Propagation Prediction and BS Planning for Indoor Wireless Communication

The installation of indoor radio systems requires rather detailed propagation characteristics for any arbitrary configuration, so appropriate wave propagation model must be established. In spite of a number proposed solutions for optimal BS stations planning in WLAN environment, it is difficult to say that we have completely satisfied solution. We developed neural network propagation model that was trained for particular environment. The network architecture is based on the multilayer perceptron with two input layers. The neural network results are additionally compared with the numerical results obtained by the deterministic 3-D ray tracing model. The neural network is used to absorb the knowledge about given environment through training with three base stations. Using such obtained knowledge the network is used to predict signal strength at any spot of space under consideration. Therefore, the neural network based propagation model is used as a cost function for optimization of the position of base station. As optimization algorithm it is used particle swarm optimization (PSO) algorithm. The results of PSO are compared with results obtained with two standard algorithms such as simplex optimization method and Powell's conjugate direction method.