An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks

Today’s terrestrial cellular communications networks face difficulties in serving coexisting users and devices due to the enormous demands of mass connectivity. Further, natural disasters unexpected events lead an unpredictable amount data traffic, thus causing congestion network. In such cases, addition on-demand network entities, as fixed or aerial base stations, has been proposed a viable solution for managing high traffic offloading existing infrastructure. This paper presents unmanned vehicles (UAVs) aided strategy network, utilizing unsupervised machine learning method best placement UAVs sites with traffic. The scheme forms clusters located affected area using k-medoid algorithm. Followingly, based on number available UAVs, cluster selection is employed select that will be deployed achieve maximum system. Comparisons traditional strategies integrating picocells other UAV-aided schemes show significant offloading, throughput, spectral efficiency, sum rate gains can harvested through under varying UAVs.