Application of an Ensemble Method to UAV Power Modeling for Cellular Communications

In this letter, we apply ensemble learning methods for the prediction of the ground (cellular base station) to air (flying node) received signal strength (RSS) at different heights, for future mobile communications. We model the RSS using different ensemble methods. Moreover, we propose a new ensemble method that combines results from five different methods. The proposed method also uses a recently introduced evolutionary algorithm, the Salp Swarm Algorithm, for weight optimization. The proposed method outperforms all the other methods and common ensemble methods. In this context, the produced results are compared to measurements using representative performance indices and exhibit satisfactory accuracy.

[1]  Dimitra Zarbouti,et al.  Artificial Neural Network Optimal Modeling and Optimization of UAV Measurements for Mobile Communications Using the L-SHADE Algorithm , 2019, IEEE Transactions on Antennas and Propagation.

[2]  David H. Wolpert,et al.  The Lack of A Priori Distinctions Between Learning Algorithms , 1996, Neural Computation.

[3]  Robert W. Heath,et al.  Analysis of Blockage Effects on Urban Cellular Networks , 2013, IEEE Transactions on Wireless Communications.

[4]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[5]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[6]  Alípio Mário Jorge,et al.  Ensemble approaches for regression: A survey , 2012, CSUR.

[7]  Hossam Faris,et al.  Salp Swarm Algorithm: A bio-inspired optimizer for engineering design problems , 2017, Adv. Eng. Softw..

[8]  Steven D. Glaser,et al.  A Machine-Learning-Based Connectivity Model for Complex Terrain Large-Scale Low-Power Wireless Deployments , 2017, IEEE Transactions on Cognitive Communications and Networking.

[9]  George V. Tsoulos,et al.  Artificial neural network optimal modelling of received signal strength in mobile communications using UAV measurements , 2018 .

[10]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[11]  George V. Tsoulos,et al.  LTE Ground-to-Air Field Measurements in the Context of Flying Relays , 2019, IEEE Wireless Communications.

[12]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[13]  Halim Yanikomeroglu,et al.  The New Frontier in RAN Heterogeneity: Multi-Tier Drone-Cells , 2016, IEEE Communications Magazine.

[14]  Cha Zhang,et al.  Ensemble Machine Learning: Methods and Applications , 2012 .

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  Hwanjo Yu,et al.  SVM Tutorial - Classification, Regression and Ranking , 2012, Handbook of Natural Computing.