Fast Response Prediction Method Based on Bidirectional Long Short-Term Memory for High-Speed Links

被引:8
|
作者
Luo, Yuhuan [1 ]
Chu, Xiuqin [1 ]
Yuan, Haiyue [1 ]
Wei, Tao [1 ]
Wang, Jun [1 ]
Wu, Feng [1 ]
Li, Yushan [1 ]
机构
[1] Xidian Univ, Minist Educ, Key Lab High Speed Circuit Design & EMC, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
Bidirectional long short-term memory (Bi-LSTM); high-speed link; nonlinearity; recurrent neural network (RNN); signal integrity (SI); EYE DIAGRAM; DESIGN;
D O I
10.1109/TMTT.2022.3233303
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
There is a recognized need to evaluate the performance of high-speed links accurately and quickly with increasing clock frequency. To evaluate the performance of the systems, the transient simulation method and the fast time-domain simulation method are adopted. Unfortunately, neither method can guarantee both the efficiency and accuracy of the results at the same time. In this article, a modeling method that can overcome the shortcomings of both the transient simulation method and the fast time-domain simulation method is proposed for obtaining responses of high-speed links based on bidirectional long short-term memory (Bi-LSTM). Here, the pulse response and response of a certain number of bits are first simulated or measured, which are used to determine training datasets. Then, the Bi-LSTM-based model uses the generated training datasets to build a precise model. Next, the developed model predicts the response of the high-speed link. Compared to the transient simulation method and fast time-domain simulation method, the results show that the proposed method can consider both accuracy and efficiency. In addition, 33 simulation experiments are performed to demonstrate the robustness of the proposed method. Finally, the accuracy of the proposed method is validated by comparing the measured and predicted results of the high-speed links with different nonlinearities.
引用
收藏
页码:2347 / 2359
页数:13
相关论文
共 50 条
  • [21] Analysis of River Management Method Based on Improved Bidirectional Long Short-Term Memory Network for Water Quality Prediction
    Wang, Zhongya
    Liu, Shuang
    WATER CONSERVATION SCIENCE AND ENGINEERING, 2025, 10 (01)
  • [22] A water quality prediction method based on the multi-time scale bidirectional long short-term memory network
    Qinghong Zou
    Qingyu Xiong
    Qiude Li
    Hualing Yi
    Yang Yu
    Chao Wu
    Environmental Science and Pollution Research, 2020, 27 : 16853 - 16864
  • [23] A water quality prediction method based on the multi-time scale bidirectional long short-term memory network
    Zou, Qinghong
    Xiong, Qingyu
    Li, Qiude
    Yi, Hualing
    Yu, Yang
    Wu, Chao
    ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2020, 27 (14) : 16853 - 16864
  • [24] Short-Term Load Forecasting Method Based on Bidirectional Long Short-Term Memory Model with Stochastic Weight Averaging Algorithm
    Zhu, Qingyun
    Zeng, Shunqi
    Chen, Minghui
    Wang, Fei
    Zhang, Zhen
    ELECTRONICS, 2024, 13 (15)
  • [25] Bidirectional Long Short-Term Memory Method for Weather Prediction in Terms of Evacuation of River Drifting Victims
    Wardani, Arin Kusuma
    Kristalina, Prima
    Hadi, Mochammad Zen Samsono
    Pratiarso, Aries
    2024 INTERNATIONAL ELECTRONICS SYMPOSIUM, IES 2024, 2024, : 663 - 668
  • [26] A short-term prediction model of global ionospheric VTEC based on the combination of long short-term memory and convolutional long short-term memory
    Peng Chen
    Rong Wang
    Yibin Yao
    Hao Chen
    Zhihao Wang
    Zhiyuan An
    Journal of Geodesy, 2023, 97
  • [27] A short-term prediction model of global ionospheric VTEC based on the combination of long short-term memory and convolutional long short-term memory
    Chen, Peng
    Wang, Rong
    Yao, Yibin
    Chen, Hao
    Wang, Zhihao
    An, Zhiyuan
    JOURNAL OF GEODESY, 2023, 97 (05)
  • [28] An Improved Initialization Method for Fast Learning in Long Short-Term Memory-Based Markovian Spectrum Prediction
    Radhakrishnan, Niranjana
    Kandeepan, Sithamparanathan
    IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2021, 7 (03) : 729 - 738
  • [29] Simplified long short-term memory model for robust and fast prediction
    Liu, Yong
    Hao, Xin
    Zhang, Biling
    Zhang, Yuyan
    PATTERN RECOGNITION LETTERS, 2020, 136 (136) : 81 - 86
  • [30] Short-term natural gas consumption prediction based on wavelet transform and bidirectional long short-term memory optimized by Bayesian network
    Li, Zhaoyang
    Liu, Liang
    Qiao, Weibiao
    ENERGY SCIENCE & ENGINEERING, 2022, 10 (09) : 3281 - 3300