Prediction of Antenna Patterns over Hotspot Clusters in WCDMA Networks

N. Yao and L. Cuthbert (UK)


CBR, WCDMA, smart antennas, prediction, simulation.


This paper proposes a new method of balancing traffic load in mobile cellular networks and predicting the change of radio coverage to prevent congestion in advance. Case-Based Reasoning (CBR) is used to learn traffic patterns at periods of congestion and to apply the most suitable antenna patterns when a similar traffic pattern reappears. In addition, CBR also provides the capability of congestion prediction. Prediction means that the optimum patterns do not have to be recalculated each time, (greatly reducing the computational complexity) and unlike previous work, the prediction is done across a cluster of cells, not just a single cell. Initial simulations have been performed to evaluate the system performance and the results are presented.

Important Links:

Go Back