Predicting QoS in LTE HetNets based on location-independent UE measurements

This paper aims to find patterns of knowledge from physical layer data coming from Heterogeneous Long Term Evolution (LTE) networks. We discuss how the collected data is employed in such a manner that improves Minimization of
Drive Tests (MDT) functionality in LTE networks. In particular we aim to predict Quality of Service (QoS) expressed in terms of throughput of the User Datagram Protocol (UDP) traffic flow. We propose regression models to estimate QoS, by extrapolating information independently of the user’s physical location. In particular our approach allows to estimate the QoS in any location, based on measurements collected at anytime in the past, or anywhere in the network. This will allow to significantly reduce costs of future network deployments, even in complex and heterogeneous scenarios, such as those foreseen in stadiums,
events, etc. We identify three feasible regression models, and we compare results in terms of prediction accuracy.