Urban Cellular Environment Research Articles

Hybrid learning strategies for multivariate time series forecasting of network quality metrics

This work addresses the challenge of forecasting temporal metrics that characterize cellular traffic behavior. The ultimate goal is to provide network operators with a valuable tool for modeling mobile network traffic and optimizing connected resources. The idea is to estimate beforehand the temporal evolution of some Quality-of-Experience (QoE) and Quality-of-Service (QoS) metrics, which is helpful for accurately tuning the allocation of network resources. Remarkably, these metrics (expressed as time series) are typically correlated, and changes in one time series can affect others in a variety of ways and to different extents. For example, high network delay (a QoS-related metric) is associated with degradation in voice quality over time (a QoE-related metric). Accordingly, we address the problem of cellular traffic forecasting with correlated time series, proposing three innovative hybrid learning strategies designed by combining the advantages of two approaches: (i) a statistical approach, implemented through the Vector Autoregressive (VAR) model, which encodes each metric as a combination of past values of the same metric along with a combination of values of other related metrics, resulting in a multivariate structure; and (ii) an approach based on deep learning techniques (specifically, CNN, LSTM, and GRU) which operate on such a multivariate structure to perform the forecasting. The resulting performance demonstrates the benefits of the proposed hybrid schemes (VAR-CNN, VAR-LSTM, VAR-GRU) over their pure counterparts, with a significant reduction in forecasting errors. The network metrics were gathered in a real urban cellular environment, where the presence of exogenous factors (e.g., interferences, weather conditions, etc.) makes the forecasting assessment particularly challenging.

Efficient Pathloss Model for determining Mobile Radio Link Design

The focus of this paper is on efficient pathloss model for determining mobile radio link design. A fixed 3G BTS transmitter was also used to generate the data. Log-normal shadowing model was used to analyse the data. The calculated data were compared using path loss exponent and standard deviation. They were found to be within the specified range for urban area cellular radio environment like Enugu urban. The result is a provision of a link design network with an adequate coverage and quality of service.

Influence of measurement conditions on the evaluation of some radio channel parameters

Communications with mobile stations undergo perturbations due to the necessary radio link. Digital systems are particularly sensitive to multipath effects and frequency selectivity. The wide-band characteristics of the channel are complex and usually summarized by parameters like the delay spread, delay window, or correlation bandwidth. The design of systems is based on statistical studies of these parameters extracted from intensive experimental campaigns. The theoretical definitions of these parameters are widely accepted. However, we have observed that some differences may arise in the practical computation method used. We first show in this paper that the evaluation method and the measurement conditions may lead to differences in parameter estimates which cannot be neglected. We used a large number of complex impulse responses measured in a UHF urban cellular environment as a test set. Theoretical relation were developed to predict the effects of some experimental conditions. These formulas show a good match with the mains changes observed in the measurements. From this analysis, some recommendations are proposed to make the statistical evaluation of these parameters more relevant. Relationships between different channel parameters are also investigated.

High-resolution 3-D direction-of-arrival determination for urban mobile radio

The in-depth knowledge of the mobile radio channel is particularly important for radio communication modeling and advanced technology system design. We propose an accurate method to determine jointly the azimuth and elevation angle and the delay of waves incoming at the receiver. The method is applied to measurements of the complex impulse response of the mobile radio channel, performed on a planar array placed on a mobile in an urban cellular environment. The directions-of-arrival (DOA) were obtained by the means of a direction finding algorithm-two-dimensional (2-D) unitary ESPRIT. Two-dimensional spatial smoothing as an extension of ordinary spatial smoothing is utilized to decorrelate coherent waves. The application of 2-D unitary ESPRIT increases the angular resolution over conventional Fourier analysis or the scattering function by an order of magnitude and overcomes difficulties due to secondary lobes. The time delay is determined from wideband channel sounder measurements. The results confirm some assumptions on propagation mechanisms: (1) the wave-guiding property of streets (canyon effect), which is especially pronounced for long-delayed paths; (2) the variation of the number of incoming waves with their excess delay-the larger the excess delay, the lower the number of paths comprising an echo in the power delay profile; (3) if a single path remains, the privileged DOA is the direction of the street; (4) the exponential part of the power delay profile due to scatterers all around the receiver; and (5) the elevation dependence or the impinging power. In the tested receiver locations, paths with elevations between 0/spl deg/ and 40/spl deg/ dominate, containing about 90% of the received power.