Comparative Analysis of Traffic Congestion Prediction Models for Cellular Mobile Macrocells

Abstract

Traffic congestion prediction is a non-linear process that involves obtaining valuable information from a set of traffic data and linear models cannot be applied because of the dynamics of combined voice and data traffic on one radio channel of GSM/GPRS access network. However, non-linear problems can easily be modeled using Artificial Intelligent (AI) techniques such as Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). In this work, three types of ANN and an ANFIS models are trained based on busy hour (BH) traffic measurement data taken from some GSM/GPRS sites in Abuja. The models were then used to predict traffic congestion for some macrocells and their accuracy are compared using four statistical indices. It was observed that Group Method of Data Handling (GMDH) model which is one of the ANN models has the best fit and predict better than ANFIS and the other two ANN models. The GMDH model is found to offer improved prediction results in terms of increasing the R2 by 20% and reducing RMSE by 60% over ANFIS, the closest model to the GMDH in term of prediction accuracy.