Machine Learning for Position Prediction and Determination in Aerial Base Station System

A novel framework for dynamic 3-D deployment of unmanned aerial vehicle (UAV) in the aerial base station system (ABSS) that based on the machine learning algorithms is proposed. In the framework, the UAV is deployed as an aerial base station to serve a group of ground users and is placed based on the prediction of the users' mobility. The joint problem of prediction of users' track and 3-D deployment of the UAV is formulated for maximizing the sum transmit rate. A two-step approach is proposed for predicting the movement of users and for determining the dynamic 3-D placement of the UAV. Firstly, an echo state network (ESN) based prediction algorithm is utilized for predicting the future positions of users based on the real-world datasets collected from Twitter. Secondly, an iterative K-Means based algorithm is proposed for obtaining the optimal placement of UAV at each time slot based on the output of ESN model. Numerical results are illustrated for showing the superiority of the proposed algorithm over the prevalent algorithm on prediction tasks. The accuracy and efficiency of the proposed framework are also investigated. Additionally, compared with static placement of the UAV, the advantage of dynamic 3-D deployment is demonstrated.

[1]  Zhu Han,et al.  Extracting typical users' moving patterns using deep learning , 2012, 2012 IEEE Global Communications Conference (GLOBECOM).

[2]  Halim Yanikomeroglu,et al.  Efficient 3-D placement of an aerial base station in next generation cellular networks , 2016, 2016 IEEE International Conference on Communications (ICC).

[3]  Walid Saad,et al.  Wireless Communication Using Unmanned Aerial Vehicles (UAVs): Optimal Transport Theory for Hover Time Optimization , 2017, IEEE Transactions on Wireless Communications.

[4]  Erik G. Larsson,et al.  Aspects of favorable propagation in Massive MIMO , 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

[5]  Luc Martens,et al.  Emergency ad-hoc networks by using drone mounted base stations for a disaster scenario , 2016, 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[6]  Karina Mabell Gomez,et al.  Aerial-terrestrial communications: terrestrial cooperation and energy-efficient transmissions to aerial base stations , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[7]  Antonello Rizzi,et al.  Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition , 2015, IEEE Access.

[8]  Halim Yanikomeroglu,et al.  3-D Placement of an Unmanned Aerial Vehicle Base Station (UAV-BS) for Energy-Efficient Maximal Coverage , 2017, IEEE Wireless Communications Letters.

[9]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[10]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[11]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[12]  Claire Cardie,et al.  Proceedings of the Eighteenth International Conference on Machine Learning, 2001, p. 577–584. Constrained K-means Clustering with Background Knowledge , 2022 .

[13]  Benjamin Schrauwen,et al.  Reservoir-based techniques for speech recognition , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[14]  E. Nebot,et al.  Automated Process for Generating Digitised Maps through GPS Data Compression , 2007 .

[15]  Salahedin Rehan,et al.  Aerial base stations with opportunistic links for next generation emergency communications , 2016, IEEE Communications Magazine.

[16]  Herbert Jaeger,et al.  Echo state network , 2007, Scholarpedia.