计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230200128-10.doi: 10.11896/jsjkx.230200128

• 大数据&数据科学 • 上一篇    下一篇

基于配置语句树的网络设备配置异常检测算法

沈袁程1, 班瑞2, 陈昕1, 华润多2, 汪云海1   

  1. 1 山东大学计算机科学与技术学院 山东 青岛 266200
    2 中讯邮电咨询设计院有限公司 北京 100000
  • 发布日期:2023-11-09
  • 通讯作者: 汪云海(cloudseawang@gmail.com)
  • 作者简介:(202135158@mail.sdu.edu.cn)
  • 基金资助:
    国家重点研发计划(2022ZD0160805);面向泛在计算环境大数据可视分析的人机交互理论与方法(62141217)

Anomaly Detection Algorithm for Network Device Configuration Based on Configuration Statement Tree

SHEN Yuancheng1, BAN Rui2, CHEN Xin1, HUA Runduo2, WANG Yunhai1   

  1. 1 School of Computer Science and Technology,Shandong University,Qingdao,Shandong 266200,China
    2 China Information Technology Designing & Consulting Institute,Beijing 100000,China
  • Published:2023-11-09
  • About author:SHEN Yuancheng,born in 1998,postgraduate.His main research interests include data visualization and interactive data exploration and analysis system.
    WANG Yunhai,born in 1984,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include visual analysis of big data,human-computer interaction and computer graphics.
  • Supported by:
    National Key R & D Program of China(2022ZD0160805) and Human Computer Interaction Theory and Methods for Visual Analysis of Big Data in Ubiquitous Computing Environment(62141217).

PDF (PC)

581

摘要： 随着网络通信设备的发展,设备配置异常引发的问题日益显著。传统的检测工具通常只针对拼写、格式等进行检测,无法检测逻辑问题。因此,目前的配置异常检测工作高度依赖工程师经验。为了提高网络服务质量并减少工程师的重复工作,以及解决传统工具检测速度慢、检测能力弱、通用性差等问题,文中借鉴了抽象语法树的设计理念,创新性地提出了一种基于“配置语句树”的无监督异常检测算法。通过统计分析,该算法可以确定7种可检测异常类型,并支持异常定位和异常修改方案的推荐。文中采用运营商现网运营中的配置,根据算法可检测种类、运行时间、准确率和召回率这几个指标进行量化评估和对比分析。实验结果表明,该算法具有良好的鲁棒性,完全能够有效应对网络设备配置异常引发的网络通信问题。

关键词: 异常检测, 聚类分析, 设备自动巡检, 抽象语法树, 共现语料分析, 无监督学习, 关联分析

Abstract: The problem of device configuration anomalies is becoming increasingly significant with the development of network communication equipment.Traditional detection tools usually only detect spelling,formatting and other issues,and cannot identify logic problems.Consequently,engineers’ experience plays a critical role in detecting such anomalies.To improve network service quality,reduce repetitive work,and address issues like slow detection speed,weak detection capabilities,and poor versatility of traditional tools,this paper draws on the design concept of abstract syntax trees and proposes an innovative unsupervised anomaly detection algorithm based on “configuration statement trees.” It can identify seven types of detectable anomalies and provides recommendations for anomaly localization and modification plans.The paper evaluates and compares the algorithm based on indicators such as detectable types,runtime,accuracy,and recall using configurations from the operator’s current network operation.The results demonstrate that the algorithm has good robustness and can effectively address network communication issues resulting from configuration anomalies in network communication equipment.

Key words: Anomaly detection, Cluster analysis, Automatic inspection of equipment, Abstract syntax tree, Co-occurrence corpus analysis, Unsupervised learning, Association analysis

中图分类号: 

