• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Automatic Estimation of Administrators' Intension in Intent-Based Networking

Research Project

Project/Area Number 19H04094
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 60060:Information network-related
Research InstitutionKyoto University

Principal Investigator

Okabe Yasuo  京都大学, 学術情報メディアセンター, 教授 (20204018)

Co-Investigator(Kenkyū-buntansha) 中村 素典  京都大学, 学術情報メディアセンター, 教授 (30268156)
Project Period (FY) 2019-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,030,000 (Direct Cost: ¥13,100,000、Indirect Cost: ¥3,930,000)
Fiscal Year 2023: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2022: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2021: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2020: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Fiscal Year 2019: ¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
KeywordsIntent-Based Networking / 機械学習 / ACL / 経路制御 / パッシブ計測 / Kubernetes / Intent Based Networking / ネットワーク管理自動化 / Network Modeling / 宣言的設定管理 / SDN / Lomb-Scargel法 / TCP輻輳制御 / DDoS攻撃 / 人工知能 / ネットワーク最適化
Outline of Research at the Start

ネットワークに何(What)を行わせようとしているかを高い抽象度の「意図」(intent)として記述し、それに従って各ネットワーク機器の設定を自動的に生成するIntent-Based Networkingにおいて、さらに管理者がネットワークの設計や運用において行っている判断を人工知能に学習させ、明示的に記述が困難な諸条件を学習データとして抽出し、システムに組み込めるようにすることで、大規模ネットワークの設計と運用、管理を真に自動化し、管理者の負担を軽減する技術を研究開発し、システムとして実装して、有効性を評価する。

Outline of Final Research Achievements

There is a lot of anticipation for Intent-Based Networking, which reduces the burden on administrators by describing what you want the network to do as a high-level “intent” when setting up a large-scale network, and then having the controller automatically generate the settings for each device according to that intent. However, the administrator's intent is often vague, contradictory, and also contains implicit assumptions. Therefore, we have researched and developed a technology to reduce the burden on administrators by automating the design, operation, and management of large-scale networks by having artificial intelligence learn the decisions that administrators make in network design and operation, and then incorporating them into the system.

Academic Significance and Societal Importance of the Research Achievements

本研究の特徴は現実に動作しているネットワークから人工知能により管理者の意図を推測しようとする点である。人工知能応用として、単に管理者が日常行っているネットワーク管理を人工知能に学習させ模倣させるだけのでは、学習データがブラックボックス化され、管理者の意図に反するものが含まれてしまってもそれが実際に使われるまでは顕在化しないという問題点がある。本研究では、管理者の動作そのものを学習させるのではなく、管理者が暗黙の前提や知識としているルールを学習し抽出して可読な形で出力させることでこの問題を回避しようとする点が独自であり、ネットワーク管理に限らず大規模な情報システムの運用に応用できる可能性がある。

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • Research Products

    (10 results)

All 2024 2023 2022 2021 2020

All Journal Article (5 results) (of which Peer Reviewed: 4 results) Presentation (5 results) (of which Int'l Joint Research: 4 results)

  • [Journal Article] Network State Estimation by Spectral Analysis of Passively Measured TCP Flows2024

    • Author(s)
      Kenta Murayama, Yasuo Okabe
    • Journal Title

      38th International Conference on Information Networking (ICOIN 2024)

      Volume: 2024 Pages: 373-378

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Partial Outsourcing of Malware Dynamic Analysis Without Disclosing File Contents2023

    • Author(s)
      Hamajima Keisuke、Kotani Daisuke、Okabe Yasuo
    • Journal Title

      2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)

      Volume: 2023 Pages: 717-722

    • DOI

      10.1109/compsac57700.2023.00098

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] TCP フローのパッシブ計測によるネットワークの状態推定2022

    • Author(s)
      村山健太、岡部寿男
    • Journal Title

      情報処理学会マルチメディア,分散,協調とモバイルシンポジウム2022論文集

      Volume: 2022 Pages: 539-549

    • Related Report
      2021 Annual Research Report
  • [Journal Article] Traffic-aware Access Control List Reconstruction2020

    • Author(s)
      Kei Wakabayashi, Daisuke Kotani, Yasuo Okabe
    • Journal Title

      International Conference on Information Networking (ICOIN)

      Volume: 34 Pages: 616-621

    • DOI

      10.1109/icoin48656.2020.9016512

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Network Routing Optimization Based on Machine Learning Using Graph Networks Robust against Topology Change2020

    • Author(s)
      Kaku Sawada, Daisuke Kotani, Yasuo Okabe
    • Journal Title

      International Conference on Information Networking (ICOIN)

      Volume: 34 Pages: 608-615

    • DOI

      10.1109/icoin48656.2020.9016573

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Presentation] 分散トレーシング手法を用いたKubernetes制御プレーンにおけるオブジェクトの連鎖的変更の観測手法の検討2023

    • Author(s)
      江平智之・小谷大祐・岡部寿男
    • Organizer
      電子情報通信学会インターネットアーキテクチャ研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] Precursory Analysis of Attack-Log Time Series by Machine Learning for Detecting Bots in CAPTCHA2021

    • Author(s)
      Tsuyoshi Arai, Yasuo Okabe, Yoshinori Matsumoto
    • Organizer
      35th International Conference on Information Networking (ICOIN2021)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Improving Attack Detection Performance in NIDS Using GAN2020

    • Author(s)
      Dongyang Li, Daisuke Kotani, Yasuo Okabe
    • Organizer
      2020 IEEE 44th Annual Computers, Software and Applications Conference (COMPSAC2020)
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Traffic-aware Access Control List Reconstruction2020

    • Author(s)
      Daisuke Kotani
    • Organizer
      2020 International Conference on Information Networking (ICOIN)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Network Routing Optimization Based on Machine Learning Using Graph Networks Robust against Topology Change2020

    • Author(s)
      Yasuo Okabe
    • Organizer
      2020 International Conference on Information Networking (ICOIN)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2019-04-18   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi