An Intelligent UAV Deployment Scheme for Load Balance in Small Cell Networks Using Machine Learning

Abstract

In wireless networks, network load can be highly unbalanced due to the mobility of user equipments (UEs). Unmanned Aerial Vehicles (UAVs) supported base station with the advantage of flexible deployment, ubiquitous wireless coverage and high speed data rate, is a promising approach to handle with the foregoing problem. However, how to achieve cost-effective UAV deployment in an autonomous and dynamic manner is a significant challenge. Facing this problem, we propose a novel UAV base station intelligent deployment scheme based on machine learning and evaluate its performance on a realworld dataset. First, we conduct data preprocessing to process, clean, and transform raw data into formatted data. Missing values are filled by Conditional Mean Imputation (CMI) method and outliers are corrected by pauta criterion. Then, we use hybrid approach which contains ARIMA model and XGBoost model. Linear predictions are carried out by ARIMA model and later nonlinear model XGBoost are applied on residue of ARIMA. Resultant prediction is obtained by adding linear and nonlinear prediction, hybrid model is estimated by Root Mean Square Error (RMSE) and R2 score. Finally, according to predicted results, UAV base stations can be deployed to cater for dynamically changing demands in the hotspot areas and achieve cost-effective deployment. Simulation results show that the propose scheme is superior to other benchmark schemes in load balancing.