  • TP301
[1]WILLIS P J.The challenges in building a carrier-scale IP net-work[J].BT Technology,2000,18(3):11-14.
[2]GOZDE B,ALIDSMAN A.AHP integrated TOPSIS and VIKORmethods with Pythagorean fuzzy sets to prioritize risks in self-driving vehicles[J].Applied Soft Computing,2021,99(3):1568-4946.
[3]SIRIWARDHANA Y,PORAMBAGE P,LIYANAGE M,et al.A survey on mobile augmented reality with 5G mobile edge computing:architectures,applications,and technical aspects[J].IEEE Communications Surveys & Tutorials,2021,23(2):1160-1192.
[4]LIU G H,MENG X C,ZHOU X R,et al.Exploring the optimization of China Unicom packet domain IP bearer network architecture for 5G[J].Telecommunications Technology,2019(12):95-98.
[5]WANG W Q.PTN network inspection solution for LTE[J].Science and Technology Innovation,2020(27):62-63.
[6]LIU H M,CHEN G.Innovative research and practice of net-work operation and maintenance system based on centralization and intelligence[J].China New Communication,2015,17(2):68-71.
[7]CUI J.Introduction to the construction of intelligent operation and maintenance mode of 5G network[J].Technology and Market,2021,28(5):126-127.
[8]THEO A,NATALI H,SANNE K,et al.In AI we trust? Perceptions about automated decision-making by artificial intelligence[J].AI & SOCIETY,2020,35(3):611-623.
[9]GUPTA S,SACHIN M,SAMADRITA,et al.Artificial intelli-gence for decision support systems in the field of operations research:review and future scope of research[J].Annals of Operations Research,2022,308(1):215-274.
[10]LIU X W,MA D D,YE X B,et al.Application of AI based Configuration Audit System in 5G Backhaul Network[J].Designing Techniques of Posts and Telecommunications,2021(8):15-19.
[11]LIN T L,CHEN J G,GUO W J,et al.Application of big data analysis methods in 5G precision construction[J].Changjiang Information and Communication,2022,35(6):230-232.
[12]HOFMANN M J,BIEMANN C,WESTBURY C,et al.SimpleCo-Occurrence Statistics Reproducibly Predict Association Ratings[J].Cogn Sci,2018,42(7):2287-2312.
[13]ZHANG J,WANG X,ZHANG H,et al.A novel neural source code representation based on abstract syntax tree[C]//2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE).IEEE,2019:783-794.
[14]SINAGA K P,YANG M S.Unsupervised K-Means clusteringalgorithm[J].IEEE access,2020,8:80716-80727.
[15]LIU X,ZHU P D,MI Q,et al.Rule-based anomaly detection for inter-domain routing systems[J].Journal of the National University of Defense Technology,2006(3):71-76.
[16]SMRITHY G S,RAMADOSS B.A Statistical-Based Light-Weight Anomaly Detection Framework for Wireless Body Area Networks[J].The Computer Journal,2022,65(7):1752-1759.
[17]YU Y J,YIN Y F,LIU Q.Analysis of the distribution pattern of high-frequency Chinese character string mutual information based on large-scale corpus[J].Computer Science,2014,41(10):276-282.
[18]PINCOMBE B.Anomaly Detection in Time Series of GraphsUsing ARMA Processes[J].Asor Bulletin,2005,24(1):67-75.
[19]ROODBANDI J,SADAT A,CHOOBINEH A,et al.Research outputs in ergonomics and human factors engineering:a bibliometric and co-word analysis of content and contributions[J].International Journal of Occupational Safety and Ergonomics,2022,28(4):2010-2021.
[20]LIU D P,ZHAO Y J,XU H W,et al.Opprentice:TowardsPractical and Automatic Anomaly Detection through Machine Learning[C]//15th Internet Measurement Conference.Tokyo,Japan.New York:ACM,2015:211-224.
[21]YANG X W,LATECKI L J,POKRAJAC D.Outlier Detection with Globally Optimal Exemplar-based GMM[C]//International Conference on Data Mining.SDM,Sparks,Nevada,USA.New York:SDM,2009:145-154.
[22]RASHIDI L,HASHEMI S,HAMZEH A.Anomaly detection in categorical datasets using bayesian networks[C]//International Conference on Artificial Intelligence and Computational Intelligence.2011:610-619.
[23]SHABTAY,LIOR,et al.A guided FP-Growth algorithm formining multitude-targeted item-sets and class association rules in imbalanced data[J].Information Sciences,2021,553(1):353-375.
[24]MAHDI B,SOHEIL E,MOHAMMAD G,et al.Approximating edit distance in truly subquadratic time:Quantum and mapreduce[J].Journal of the ACM,2021,68(3):1-41.
[25]MERIGOUX D,MONAT R,PROTZENKO J.A modern compiler for the french tax code[C]//Proceedings of the 30th ACM SIGPLAN International Conference on Compiler Construction.2021.
[26]DONG Z B.Analytical and Research on 3D Point Cloud Segmentation Algorithm Based on Improved Euclidean Distance [D].Beijing:North China Electric Power University,2022:4-38.
[27]CAO J D.Research on cryptographic table encryption algorithm based on Hash function and triplet [J].Software Guide,2012,11(11):54-56.
[28]ZHAO X H.Research on encryption method based on DNAcomputing[D].Zhengzhou:Zhengzhou Institute of Light Industry,2013.
[29]YI J,QIU M X.Design of user password authentication scheme based on ACSII code and random numbers[J].Computer and Digital Engineering,2011,39(3):102-104.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发