MA system identification using higher order cumulants application to modelling solar radiation

The main goal of this investigation is to elaborate an accurate and efficient algorithm able to estimate the moving average (MA) parameters in noisy environment. So, we address the problem of estimating the parameters of a MA--non-minimum phase (NMP)-system from the output observation when the system is excited by an unobservable independent identically distributed (i.i.d.) sequence. A new procedure, based on third and fourth order cumulants, to estimate the parameters of MA process when the order is known, is presented. This procedure was tested for various examples of MA (NMP) system, and for different order and different signal-to-noise-ratio (SNR). A comparison with some existing methods was also performed and the result shows the efficiency of the proposed algorithm. For validation purpose this method is used to search for a model able to describe and to predict the data set representing the daily solar radiation.