Improved model for traffic fluctuation prediction by neural network

The traffic prediction are mainly used to improve the performance of telecommunication network management. This paper improved model for telephone traffic prediction in Thailand by using artificial neural network (ANN) with back propagation learning algorithms. By applied data which is collected at different node in main routes of TOT, Thailand telephone network for learning process and testing. The neural network structure and input/output musters are descried in detail. We present the comparatively results of simulation with another methods, the results shows traffic fluctuation prediction by the method of ANN is accurately.