The performance of a The performance of a The performance of a The performance of a cellular network is cellular network is cellular network is cellular network is assessed assessed assessed assessed in terms in terms in terms in terms of key of key of key of key performance indicators (KPI) based on statistics performance indicators (KPI) based on statistics performance indicators (KPI) based on statistics performance indicators (KPI) based on statistics generated from drive tests generated from drive tests generated from drive tests generated from drive tests or or or or network management systems. network management systems. network management systems. network management systems. However, drive tests give the 'feel' of the designed However, drive tests give the 'feel' of the designed However, drive tests give the 'feel' of the designed However, drive tests give the 'feel' of the designed network as it is experienced by the subscribers. network as it is experienced by the subscribers. network as it is experienced by the subscribers.

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 R 2 by 20% and reducing RMSE by 60% over ANFIS, the closest model to the GMDH in term of prediction accuracy.

Traffic congestion during busy hour (BH) deteriorates the overall performance of cellular network and may become unmanageable unless effective and efficient methods of congestion control are developed through real live traffic data measurement and analysis. In this work, real live traffic data from integrated GSM/GPRS network was used for traffic congestion analysis. The analysis was carried out on 10 congesting cells using network management system (NMS) statistics data span for three years period. Correlation test showed that traffic channel (TCH) congestion depend only on call setup success rate (CSSR) and BH traffic at cell level. An average correlation coefficient value of 0.9 was observed between TCH congestion and CSSR while 0.6 was observed between TCH congestion and BH traffic. The correlation test is important when selecting input for congestion prediction modeling.

No abstract

No abstract