Feasibility of neural networks in modelling radio propagation for field strength prediction

A typical back-propagation neural network (BPN) model is developed for modelling radio propagation for field strength prediction based on data measurements of propagation loss (in decibels) with terrain information taken in an urban area (Athens region) in the 900 MHz band. The feasibility of the BPN model is checked against the performance of a conventional semiempirical reference model. The performance of both models is quantified by statistical methods. The evaluation is done by comparing their prediction error statistics of average absolute, standard deviation and root mean square and by comparing their percentage accuracy and correlation of predicted values relative to true data measurements. © 1998 John Wiley & Sons, Ltd.     

Assessment of GTD for mobile radio propagation prediction

The applicability of a GTD-based technique for path loss prediction in cellular radio systems is investigated. The bounds of applicability reported show that such a model could find application in cellular systems with small urban cells and in microcellular systems.<>     

800 MHz mobile radio propagation prediction using Kalman filteringtechniques

A method is presented to derive a propagation model to predict the received median signal voltage for an 800-MHz mobile radio system. Results are given of an investigation into the performance of a particular model that was derived using this method. The method uses a Kalman filter that uses propagation measurements to derive a best fit for a particular propagation model to the measured data. The model that was derived is based on propagation measurements made in the State of Florida. The new propagation model uses a plane-Earth propagation model that is corrected with an environmental propagation loss term that takes into account the various environmental effects near the mobile unit. The parameters in the environmental propagation loss model were determined using a Kalman filter that computes minimum mean square estimates of the parameters using measured propagation data. The environmental propagation loss term accounts for the effects of Earth diffraction, hills, valleys, urban and suburban areas, bare and grass-covered ground, bushes, trees, swamps, and propagation over fresh and salt water. It was found that, with the 800-MHz propagation model derived with this method, the prediction error for the received median signal voltage had a standard deviation of 5.08 dB     

Median signal strength prediction for mobile radio propagation in london

Field trials have confirmed that propagation is characterised by a fourth-power law relating median transmission loss to range. Excess losses due to buildings are about 29 dB at 168 MHz and 37 dB at 445 MHz. These values are greater than those measured in smaller cities, but similar to earlier measurements in New York.     

A comparison of prediction methods for 800 MHz mobile radio propagation

The design and installation of a mobile radio system involves the evaluation or prediction of the propagation characteristics associated with the geographical area of interest. A wide variety of prediction techniques has been developed for different mobile environments, so that the task of selecting an appropriate propagation prediction method can be difficult and complex. This is especially true for systems operating in the upper-UHF band of 800-950 MHz, where mobile radio services are rapidly growing. A practical comparison is given of current prediction techniques available in the literature (for slow lognormal fading rather than multipath Rayleigh fading), with an emphasis on three essential criteria to consider in the selection process: the type of terrain or geography covered by each method, the form of prediction provided (e.g., transmission loss estimates, field strength contour maps, etc.), and the implementation difficulty and degree of sophistication.     

Flood forecasting using radial basis function neural networks

A radial basis function (RBF) neural network (NN) is proposed to develop a rainfall-runoff model for three-hour-ahead flood forecasting. For faster training speed, the RBF NN employs a hybrid two-stage learning scheme. During the first stage, unsupervised learning, fuzzy min-max clustering is introduced to determine the characteristics of the nonlinear RBFs. In the second stage, supervised learning, multivariate linear regression is used to determine the weights between the hidden and output layers. The rainfall-runoff relation can be considered as a linear combination of some nonlinear RBFs. Rainfall and runoff events of the Lanyoung River collected during typhoons are used to train, validate,and test the network. The results show that the RBF NN can be considered a suitable technique for predicting flood flow     

Closed-form expressions for the prediction of microcellular mobile radio propagation in urban environments

The paper derives two closed-form expressions for predicting microcellular mobile radio signal levels in urban street-grid environments. The results demonstrate that the two expressions are faster and more accurate than existing models and methods. Benefiting from physical optics and the conservation of energy, the two expressions are alternatives to available techniques such as ray tracing. The dielectric property (i.e., permittivity) of street buildings and other obstacles is essential to the ray tracing technique. However, there are no established, widely accepted techniques for selecting the permittivity in urban mobile environments, which varies in a wide range. Establishing a natural link between the received power after a street corner to the width of the street and the angle of incidence, our expressions show the possibility of making fast and accurate propagation predictions without having to use the permittivity.     

Minimal radial basis function neural networks for nonlinear channelequalisation

The results of linear and nonlinear channel equalisation in data communications are presented, using a previously developed minimal radial basis function neural network structure, referred to as the minimal resource allocation network (MRAN). The MRAN algorithm uses online learning, and has the capability to grow and prune the RBF network's hidden neurons ensuring a parsimonious network structure. Compared to earlier methods, the proposed scheme does not have to estimate the channel order first, and fix the model parameters. Results showing the superior performance of the MRAN algorithm for two linear channels (minimum and non-minimum phase) for 2PAM signalling, and three nonlinear channels for 2PAM and 4QAM signalling, are presented     

Urban mobile radio propagation at 900 MHz

A series of field trials in London and Birmingham have been used to provide a propagation data base in urban areas at 900 MHz. Measured signal strengths are highly correlated with the results of earlier trials at lower frequencies. The excess loss over plane earth predictions varies with location but is generally in excess of 40 dB.     

