北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (5): 27-33.doi: 10.13190/j.jbupt.2020-084

• 论文 • 上一篇    下一篇

面向多模态数据的混合型FIB

王彬志1, 李卓1, 罗蓬2, 马天祥2, 刘开华1   

  1. 1. 天津大学 微电子学院, 天津 300072;
    2. 国网河北省电力有限公司 电力科学研究院, 石家庄 050021
  • 收稿日期:2020-07-10 发布日期:2021-03-11
  • 通讯作者: 李卓(1984-),男,副教授,硕士生导师,E-mail:zli@tju.edu.cn. E-mail:zli@tju.edu.cn
  • 作者简介:王彬志(1997-),男,硕士生.
  • 基金资助:
    国家自然科学基金项目(61602346);河北省重点研发计划项目(20314301D);天津大学北洋学者青年骨干教师项目(2020XRG-0102)

A Hybrid Forwarding Information Base for Multi-Modal Data

WANG Bin-zhi1, LI Zhuo1, LUO Peng2, MA Tian-xiang2, LIU Kai-hua1   

  1. 1. School of Microelectronics, Tianjin University, Tianjin 300072, China;
    2. Electric Power Research Institute, Hebei Electric Power Corporation, Shijiazhuang 050021, China
  • Received:2020-07-10 Published:2021-03-11

摘要: 针对未来网络转发信息库(FIB)中多模态数据带来的差异化快速索引、高效存储转发信息和多模态数据最长前缀匹配等问题,设计了一种支持多模态数据索引的混合型FIB,称为Hybrid-FIB.通过对不同类型的数据进行差异化处理,得到可供神经网络模型学习的输入向量,进而训练出能够实现均匀分布的神经网络混合索引模型.为了实现多模态数据最长前缀匹配,在片上静态随机存取存储器中部署两组Hybrid-FIB结构.实验结果表明,该混合型FIB在误判率、存储消耗及吞吐量等方面具备优异性能.

关键词: 信息中心网络, 多模态网络, 转发信息库, 神经网络

Abstract: In order to solve the problems of rapid indexing, efficient storage of forwarding information and longest prefix matching brought by multi-modal data in the forwarding information base(FIB) in the future network, a hybrid FIB based on neural networks, called Hybrid-FIB, which supports multi-modal data indexing is designed. Hybrid-FIB differentiates different type of data to obtain input vectors for neural network model, and then trains a neural network hybrid index model that can achieve uniform distribution. Experiments show that deploying two sets of Hybrid-FIB on the static random access memory can not only achieve the longest prefix matching of the multi-modal data, but also have better retrieval speed and misjudgment rate than the current network.

Key words: information-centric networking, polymorphic network, forwarding information base, neural network

中图分类号: