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

2023 Fiscal Year Final Research Report

A compact packet classification method that realizes large scale NFV

Research Project

  • PDF
Project/Area Number 19K11953
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60060:Information network-related
Research InstitutionKanagawa University

Principal Investigator

Tanaka Ken  神奈川大学, 情報学部, 教授 (50272810)

Co-Investigator(Kenkyū-buntansha) 三河 賢治  前橋工科大学, 工学部, 教授 (00344838)
Project Period (FY) 2019-04-01 – 2024-03-31
Keywordsパケット分類 / 決定木 / RBT / C1P / Circ1P
Outline of Final Research Achievements

In this study, we realized a decision tree construction algorithm for C1P and Circ1P, which is necessary to realize fast packet classification for complex rule-based packet classification problems. We analyzed C1P in detail when the rule list is viewed as a binary matrix, and studied efficient methods for its determination and replacement. Based on the survey and analysis of relevant literature and classification, we conducted a detailed analysis of the operation of unifying the chain and its time-computing complexity. Based on these results, we developed algorithms for C1P and Circ1P, which are necessary to achieve fast packet classification. We conducted a computer experiment of the unification operation on a 108-bit chain, assuming an actual IP4 packet, and confirmed the effectiveness of the unification operation.

Translated with www.DeepL.com/Translator (free version)

Free Research Field

ネットワークセキュリティ

Academic Significance and Societal Importance of the Research Achievements

リモートワークの急激な普及に伴い、企業や官公庁、研究機関においてセキュリティの確保や機器性能の限界、ネットワーク運用の難しさなどが大きな問題となっている。NFVの下では、IPアドレスやプロトコルからセッション、アプリケーションなどの通信内容に応じたネットワーク構成の柔軟な変更が仮想環境上の高速なソフトウェアで実現される必要がある。本研究ではこの点に着目し、NFV環境の下で複雑な条件に従った高速なパケット分類アルゴリズムを構築した。考案した方法は、今後リモートワークを前提としたクラウドシステムへと移行する中で、汎用ハードウェアによって高度なネットワーク機能を実現するための必須の技術になる。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi