A SURVEY ON MACHINE LEARNING ALGORITHMS FOR SOFTWARE-DEFINED NETWORKS

Author:

Kanivets Z.1,Vybornova A.1

Affiliation:

1. The Bonch-Bruevich Saint-Petersburg State University of Telecommunications

Abstract

With the advent of the concept of Software-Defined Networks with a centralized control plane, it became possible to collect a huge amount of information about the network, for example, network topology, network congestion, the state of network devices. This data can be used to train machine learning algorithms. Moreover, these algorithms can be applied for completely different purposes, such as traffic classification, quality of service, optimization of traffic transmission routes, resource management, and security. Research subject of this article consist on the different aspects of SDN operating that can be optimized with ML. Research method is an analysis of the literature on the subject. Core results are analysis and classification of the areas and methods of the ML algorithms implementation for the SDN. Practical relevance of the work is that the results can be used for optimization of different SDN characteristics.

Publisher

Bonch-Bruevich State University of Telecommunications

Reference20 articles.

1. D. Clark, C. Partridge, J. Ramming, J. Wroclawski, “A Knowledge Plane for the In-ternet,” Proc SIGCOMM'03. 3-10, 2003.

2. G. Xu, Y. Mu, and J. Liu, “Inclusion of artifificial intelligence in communication networks and services,” ITU Journal: ICT Discoveries, no. 1, pp. 1–6, Oct. 2017.

3. P. Amaral, J. Dinis, P. Pinto, L. Bernardo, J. Tavares, and H. S. Mamede, “Machine learning in software defifined networks: Data collection and traffific classifification,” in Proc. IEEE ICNP’16, Singapore, Nov. 2016, pp. 1–5.

4. Koucheryavy A., Borodin A., Muthanna A., Abdellah A. R., Volkov A. Artificial Intelligence for Telecommunication Networks // 10TH International conference on advanced infotelecommunications, ICAIT 2021. РР. 8–18(in Russia).

5. R. Hajlaoui, H. Guyennet, and T. Moulahi, “A survey on heuristic-based routing methods in vehicular ad-hoc network: Technical challenges and future trends,” IEEE Sensors Journal, vol. 16, no. 17, pp. 6782–6792, Sept. 2016.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3