Artificial Neural Network Based Path Loss Prediction for Wireless Communication Network
Open Access
- 2 November 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 199523-199538
Abstract
Accurate path loss (PL) prediction is essential for predicting transmitter coverage and optimizing wireless network performance. Traditional PL models are difficult to cope with the development trend of diversity, time-varying and mass wireless channels. In this work, the most widely used multilayer perceptron (MLP) neural network in artificial neural network (ANN) is employed to accurately predict PL. Three types of environmental features are defined and extracted, which describe the propagation environment only by considering limited environmental types instead of complex 3D environment modeling. Principal component analysis (PCA) is used to generate the low-dimensional environmental features, and eliminate redundant information among similar environmental types. Moreover, the information of base station (BS) and the receiver (Rx), including 3D locations, frequency, the transmitted power of BS, the antenna information, the feeder loss, and the received power of all the locations are obtained from the measurements. Different environmental features are combined with the information of BS and Rx to construct seven datasets for PL prediction models based on MLP neural networks. The impacts of the number of neurons in the hidden layer, the number of hidden layers, the number of training samples, and environmental features on PL prediction models are explored by considering the absolute value of mean error (AME), the mean absolute error (MAE), the standard deviation (STD) of error, the correlation coefficient, and the time ratio, respectively. This work aims to understand the propagation characteristics of radio waves, which can provide a theoretical basis for wireless network optimization and communication system design.Keywords
Funding Information
- Fundamental Research Funds for Central Universities (2020JBZD005)
- NSFC (61901029)
- NSFC (61771036)
- NSFC (61725101)
- NSFC (U1834210)
- Royal Society Newton Advanced Fellowship (6196113039)
- Royal Society Newton Advanced Fellowship (NA191006)
- State Key Lab of Rail Traffic Control and Safety Project (RCS2020ZT011)
- State Key Lab of Rail Traffic Control and Safety Project (RCS2020ZZ005)
- State Key Lab of Rail Traffic Control and Safety Project (RCS2020ZT010)
- Science and Technology Key Project of Guangdong Province, China (2019B010157001)
This publication has 37 references indexed in Scilit:
- Investigation of Prediction Accuracy, Sensitivity, and Parameter Stability of Large-Scale Propagation Path Loss Models for 5G Wireless CommunicationsIEEE Transactions on Vehicular Technology, 2016
- Emulating Ray-Tracing Channels in Multiprobe Anechoic Chamber Setups for Virtual Drive TestingIEEE Transactions on Antennas and Propagation, 2015
- Wideband Millimeter-Wave Propagation Measurements and Channel Models for Future Wireless Communication System DesignIEEE Transactions on Communications, 2015
- Communicating in the real world: 3D MIMOIEEE Wireless Communications, 2014
- Three-dimensional fading channel models: A survey of elevation angle researchIEEE Communications Magazine, 2014
- Modeling by optimal Artificial Neural Networks the prediction of propagation path loss in urban environments2013
- Neural networks applications for the prediction of propagation path loss in urban environments2001
- UTD multiple-edge transition zone diffractionIEEE Transactions on Antennas and Propagation, 1997
- Environment-adaptation mobile radio propagation prediction using radial basis function neural networksIEEE Transactions on Vehicular Technology, 1997
- An evaluation of Longley-Rice and GTD propagation modelsIEEE Transactions on Antennas and Propagation, 1982