Optimizing Neural Network for TV Idle Channel Prediction in Cognitive Radio Using Particle Swarm Optimization

The communications frequency spectrum in Nairobi city is statically allocated. The cellular network is overwhelmed by broadband demand yet TV channels are under-used. Cognitive Radio would enable an opportunistic user to `borrow' an idle band and seamlessly hand it back. Cognitive Radio would conventionally sense idle channels and decide on the most technically-appropriate idle channel to allocate a secondary user. However, the process of decision is time-consuming and allocates channels erratically without due consideration of temporal appropriateness of the channel. This twin problem is solved if the decisionmaking were done earlier. This is only possible by predicting the occurrence of idle channels within the cell of concern. Prediction of idle channels demands that patterns of TV-viewing within that cell be modeled successfully. This paper explores the ability of particle swarm optimization (PSO) technique to optimize a neural network (NN) used in modeling the mentioned patterns.