Critical Review on Machine Learning in 5G Mobile Networks


Mohamed Hussein, Mohamed Mohsen Farouk and Pang, Wai Leong and Chung, Gwo Chin and Roslee, Mardeni (2023) Critical Review on Machine Learning in 5G Mobile Networks. International Journal of Intelligent Systems and Applications in Engineering, 11 (8S). pp. 362-367. ISSN 2147-6799

[img] Text
document.pdf - Published Version
Restricted to Repository staff only

Download (187kB)


The 5G wireless network standard was created through the 3rd Generation Partnership Project as the next big leap in wireless network technology. Offering several advantages over previous generations of wireless network technology 5G, promises to bring with it higher speeds, lower latency rates, better reliability, and much more. All these improvements offered by the Fifth-Generation network allowed for a variety of new applications that increased the complexity of maintaining the quality of service across the network due to their stringent and heterogeneous quality of service requirements, which must be met simultaneously. This increased complexity has motivated many researchers to propose innovative approaches in the literature, such as implementing network schedulers that can leverage different kinds of machine learning, network slicing, or combinations of several different techniques. This has motivated us to investigate the existing research regarding machine learning in network orchestration, to determine the most capable methods and algorithms to satisfy the quality-of-service requirements of the heterogeneous traffic flows across the 5G wireless network.

Item Type: Article
Uncontrolled Keywords: 5G, Network Slicing, QoS, Reinforcement Learning
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 05 Sep 2023 01:46
Last Modified: 05 Sep 2023 01:46


Downloads per month over past year

View ItemEdit (login required)