基于J48决策树的CDN域名检测方法
CDN Domain Name Detection Method Based on J48 Decision Tree
DOI: 10.12677/CSA.2021.117203, PDF,   
作者: 杜 飞, 李国静：北京锐驰信安技术有限公司，北京；王杉杉：中国联合网络通信有限公司河南省分公司，河南 郑州
关键词: 域名系统；内容分发网络；CDN；Domain Name System； Content Delivery Network； CDN
摘要: 内容分发网络(Content Delivery Network)是新兴的网络加速技术，可以避开互联网上影响数据传输速度和稳定性的瓶颈和环节，使内容传输更快、更稳定。CDN有效的利用DNS，将用户重定向到附近的CDN网络的边缘节点服务器来提高用户获取内容信息的效率和质量。DNS重定向技术的运用为CDN网络带来了显著的优势和灵活性。本文介绍了CDN的基础原理、工作流程及CDN域名监测的必要性，采用基于J48决策树算法对CDN域名进行检测，构建CDN基础资源库。实验结果表明，该算法能有效提高CDN域名检测的效率，准确率达到98.8%，召回率达到98.1%。
Abstract: Content Delivery Network is an emerging network acceleration technology. CDN can avoid bottle-necks and links on the Internet that affect the speed and stability of data transmission, that makes the content transfer faster and more stable. CDN effectively utilizes DNS that redirects user to the edge node server of the nearby CDN network to improve the efficiency and quality of the user’s access to content information. The application of DNS redirection technology brings significant advantages and flexibility to CDN. This paper introduces the basic principles, workflow, and the neces-sity of CDN domain name monitoring. It uses the J48 decision tree algorithm to detect CDN domain names and builds a basic CDN resource library. Experimental results show that the algorithm can effectively improve CDN domain name detection efficiency, with an accuracy rate of 98.8% and a recall rate of 98.1%.
文章引用：杜飞, 李国静, 王杉杉. 基于J48决策树的CDN域名检测方法[J]. 计算机科学与应用, 2021, 11(7): 1982-1993. https://doi.org/10.12677/CSA.2021.117203

参考文献

[1] 李聪颖, 王瑞刚, 梁小江. CDN技术的研究与设计[J]. 物联网技术, 2015, 5(12): 28-30.
[2] 熊明. CDN技术研究及在宽带中的应用[D]: [硕士学位论文]. 天津: 天津大学, 2015.
[3] 蒋杰. CDN系统的关键技术[J]. 数字通信世界, 2018(8): 12-13.
[4] 田光辉. 移动内容分发网络节点位置部署建模及部署方案研究[D]: [硕士学位论文]. 北京: 北京邮电大学, 2013.
[5] 张戈. 基于CDN的视频网络架构研究[J]. 电脑编程技巧与维护, 2018(12): 161-163.
[6] 唐宏, 陈戈, 陈步华, 余媛. 内容分发网络原理与实践[J]. 电信科学, 2018, 34(11): 181.
[7] 郎丰凯. CDN技术及发展趋势分析[J]. 电子世界, 2019(14): 106.
[8] 王海洋, 赵建福, 韩增辉, 王晟. 分布式CDN带来的挑战与应对方案[J]. 山东通信技术, 2018, 38(1): 22-25.
[9] 乔爱锋. CDN体系架构及运营部署方案[J]. 电信快报, 2018(10): 17-21.
[10] 罗明. 基于移动边缘计算的网络信息监测与缓存业务优化[D]: [硕士学位论文]. 北京: 北京邮电大学, 2019.
[11] 周昌令, 陈恺, 公绪晓, 等. 基于Passive DNS的速变域名检测[J]. 北京大学学报: 自然科学版, 2016, 52(3): 396-402.
[12] 薛景安. 大规模内容分发网络客户端映射性能测量与优化研究[D]: [博士学位论文]. 北京: 清华大学, 2018.
[13] 徐翔, 任昌燕, 管黎晨, 等. 一种高效的全球DNS智能调度系统研究[J]. 新一代信息技术, 2019, 2(22): 33-38.
[14] Jin, C., De-Lin, L. and Mu, F.-X. (2009) An Improved ID3 De-cision Tree Algorithm. 2009 4th International Conference on Computer Science & Education. Nanning, 25-28 July 2009, 127-130.
[15] 韩存鸽, 叶球孙. 决策树分类算法中C4.5算法的研究与改进[J]. 计算机系统应用, 2019, 28(6): 198-202.
[16] Mathuria, M. (2013) Decision Tree Analysis on J48 Algorithm for Data Mining. International Journal of Advanced Research in Computer Science and Software Engineering, 3, No. 6.
[17] Lewis, R.J. (2000) An Introduction to Classification and Regression Tree (CART) Analysis. Annual Meeting of the Society for Academic Emergency Medi-cine in San Francisco, California, 14.
[18] Al-Abbasi, A., Aggarwal, V., Lan, T., et al. (2019) FastTrack: Minimizing Stalls for CDN-Based Over-the-Top Video Streaming Systems. IEEE Transactions on Cloud Computing, 1, 1. [Google Scholar] [CrossRef] 
[19] Helt, J., Feng, G., Seshan, S., et al. (2019) Sandpaper: Mitigating Performance Interference in CDN Edge Proxies. Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, Ar-lington, 7-9 November 2019, 30-46. [Google Scholar] [CrossRef] 
[20] Flores, M. and Bedi, H. (2019) Caching the Internet: A View from a Global Multi-Tenant CDN. In: International Conference on Passive and Active Network Measurement, Springer, Cham, 68-81. [Google Scholar] [CrossRef] 
[21] Alabbasi, A.O. (2020) A Quantitative Framework for CDN-Based Over-the-Top Video Streaming Systems. Purdue University Graduate School, West Lafayette.