Next Article in Journal
Characterization and Prediction of Air Transport Delays in China
Next Article in Special Issue
Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data
Previous Article in Journal
Numerical Study on the Feasibility of a 24 GHz ISM-Band Doppler Radar Antenna for Near-Field Sensing of Human Respiration in Electromagnetic Aspects
Article

Can We Exploit Machine Learning to Predict Congestion over mmWave 5G Channels?

1
Communications Engineering Department, University of Cantabria, 39005 Santander, Spain
2
Communication Networks Lab, New York University Abu Dhabi, 129188 Abu Dhabi, UAE
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(18), 6164; https://doi.org/10.3390/app10186164
Received: 31 July 2020 / Revised: 28 August 2020 / Accepted: 2 September 2020 / Published: 4 September 2020
(This article belongs to the Special Issue AI in Mobile Networks)
It is well known that transport protocol performance is severely hindered by wireless channel impairments. We study the applicability of Machine Learning (ML) techniques to predict congestion status of 5G access networks, in particular mmWave links. We use realistic traces, using the 3GPP channel models, without being affected using legacy congestion-control solutions. We start by identifying the metrics that might be exploited from the transport layer to learn the congestion state: delay and inter-arrival time. We formally study their correlation with the perceived congestion, which we ascertain based on buffer length variation. Then, we conduct an extensive analysis of various unsupervised and supervised solutions, which are used as a benchmark. The results yield that unsupervised ML solutions can detect a large percentage of congestion situations and they could thus bring interesting possibilities when designing congestion-control solutions for next-generation transport protocols. View Full-Text
Keywords: machine learning; mmWave; 5G; congestion control; ns-3; network simulation; unsupervised learning machine learning; mmWave; 5G; congestion control; ns-3; network simulation; unsupervised learning
Show Figures

Figure 1

MDPI and ACS Style

Diez, L.; Fernández, A.; Khan, M.; Zaki, Y.; Agüero, R. Can We Exploit Machine Learning to Predict Congestion over mmWave 5G Channels? Appl. Sci. 2020, 10, 6164. https://doi.org/10.3390/app10186164

AMA Style

Diez L, Fernández A, Khan M, Zaki Y, Agüero R. Can We Exploit Machine Learning to Predict Congestion over mmWave 5G Channels? Applied Sciences. 2020; 10(18):6164. https://doi.org/10.3390/app10186164

Chicago/Turabian Style

Diez, Luis, Alfonso Fernández, Muhammad Khan, Yasir Zaki, and Ramón Agüero. 2020. "Can We Exploit Machine Learning to Predict Congestion over mmWave 5G Channels?" Applied Sciences 10, no. 18: 6164. https://doi.org/10.3390/app10186164

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop