Machine-Learning and 3D Point-Cloud Based Signal Power Path Loss Model for the Deployment of Wireless Communication Systems

Modeling signal power path loss (SPPL) for deployment of wireless communication systems (WCSs) is one of the most time consuming and expensive processes that require data collections during link budget analysis. Radio frequency (RF) engineers mainly employ either deterministic or stochastic approaches for the estimation of SPPL. In the case of stochastic approach, empirical propagation models use predefined estimation parameters for different environments such as reference distance path loss PL<inline-formula> <tex-math notation="LaTeX">$(d_{0})$ </tex-math></inline-formula>(dB), path loss exponent <inline-formula> <tex-math notation="LaTeX">$(n)$ </tex-math></inline-formula>, and log-normal shadowing <inline-formula> <tex-math notation="LaTeX">$(X_{\sigma }$ </tex-math></inline-formula> with <inline-formula> <tex-math notation="LaTeX">$N(\sigma ,\mu =0))$ </tex-math></inline-formula>. Since empirical models broadly classify the environment under urban, suburban, and rural area, they do not take into account every micro-variation on the terrain. Therefore, empirical models deviate significantly from actual measurements. This paper proposes a smart deployment method of WCS to minimize the need for predefined estimation parameters by creating a 3-D deployment environment which takes into account the micro-variations in the environment. Tree canopies are highly complex structures which create micro-variations and related unidentified path loss due to scattering and absorption. Thus, our proposed model will mainly focus on the effect of tree canopies and can be applied to any environment. The proposed model uses a 2-D image color classification to extract features from a 3-D point cloud and a machine learning (ML) algorithm to predict SPPL. Empirical path loss models have received signal level (RSL) errors in the range of 6.29%–16.9% from the actual RSL measurements while the proposed model has an RSL error of 4.26%.

[1]  Ivica Kostanic,et al.  An Efficient Approach for Evaluating Performance in LTE Wireless Networks , 2017 .

[2]  Wint Yi Poe,et al.  Node deployment in large wireless sensor networks: coverage, energy consumption, and worst-case delay , 2009, AINTEC.

[3]  Theodore S. Rappaport,et al.  Wireless communications - principles and practice , 1996 .

[4]  Hemant Kumar Rath,et al.  Path Loss model for Indian terrain - empirical approach , 2016, 2016 Twenty Second National Conference on Communication (NCC).

[5]  Sambit Kumar Sahu,et al.  Comparison of Okumura, Hata and COST-231 Models on the Basis of Path Loss and Signal Strength , 2016 .

[6]  M. V. S. N. Prasad,et al.  Double knife edge diffraction propagation studies over irregular terrain , 2004 .

[7]  Martin Haenggi,et al.  Path loss exponent estimation in large wireless networks , 2008, 2009 Information Theory and Applications Workshop.

[8]  Arthur Getis,et al.  Introduction to Geography , 1988 .

[9]  Frank L. Lewis,et al.  Experimental Path Loss Models for Wireless Sensor Networks , 2007, MILCOM 2007 - IEEE Military Communications Conference.

[10]  Lorenzo Bruzzone,et al.  Estimating Low-Power Radio Signal Attenuation in Forests: A LiDAR-Based Approach , 2015, 2015 International Conference on Distributed Computing in Sensor Systems.

[11]  Ivica Kostanic,et al.  Empirical Path Loss Models for Wireless Sensor Network Deployments in Short and Tall Natural Grass Environments , 2016, IEEE Transactions on Antennas and Propagation.

[12]  Antonio Jose Martins Soares,et al.  On the use of image segmentation for propagation path loss prediction , 2011, 2011 SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference (IMOC 2011).

[13]  Rodrigo Fernandes de Mello,et al.  Statistical Learning Theory , 2018 .

[14]  Jun-ichi Takada,et al.  Radio Wave Propagation Through Vegetation , 2013 .