Machine Learning-Enabled Data Rate Prediction for 5G NSA Vehicle-to-Cloud Communications

TL;DR

This paper investigates the use of machine learning to predict data rates in 5G NSA vehicle-to-cloud communications, demonstrating that conventional ML methods can effectively estimate highly fluctuating end-to-end data rates using local measurements.

Contribution

It provides the first empirical analysis of client-based data rate prediction in 5G NSA vehicle-to-cloud scenarios, highlighting the effectiveness of conventional machine learning approaches.

Findings

ML methods achieve accurate data rate predictions despite fluctuations

Local measurements suffice for effective end-to-end behavior estimation

First empirical analysis of its kind for 5G NSA vehicle-to-cloud communications

Abstract

In order to satisfy the ever-growing Quality of Service (QoS) requirements of innovative services, cellular communication networks are constantly evolving. Recently, the 5G NonStandalone (NSA) mode has been deployed as an intermediate strategy to deliver high-speed connectivity to early adopters of 5G by incorporating Long Term Evolution (LTE) network infrastructure. In addition to the technological advancements, novel communication paradigms such as anticipatory mobile networking aim to achieve a more intelligent usage of the available network resources through exploitation of context knowledge. For this purpose, novel methods for proactive prediction of the end-to-end behavior are seen as key enablers. In this paper, we present a first empirical analysis of client-based end-to-end data rate prediction for 5G NSA vehicle-to-cloud communications. Although this operation mode is characterized by massive fluctuations of the observed data rate, the results show that conventional machine learning methods can utilize locally acquirable measurements for achieving comparably accurate estimations of the end-to-end behavior.