Planning effective cellular mobile radio networks

This paper deals with the automatic selection and configuration of base station sites for mobile cellular networks. An optimization framework based on simulated annealing is used for site selection and for base-station configuration. Realistic path-loss estimates incorporating terrain data are used. The configuration of each base station involves selecting antenna type, power control, azimuth, and tilt. Results are presented for several design scenarios with between 250 and 750 candidate sites and show that the optimization framework can generate network designs with desired characteristics such as high area coverage and high traffic capacity. The work shows that cellular network design problems are tractable for realistic problem instances     

Time-delay/Doppler scattering function for suburban mobile radio propagation at 436 MHz

Time-delay/Doppler scattering functions are presented for two different suburban locations where multipath propagation is evident. The major features of the scattering functions are explained in terms of the surrounding environment and the street orientation with respect to the transmitter.     

Microwave propagation measurements for mobile digital radio application

Measurements over a variety of urban and terrain conditions were made using a spread-spectrum waveform centered at 1370 MHz. Chip rates of 10 and 20 MHz were used, giving high time-delay resolution. The transmitter end of the measurement link was elevated and fixed while the receiver was mobile. A detailed analysis of the multipath structure was made for various terrain conditions. This included distributions of the number and spacing of individual multi-path components as a function of amplitude threshold and also distribution of total delay. Thresholds are referenced to both average signal level and the maximum level in each pulse interval. Some instances of spatial variation of the received signal are also presented.     

Capture models for mobile packet radio networks

The probability q_i of successful reception in a nonfading mobile radio channel with i contending mobiles transmitting to a central base station is studied for a number of different capture and spatial distribution models. It is shown that a generalized capture model can be used to estimate q_i's for a simplified example system which uses noncoherent frequency shift keying modulation. This model can be applied to other systems as well. An example of the use of the q_i 's in the throughput evaluation of a finite population slotted ALOHA system is given. In most practical systems, the mobiles cannot get arbitrarily close to the base station. The effect of this constraint on q_i is examined. Finally, the dependence of the capture probability for a test mobile on its distance from the base station is obtained     

Analysis of mobile radio slotted ALOHA networks

Given a mobile terminal transmitting a message to some receiver, the level at the receiver will be affected by path loss and by fading phenomena. Transmissions from different terminals will suffer different attenuations on their respective ways to the receiver and will therefore yield different levels at the receiver. Thanks to the capture effect, the receiver will now be able to read the message with the strongest signal, provided that it is sufficiently stronger than its contenders. In a mobile radio ALOHA network this means that a packet collision need not necessarily destroy all packets involved. A Markov model is developed for slotted ALOHA networks with capture and it is shown that the throughput in such a network can be markedly greater than the famous 1/e. Perhaps even more important is the result that such networks are very stable under overload.     

移动通信网络规划中电磁波传播模型的选择和应用

在移动通信网络中，移动机和基站之间的通信是以电磁波传播的方式进行信息联系的。但由于发射机发射的电磁波在到达接收机之前，可能要受到地形、植被、建筑物及移动物体等因素的影响而引发反射、衍射、散射等现象，进而产生电磁波信号的时延扩散和多径衰落效应。这些效应将大大降低移动通信系统的通信质量，     

Futuristic speed prediction using auto‐regression and neural networks for mobile ad hoc networks

In this paper, we propose a speed prediction model using auto‐regressive integrated moving average (ARIMA) and neural networks for estimating the futuristic speed of the nodes in mobile ad hoc networks (MANETs). The speed prediction promotes the route discovery process for the selection of moderate mobility nodes to provide reliable routing. The ARIMA is a time‐series forecasting approach, which uses autocorrelations to predict the future speed of nodes. In the paper, the ARIMA model and recurrent neural network (RNN) trains the random waypoint mobility (RWM) dataset to forecast the mobility of the nodes. The proposed ARIMA model designs the prediction models through varying the delay terms and changing the numbers of hidden neuron in RNN. The Akaike information criterion (AIC), Bayesian information criterion (BIC), auto‐correlation function (ACF), and partial auto‐correlation function (PACF) parameters evaluate the predicted mobility dataset to estimate the model quality and reliability. The different scenarios of changing node speed evaluate the performance of prediction models. Performance results indicate that the ARIMA forecasted speed values almost match with the RWM observed speed values than RNN values. The graphs exhibit that the ARIMA predicted mobility values have lower error metrics such as mean square error (MSE), root MSE (RMSE), and mean absolute error (MAE) than RNN predictions. It yields higher futuristic speed prediction precision rate of 17% to 24% throughout the time series as compared with RNN. Further, the proposed model extensively compares with the existing works.     

900-MHz mobile radio propagation in the Copenhagen area

A comparative study of 900-MHz, 450-MHz, and 150-MHz mobile radio propagation characteristics performed in Copenhagen, Denmark is described. The three systems were compared with respect to usable coverage area, flutter characteristics, and transmission quality. A statistical method was used for the determination of the coverage area, the limits of which are defined by the contour line corresponding to 20-dB noise quieting at 90 percent of the locations. Flutter patterns were photographically recorded, and simultaneous recordings of voice signals received on the three systems were made on magnetic tape. Concluded is that when corrections are made for differences in transmitter power, antenna gain, receiver sensitivity, etc., and when the propagation losses are assumed to vary with frequency like the free space losses, the coverage areas obtained will be nearly identical. The increased flutter rate at 900 MHz apparently does not affect the transmission noticeably, and it must be generally concluded that the 900-MHz band will provide as good mobile radio performance as any of the lower bands.     

Transparent IP radio access for next-generation mobile networks

Advances in network architecture, enhancements in signaling protocols, provisioning of end-to-end QoS, worldwide seamless mobility, and flexible service provision are among the major research challenges toward next-generation wireless networks. The integration and interoperability of all these technologies, along with new truly broadband wireless innovations and intelligent user-oriented services will lead toward the so-called 4G wireless networks. In this article we identify the key issues of an innovative transparent IP radio access system that targets 4G networks.