Optimum Selection of Signal Processing Method for Subsequent STLF

Abstract

This article describes one type of the signal conversion - wavelet transform. The fundamental idea of wavelet transforms is that the transformation should allow only changes in time extension, but not shape. This is effected by choosing suitable basis functions that allow for this. Changes in the time extension are expected to conform to the corresponding analysis frequency of the basis function. This type is chosen to build the dynamics of the time series of the electrical load consumption and must perform the following tasks: accurate tracking of the signal’s local features and temporal localization. Data obtained at the output of the wavelet-filtering have multiple channels (decomposition levels), which further take part in the short-term load forecast (STLF). In particular, it is used in the forecast, which is a committee of the Neuro-Fuzzy Network.