Multibit Tries Packet Classification with Deep Reinforcement Learning

被引:3
|
作者
Jamil, Hasibul [1 ]
Weng, Ning [1 ]
机构
[1] Southern Illinois Univ, Dept Elect & Comp Engn, Carbondale, IL 62901 USA
关键词
packet classification; machine learning; and optimization;
D O I
10.1109/hpsr48589.2020.9098974
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
High performance packet classification is a key component to support scalable network applications like firewalls, intrusion detection, and differentiated services. With ever increasing in the line-rate in core networks, it becomes a great challenge to design a scalable and high performance packet classification solution using hand-tuned heuristics approaches. In this paper, we present a scalable learning-based packet classification engine and its performance evaluation. By exploiting the sparsity of ruleset, our algorithm uses a few effective bits (EBs) to extract a large number of candidate rules with just a few of memory access. These effective bits are learned with deep reinforcement learning and they are used to create a bitmap to filter out the majority of rules which do not need to be full-matched to improve the online system performance. Moreover, our EBs learning-based selection method is independent of the ruleset, which can be applied to varying rulesets. Our multibit tries classification engine outperforms lookup time both in worst and average case by 55% and reduce memory footprint, compared to traditional decision tree without EBs.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Packet classification using two-dimensional multibit tries
    Lu, WC
    Sahni, S
    10TH IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, PROCEEDINGS, 2005, : 849 - 854
  • [2] Efficient 2D Multibit Tries for Packet Classification
    Lu, Wencheng
    Sahni, Sartaj
    IEEE TRANSACTIONS ON COMPUTERS, 2009, 58 (12) : 1695 - 1709
  • [3] Packet classification using space-efficient pipelined multibit tries
    Lu, Wencheng
    Sahni, Sartaj
    IEEE TRANSACTIONS ON COMPUTERS, 2008, 57 (05) : 591 - 605
  • [4] Deep reinforcement learning for imbalanced classification
    Enlu Lin
    Qiong Chen
    Xiaoming Qi
    Applied Intelligence, 2020, 50 : 2488 - 2502
  • [5] Deep reinforcement learning for imbalanced classification
    Lin, Enlu
    Chen, Qiong
    Qi, Xiaoming
    APPLIED INTELLIGENCE, 2020, 50 (08) : 2488 - 2502
  • [6] Many-field packet classification with decomposition and reinforcement learning
    Jamil, Hasibul
    Yang, Ning
    Weng, Ning
    IET NETWORKS, 2022, 11 (3-4) : 112 - 127
  • [7] Improving Hierarchical Tree-Based Packet Classification by Reinforcement Learning
    Ou, Zhi-Xing
    Shih, Wen-Chi
    Hsieh, Tsung-Yu
    Chang, Yeim-Kuan
    2024 FIFTEENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS, ICUFN 2024, 2024, : 336 - 341
  • [8] Efficient construction of multibit tries for IP lookup
    Sahni, S
    Kim, KS
    IEEE-ACM TRANSACTIONS ON NETWORKING, 2003, 11 (04) : 650 - 662
  • [9] Toward Packet Routing With Fully Distributed Multiagent Deep Reinforcement Learning
    You, Xinyu
    Li, Xuanjie
    Xu, Yuedong
    Feng, Hui
    Zhao, Jin
    Yan, Huaicheng
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2022, 52 (02): : 855 - 868
  • [10] A Optimal Packet Delivery Strategy Based on Deep Reinforcement Learning in IoV
    Liao, Xiwen
    Leng, Supeng
    Xiong, Kai
    Wei, Yunkai
    2021 6TH INTERNATIONAL CONFERENCE ON UK-CHINA EMERGING TECHNOLOGIES (UCET 2021), 2021, : 146 - 151