Cardinality Estimation in a Virtualized Network Device Using Online Machine Learning

被引:18
|
作者
Cohen, Reuven [1 ]
Nezri, Yuval [1 ]
机构
[1] Technion, Dept Comp Sci, IL-32000 Haifa, Israel
关键词
Cardinality estimation; machine learning;
D O I
10.1109/TNET.2019.2940705
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Cardinality estimation algorithms receive a stream of elements, with possible repetitions, and return the number of distinct elements in the stream. Such algorithms seek to minimize the required memory and CPU resource consumption at the price of inaccuracy in their output. In computer networks, cardinality estimation algorithms are mainly used for counting the number of distinct flows, and they are divided into two categories: sketching algorithms and sampling algorithms. Sketching algorithms require the processing of all packets, and they are therefore usually implemented by dedicated hardware. Sampling algorithms do not require processing of all packets, but they are known for their inaccuracy. In this work we identify one of the major drawbacks of sampling-based cardinality estimation algorithms: their inability to adapt to changes in flow size distribution. To address this problem, we propose a new sampling-based adaptive cardinality estimation framework, which uses online machine learning. We evaluate our framework using real traffic traces, and show significantly better accuracy compared to the best known sampling-based algorithms, for the same fraction of processed packets.
引用
收藏
页码:2098 / 2110
页数:13
相关论文
共 50 条
  • [1] QardEst: Using Quantum Machine Learning for Cardinality Estimation of Join Queries
    Kittelmann, Florian
    Sulimov, Pavel
    Stockinger, Kurt
    PROCEEDINGS OF THE 1ST WORKSHOP ON QUANTUM COMPUTING AND QUANTUM-INSPIRED TECHNOLOGY FOR DATA-INTENSIVE SYSTEMS AND APPLICATIONS, Q-DATA, CO-LOCATED WITH ACM INTERNATIONAL CONFERENCE ON DATA MANAGEMENT, SIGMOD, 2024, : 2 - 13
  • [2] PostCENN: PostgreSQL with Machine Learning Models for Cardinality Estimation
    Woltmann, Lucas
    Olwig, Dominik
    Hartmann, Claudio
    Habich, Dirk
    Lehner, Wolfgang
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2021, 14 (12): : 2715 - 2718
  • [3] Survey of cardinality estimation techniques based on machine learning
    Yue W.
    Qu W.
    Lin K.
    Wang X.
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2024, 61 (02): : 413 - 427
  • [4] Machine Learning-assisted Management of a Virtualized Network
    Hayashi, Michiaki
    2018 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC), 2018,
  • [5] Distributed Online Learning of Fog Computing Under Nonuniform Device Cardinality
    Ren, Chenshan
    Lyu, Xinchen
    Ni, Wei
    Tian, Hui
    Liu, Ren Ping
    IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (01) : 1147 - 1159
  • [6] Hematocrit estimation using online sequential extreme learning machine
    Hieu Trung Huynh
    Won, Yonggwan
    Kim, Jinsul
    BIO-MEDICAL MATERIALS AND ENGINEERING, 2015, 26 : S2025 - S2032
  • [7] Modeling Virtualized Applications using Machine Learning Techniques
    Kundu, Sajib
    Rangaswami, Raju
    Gulati, Ajay
    Zhao, Ming
    Dutta, Kaushik
    ACM SIGPLAN NOTICES, 2012, 47 (07) : 3 - 14
  • [8] A Distributed Online Learning Approach to Detect Anomalies for Virtualized Network Slicing
    Wang, Weili
    Chen, Qianbin
    Liu, Tong
    He, Xiaoqiang
    Tang, Lun
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [9] CARDINALITY ESTIMATION IN NUMERIC ONLINE DATABASES
    JARVELIN, K
    INFORMATION PROCESSING & MANAGEMENT, 1986, 22 (06) : 523 - 548
  • [10] Online classification of user activities using machine learning on network traffic
    Labayen, Victor
    Magana, Eduardo
    Morato, Daniel
    Izal, Mikel
    COMPUTER NETWORKS, 2020, 181