AEU - International Journal of Electronics and Communications
Mobile radio propagation path loss prediction using Artificial Neural Networks with optimal input information for urban environments
Introduction
The prediction of radiowave propagation in a wireless communication environment, as in every type of radio access technology, is crucial for the planning of a mobile network being the physical layer of its operation. It is also a difficult task for several physical mechanisms, as the reflection, the diffraction and generally the scattering of the waves as well as the multipath phenomenon contribute to the transmission of the signal power. Taking into account the continuous movement of the users, the profile of the radio channel changes in real time and the parameters of the propagation process become random variables. The quantities, the values of which, have to be predicted are (a) the reduction of the mean power level of the signal versus the distance from the transmitter (Trx), termed as the ‘large scale’ attenuation and known as Path Loss (PL) prediction and (b) the usual rapid variation of the signal power inside a small area around any point of the path, known as ‘small scale’ variation. What makes, the a priori estimation of both type transmission characteristics, be complicated, is that the propagation occurs in random manmade environment. So, the synthesis of a global model suitable for every built-up area profile, is very difficult. For all that, several PL prediction models have been proposed in the literature. These models, used extensively in communication network planning and signal interference studies, can broadly be classified [1], [2], [3], [4], [5], [6], [7], [8], [9] as (a) empirical and (b) deterministic. The models of the former class are easier to implement and require less computational effort but are less sensitive to the environment's physical and geometrical configuration. Those of the latter category have a certain physical basis and are more accurate but at the cost of more computation effort and the necessity of more detailed information about the coverage area. All the aforementioned methods, being flexible and reliable tools for the PL estimation, can effectively replace the realization of measurements, an also efficient process, which, however requires the installation of a complete system of suitable equipment.
The work at hand proposes Artificial Neural Network (ANN) models for the PL prediction in urban environments. The ANN technique has been introduced in several articles of the literature, for the solution of this problem [10], [11], [12], [13], [14], [15], [16], [17], [18], [19]. The majority of these works use, as input to the ANNs, information which concern general parameters of the manmade terrain as, the mean road width, the mean height and length of built blocks, the percentage coverage of the built area, etc. These formulations lead to easy to handle simple ANNs, because small amount and easy to be gathered input information is required. However this kind of data give to the ANNs, substantially very little information for the relief of the environment and lead inevitably to results of decreased accuracy for points at which the built-up characteristics diverge significantly from their mean values over the entire area. On the other hand there have been proposed ANN techniques of large ANNs [16], which use detailed information for the environment thus obtaining accurate prediction but at the cost of the requirement of a large amount of information data to be selected for the area under consideration. The present work focuses on finding the appropriate kind and amount of input information in a way that, on the one hand this information to include details for the terrain of the environment and on the other hand the amount of data given to the ANNs, namely the number of its input nodes, to be small. The research was made at 900 MHz and the pre-condition in finding these optimal input data, was the ensuring, as far as possible, of the accuracy of the prediction
Section snippets
The ANN architecture and training
The idea to employ ANN algorithms for the solution of a problem is based on the general ability of these stochastic and evolutionary procedures, to find out the relationship among the physical parameters of the problem and the results coming from it, even if the physical procedure which relates them is complicated. So, in the case of PL estimation, a properly designed ANN, trained with information data for the build-up area of the communication network, would be capable of finding the relation
The synthesized ANNs and their performance
As discussed in Section 1, when employing the ANN algorithms for the PL prediction, the crucial parameters for accurate results, are the suitable information of the environment as well as the proper ANN structure. Thus the present work has focused on finding the appropriate kind and amount of input information in a way that two requirements to be matched: (a) this information to include details for the man-made terrain of the coverage area and (b) small amount of data to be given to the ANN,
General conclusions
The aim of the work was to develop an alternative technique based on ANNs algorithms for the prediction of signal path loss in mobile communication environments.
The ANN technique has been proposed by several article of the literature for the solution of the specific problem. In the work at hand a new approach to the solution of the problem of PL prediction was attempted and it was proved successful. The concept was to find out the optimal kind of input to ANNs information, or the suitable
Acknowledgments
This research has been co-financed by the European Union (European Social Fund – ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) – Research Funding Program: THALES: Reinforcement of the interdisciplinary and/or inter-institutional research and innovation (MIS 379489)
References (20)
- et al.
Microcell electric fieldstrength prediction model based upon artificial neural networks
Int J Electron Commun (AEÜ)
(2010) - et al.
A robust prediction model using ANFIS based on recent TETRA outdoor RF measurements conducted in Riyadh city – Saudi Arabia
Int J Electron Commun (AEÜ)
(2008) - et al.
A survey of various propagation models for mobilie communication
IEEE Antennas Propag Mag
(2003) Empirical formula for propagation loss in land mobile radio service
IEEE Trans Veh Technol
(1980)- et al.
A survey of wireless path loss prediction and coverage mapping methods
IEEE Commun Surv Tutor
(2013) - et al.
Explicit multiple bulding diffraction attemuation function for mobile radio wave propagation
Electron Lett
(1991) - et al.
Prediction of mobile radio wave propagation over buildings of irregular heights and spacings
IEEE Trans Antennas Propag
(1994) - et al.
A theoretical model for UHF propagation in urban environments
IEEE Trans Antennnas Propag
(1988) - et al.
Path-loss characteristics of urban wireless channels
IEEE Trans Antennas Propag
(2010) - et al.
Propagation path loss – a comparison between Ray-tracing approach and empirical models
IEEE Trans Antennas Propag
(2002)
Cited by (47)
Plane-wave UTD-PO formulation for multiple-plateau diffraction analysis assuming negative incidence angles
2023, AEU - International Journal of Electronics and CommunicationsANN-based model for multiband path loss prediction in built-up environments
2022, Scientific AfricanUsing 2W-PE method based on machine learning to accurately predict field strength distribution in flat-top obstacle environment
2022, AEU - International Journal of Electronics and CommunicationsCitation Excerpt :Machine learning is currently widely-used, which can find the rules between feature parameters and target results based on a large number of data sets, so it is often used for field strength prediction and target recognition. In the field of radio wave propagation calculation, machine learning can overcome the shortcomings of the original empirical model and deterministic model, and has been proven to have superior performance in path loss calculation and can greatly improve calculation efficiency [13–16]. However, because the entire prediction model is established based on determined environment parameters, it is possible that the final prediction model cannot adapt to all propagation scenarios, resulting in a decrease in accuracy.
Deep learning for radio propagation: Using image-driven regression to estimate path loss in urban areas
2020, ICT ExpressCitation Excerpt :The work at hand proposes a framework which devolves the task of feature extraction to the Deep Learning model. Instead of calculating various quantities which characterize the manmade terrain and the radio link [8,9] (such as the number of buildings which are intersected by the Line of Sight path between the transmitter and the receiver), one should only provide the coordinates and the heights of the buildings in the area under consideration. This information can then easily be used to create a map, where the color of the buildings corresponds to their heights: the taller the building, the darker its color.
Influence of Learning Rate Hyper-Parameter and Early Stopping Training Technique in Training Vanilla Neural Network Model for Effective Signal Power Loss Prediction
2023, International Journal on Communications Antenna and PropagationFrom Spatial Urban Site Data to Path Loss Prediction: An Ensemble Learning Approach
2022, IEEE Transactions on Antennas and Propagation