Adaptive Hybrid Model for Prediction of Electromagnetic Signal Path Loss in Long Term Evolution radio Microcellular Network

Abstract

Accurate path loss modeling and prediction will provide realistic information on the level of signal attenuation in a service area and contribute positively to better performance of cellular radio network. This will also support the tight fitting of cell fringe areas that are likely to be impacted negatively by interference around the cell edge/contour. A better predictive path loss model that will facilitate superb cellular network planning process will be of a great support to cellular radio network planners, stakeholders and end users. In this work we used a hybrid wavelet and Long Short Term Memory model for adaptive modeling and prediction of signal path loss in urban microcellular radio network. A measured signal data was obtained and routed through a wave let-based decomposition process with two decomposition levels. The decomposed measured signal data was converted into path loss values and then utilized as input data to Long Short Term Memory model where relevant extracted information were captured and trained for robust predictive adaptive learning and prediction. The degree of prediction accuracy using the proposed model over other prediction techniques were statistically quantified using four different first order statistical metricsSignal Pathloss model can accurately estimate pathloss which in turn are useful for maximizing of network quality and coverage area of base stations, frequency assignments, proper determination of electric field strength, interference analysis, handover optimization, power level adjustment, radio link budget design and analysis.