Work

Machine Learning for Automatic Machine-to-Machine (M2M) Communication in 5G

Year: 2021
Type: dissertation
Abstract: Fifth Generation (\gls{5G}) is envisioned by Telecom operators as the next mobile network generation which brings solutions to massive customers who are more and more demanding for both cost-efficient services as well as high satisfaction. Machine to machine (M2}) communication is an important component of the future 5G, which enables the ubiquitous connectivity between a myriad of machines without or with limited human intervention. Thus, the autonomous connection of devices facilitates the emergence of a wide range of intelligent M2M applications. These latter have exhibited a strong potential to improve human life in different fields such as eHealth, smart grids, smart home/cities, intelligent transportation and surveillance, enabling partially the internet of things (IoT). By 2020, the number of connected devices is expected to reach 50 billions. To meet these huge demands, the network autonomic mechanisms, named as “Autonomic Networking”, are considered as good candidates to provide intelligent networking solutions for M2M communication in 5G networks. The objective of this thesis is to improve the self-organization and autonomic networking approaches with the integration of machine learning and data analytics for M2M communication. This approach based on machine learning and data analysis will be used to customize the \gls{QoS} for users through the customization of Autonomic Networking.
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W4392279563
Cites:
Cited by:
Related to: 10