Machine Learning Meets Communication Networks: Current Trends and Future Challenges

IEEE Access

Teemu Leppanen¹  Lauri Loven¹  Antti Yla-Jaaski²  Erkki Harjula²  Hassan Malik³  Thilo Sauter⁴  Mika Ylianttila⁵  Ali Hassan Sodhro⁶  Andrei Gurtov⁷  Shariar Shahabuddin⁸  Markku Juntti⁹  Ijaz Ahmad^1,10  Antti Anttonen^1,10  Jukka Riekki^1,11  Muhammad Mahtab Alam^1,12 

[1] Center for Ubiquitous Computing, University of Oulu, Oulu, Finland;Centre for Wireless Communications, University of Oulu, Oulu, Finland;Computer Science Department, Edge Hill University, Ormskirk, U.K.;Department of Computer Science, Aalto University, Espoo, Finland;Department of Computer and Information Science, Link&x00F6;Department of Computer and System Science, Mid-Sweden University, &x00D6;Institute of Computer Technology, TU Wien, Wien, Austria;Nokia, Nokia, Finland;Thomas Johann Seebeck Department of Electronics, Tallinn University of Technology, Tallinn, Estonia;VTT Technical Research Centre of Finland, Espoo, Finland;ping University, Link&x00F6;stersund, Sweden;

关键词: Communication networks;    machine learning;    physical layer;    MAC layer;    network layer;    SDN;   

DOI  :  10.1109/ACCESS.2020.3041765

来源: DOAJ

【 摘 要 】

The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future communicating devices and services. In this article, we provide a detailed account of current research on the application of ML in communication networks and shed light on future research challenges. Research on the application of ML in communication networks is described in: i) the three layers, i.e., physical, access, and network layers; and ii) novel computing and networking concepts such as Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Functions Virtualization (NFV), and a brief overview of ML-based network security. Important future research challenges are identified and presented to help stir further research in key areas in this direction.

【 授权许可】

Unknown