Seamless connectivity with 5G enabled unmanned aerial vehicles base stations using machine programming approach

Abstract

Deployment of a small unmanned aerial vehicle (UAV) mounted 5G base station is a promising solution for providing seamless network connectivity to users in a modern, data-centric thrust areas. The key challenge is to find the location, the height and the optimum number of mounts. A machine programming based approach is proposed here for optimal placement of UAV-mounted base station. The location of the deployment is determined using three clustering algorithms such as K-means, K-medoids, and fuzzy cluster means. Different sets of UAV-mounted base stations have been deployed with variable user density at different heights. The impact on the network performance has been quantified through measurements of received power, signal to interference plus noise ratio (SINR), and path loss per active user equipment (UEs). To gain further insights, a scenario where UEs are connected only to the terrestrial base station, that is, the network is devoid of any sort of UAV mounted base station is evaluated. Numerical computations reaffirm that the proposed technique reduces the average path loss of the active UEs. Moreover, the use of height-mounted base station also alleviates the issues arising due to low SINR values. The said technique shows immense potential in terms of seamless connectivity to end users in events of emergency and remote deployment scenarios, where ground-based base station is not possible. The big transition of on-demand connectivity for 5G networks shall be benefitted from purpose-built UAV infrastructure with specific locations or areas in mind.

Introduction to the special issue on big data analytics with internet of things‐oriented infrastructures for future smart cities

“…This work (Mandloi & Arya, 2022) proposed a Machine Programming based approach for the deployment of 5 G‐enabled UmBSs. The centroid‐based clustering algorithms such as; K‐means, K‐medoid, and FCM were proposed to find the centroid of the cluster.…”

“…The authors have used the smart grid stability data set freely available on Kaggle to train and test the models. This work (Mandloi & Arya, 2022) proposed a Machine Programming based approach for the deployment of 5 G-enabled UmBSs. The centroid-based clustering algorithms such as; K-means, K-medoid, and FCM were proposed to find the centroid of the cluster.…”

Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks

“…However, applying these algorithms individually to a UAV-NOMA and D2D cooperative network might degrade the overall network quality while rendering the D2D network unnecessary. Hence, to achieve enhanced network quality, it is vital to consider the interactions and trade-offs between the two algorithms and the network elements and adopt an integrated approach [ 7 , 24 ].…”

“…The two methods are fed with the terrestrial users’ coordinates as an input feature to find the point where the UFBS should be placed. In such scenarios, k-means behaves well when the terrestrial users form spherical clusters without outliers [ 24 ]. In contrast, k-medoids is robust to the outliers and correctly represents the cluster center [ 7 ].…”

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

“…Simulation results showed that the proposed method could increase the offloading factor from 15% to the required 50%. D. Mandloi et al [16], have introduced a machine-programming-based approach for building a 5G-enabled UAV-BSs network in mmWave. The unsupervised machine learning (ML) methods such as the k-means, the k-medoids, and the fuzzy cluster means (FCM) algorithm were proposed to determine the optimal 2D placement of UAV-BSs.…”