Fuzzy interpolation of hydro power sales data in Simulink

The problem in this case study can be described as a multi-dimensional surface fit to a given set of data. The data are sales figures in MWH/H for a hydro-thermal power generation system. The data are incomplete and not totally reliable. A model with ten fuzzy rules fits the data with a total error of 19%; with twenty-six rules the error would be 0%. The model is used in the long term planning concerning operating costs. It is further intended as a short term decision support for operators when negotiating power interchange contracts.<
>