Intelligent forecasting: Fuzzy/neuro-fuzzy methodologies with case studies
A key component of the operation and planning activities in the majority of industrial plants such as electric utilities, refineries, and manufacturers, as well as enterprises and organizations is demand, or sales, forecasting. The aim of this paper is to present the solution of the forecasting problem through the application of the fuzzy/neurofuzzy methodologies. In particular, two very effective techniques are discussed based on the Takagi-Sugeno (functional reasoning) fuzzy model. The first uses the orthogonal least squares (OLS) technique to identify the structure of the fuzzy system (input variables selection and input space partitioning), and the second one uses the adaptive resonance theory (ART) technique for the same purpose. A power load forecast and a refinery product quality forecast case study are included to demonstrate the high accuracy achieved by fuzzy/neurofuzzy forecasting methods.
Bibliogr. 15 poz.