Cell-Level Quality of Service Estimation Using Machine Learning Techniques on 5G Networks in Dense Urban Areas

This study presents a general machine learning framework to estimate the traffic-measurement-level experience rate at given throughput values as a Key Performance Indicator for the cells on base stations across various urban regions within a large city, using busy-hour counter data and several technical parameters together with the network topology. We propose scores of additional predictors to enhance the effects of raw correlated counter values over the corresponding targets and effectively represent the underlying interactions among groups of cells within nearby spatial locations; and apply an end-to-end regression modeling to the transformed data, presenting results on unseen regions of varying characteristics.