Telecommunications Science ›› 2020, Vol. 36 ›› Issue (3): 61-70.doi: 10.11959/j.issn.1000-0801.2020054

• Research and Development • Previous Articles     Next Articles

Overview of research on fiber nonlinear equalization algorithm based on artificial intelligence

Yajie LI,Yongli ZHAO,Shoudong LIU,Jie ZHANG()   

  1. State Key Laboratory of Information Photonics and Optical Communications,Beijing University of Posts and Telecommunications,Beijing 100876,China
  • Revised:2020-02-25 Online:2020-03-20 Published:2020-03-26
  • Supported by:
    The Technology Project of State Grid Corporation of China(5100-201940006A-0-0-00)


The necessity and importance of nonlinear equalization algorithm in optical transmission systems were outlined.The principle of classical nonlinear equalization algorithm was described,and the shortcomings and limitations of classical algorithms were presented.Combined with the status in recent years,four kinds of nonlinear equalization algorithms based on artificial intelligence were introduced in detail.These algorithms include artificial neural networks,support vector machine,unsupervised clustering and deep neural network.All the nonlinear equalization algorithms mentioned were compared in terms of performance,complexity,instantaneity and application flexibility.Finally,the future development trend of nonlinear equalization algorithm based on artificial intelligence was analyzed.

Key words: nonlinear equalization, artificial neural network, support vector machine, clustering, deep neural network

CLC Number: 

No Suggested Reading articles found!