to-noise ratio (SNR). The analysis of the SNR optimized by the ESN proves that the ESN-based symbol detection algorithm is effective in compensating nonlinear distortion.

关键词:

echo state network(ESN), channel estimation, channel compensation, symbol synchronization, training sequence

Abstract: In the current research on intensity-modulation and direct-detection optical orthogonal frequency division multiplexing ( IMDD-OOFDM ) system, effective channel compensation is a key factor to improve system performance. In order to improve the efficiency of channel compensation, a deep learning-based symbol detection algorithm is proposed in this paper for IMDD-OOFDM system. Firstly, a high-speed data streams symbol synchronization algorithm based on a training sequence is used to ensure accurate symbol synchronization. Then the traditional channel estimation and channel compensation are replaced by an echo state network (ESN) to restore the transmitted signal. Finally, we collect the data from the system experiment and calculate the signal-to-noise ratio (SNR). The analysis of the SNR optimized by the ESN proves that the ESN-based symbol detection algorithm is effective in compensating nonlinear distortion.

Key words: echo state network(ESN), channel estimation, channel compensation, symbol synchronization, training sequence

中图分类号: