A Novel Artificial Neural Network Based on Hybrid PSO-BP Algorithm in the Application of Adaptive PMD Compensation System

  • Authors:

  • Ying Chen;Qiguang Zhu;Zhiquan Li

  • Affiliations:

  • Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China;Institute of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China;Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China

  • Venue:
  • ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
  • Year:
  • 2007

Quantified Score

Hi-index 0.05

Visualization

Abstract

An artificial neural network (ANN) based on hybrid algorithm combining particle swarm optimization (PSO) algorithm with back-propagation (BP) algorithm has been introduced to compensate the polarization mode dispersion (PMD) in the ultra-high speed optical communication system. The hybrid algorithm, also referred to as PSO-BP algorithm, has been adopted to train the weights of ANN, and it can make use of not only strong global searching ability of the PSO algorithm, but also strong local searching ability of the BP algorithm. In the proposed algorithm, a heuristic way was adopted to give a transition from particle swarm search to gradient descending search. The experimental results show that the hybrid algorithm is better than the Adaptive PSO algorithm and BP algorithm in convergent speed and convergent accuracy. And in the PMD compensation system, the ANN is used to optimize the degree of polarization (DOP) signal, which can achieve the random stochastic PMD compensation adaptively. Simulation results show the opening of eye diagram can be improved obviously.