首页 > 论文 > Chinese Optics Letters > 17卷 > 7期(pp:07)

Traffic Estimation Based on Long Short-Term Memory Neural Network for Mobile Front-Haul with XG-PON

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
分享:

摘要

A novel predictive dynamic bandwidth allocation (DBA) method based on Long Short-Term Memory (LSTM) neural network is proposed for 10-Gigabit-capable passive optical network in mobile front-haul (MFH) links. By predicting the number of packets that arrive at the optical network unit buffer based on LSTM, the round-trip time delay in traditional DBAs can be eliminated to meet the strict latency requirement for MFH links. Our study shows that LSTM has better performance than feed-forward neural network. Based on extensive simulations, the proposed scheme is found to be able to achieve the latency requirement for MFH and outperforms the traditional DBAs in terms of delay, jitter and packet loss ratio.

Newport宣传-MKS新实验室计划
补充资料

作者单位:

    University of Electronic Science and Technology of China
    University of Electronic Science and Technology of China
    University of International Business and Economics
    University of Electronic Science and Technology of China
    University of Electronic Science and Technology of China
    University of Electronic Science and Technology of China

引用该论文

Zhang Min,Xu Bo,Li Xiaoyun,Cai Yi,Wu Baojian,Qiu Kun. Traffic Estimation Based on Long Short-Term Memory Neural Network for Mobile Front-Haul with XG-PON[J].Chinese Optics Letters,2019,17(7):07.