Model-Aided Deep Learning Method for Path Loss Prediction in Mobile Communication Systems at 2.6 GHz

Accurate channel models are essential to evaluate mobile communication system performance and optimize coverage for existing deployments. The introduction of various transmission frequencies for 5G imposes new challenges for accurate radio performance prediction. This paper compares traditional channel models to a channel model obtained using Deep Learning (DL)-techniques utilizing satellite images aided by a simple path loss model. Experimental measurements are gathered and compose the training and test set. This paper considers path loss modelling techniques offered by state-of-the-art stochastic models and a ray-tracing model for comparison and evaluation. The results show that 1) the satellite images offer an increase in predictive performance by ≈ 0.8 dB, 2) The model-aided technique offers an improvement of ≈ 1 dB, and 3) that the proposed DL model is capable of improving path loss prediction at unseen locations for 811 MHz with ≈ 1 dB and ≈ 4.7 dB for 2630 MHz.

[1]  Dirk Grunwald,et al.  Bounding the Practical Error of Path Loss Models , 2012 .

[2]  Sotirios K. Goudos,et al.  Neural Networks and Random Forests: A Comparison Regarding Prediction of Propagation Path Loss for NB-IoT Networks , 2019, 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST).

[3]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  Cheng-Xiang Wang,et al.  A Survey of 5G Channel Measurements and Models , 2018, IEEE Communications Surveys & Tutorials.

[5]  Matteo Artuso,et al.  Drive Test Minimization Using Deep Learning with Bayesian Approximation , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[6]  Ronald Davis,et al.  Neural networks and deep learning , 2017 .

[7]  Ming Xiao,et al.  Heterogeneous Ultradense Networks with NOMA: System Architecture, Coordination Framework, and Performance Evaluation , 2018, IEEE Vehicular Technology Magazine.

[8]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[9]  Vinesh Thiruchelvam,et al.  Indoor 3-D RT Radio Wave Propagation Prediction Method: PL and RSSI Modeling Validation by Measurement at 4.5 GHz , 2019 .

[10]  Adaildo G. D'Assuncao,et al.  A Hybrid Path Loss Prediction Model based on Artificial Neural Networks using Empirical Models for LTE And LTE-A at 800 MHz and 2600 MHz , 2017 .

[11]  Nasir Faruk,et al.  Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel , 2019, IEEE Access.

[12]  Zaher Dawy,et al.  Planning Wireless Cellular Networks of Future: Outlook, Challenges and Opportunities , 2017, IEEE Access.

[13]  Jakob Hoydis,et al.  End-to-End Learning of Communications Systems Without a Channel Model , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[14]  Zhengqing Yun,et al.  Ray Tracing for Radio Propagation Modeling: Principles and Applications , 2015, IEEE Access.

[15]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[16]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[17]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[18]  A. Atayero,et al.  Optimal model for path loss predictions using feed-forward neural networks , 2018 .

[19]  Alberto Rodriguez,et al.  TossingBot: Learning to Throw Arbitrary Objects With Residual Physics , 2019, IEEE Transactions on Robotics.

[20]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[21]  Vittorio Degli-Esposti,et al.  Ray Tracing RF Field Prediction: An Unforgiving Validation , 2015 .

[22]  Alessio Zappone,et al.  Model-Aided Wireless Artificial Intelligence: Embedding Expert Knowledge in Deep Neural Networks for Wireless System Optimization , 2019, IEEE Vehicular Technology Magazine.

[23]  Cheng-Xiang Wang,et al.  5G Ultra-Dense Cellular Networks , 2015, IEEE Wireless Communications.

[24]  Hans-Jürgen Zepernick,et al.  Macrocell Path-Loss Prediction Using Artificial Neural Networks , 2010, IEEE Transactions on Vehicular Technology.

[25]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[26]  Henrik Lehrmann Christiansen,et al.  Comparison of Empirical and Ray-Tracing Models for Mobile Communication Systems at 2.6 GHz , 2019, 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall).

[27]  Mikko Valkama,et al.  Spectral and energy efficiency of ultra-dense networks under different deployment strategies , 2015, IEEE Communications Magazine.