Title :
Building a `quasi optimal´ neural network to solve the short-term load forecasting problem
Author :
Choueiki, M. Hisham ; Mount-Campbell, Clark A. ; Ahalt, Stanley C.
Author_Institution :
Forecasting Div., Public Utilities Comm. of Ohio, Columbus, OH, USA
fDate :
11/1/1997 12:00:00 AM
Abstract :
The ability to solve the short-term load forecasting (STLF) problem with artificial neural networks (ANNs) is investigated by conducting a fractional factorial experiment. The results of the experiment are analyzed, and the factors and factor interactions that affect forecast errors are identified and quantified. From the analysis, we derive rules for building a `quasi optimal´ neural network to solve the STLF problem. A comparison study demonstrates the superior performance of the `quasi optimal´ neural network over an automated Box-Jenkins seasonal ARIMA model in solving the STLF problem
Keywords :
learning (artificial intelligence); load forecasting; neural nets; power system analysis computing; artificial neural networks; automated Box-Jenkins seasonal ARIMA model; forecast errors; fractional factorial experiment; neural network input calibration; neural network training; quasi optimal neural network; short-term load forecasting; Artificial neural networks; Costs; Economic forecasting; Environmental economics; Fuel economy; Load forecasting; Neural networks; Power generation economics; Power system planning; Power system reliability;
Journal_Title :
Power Systems, IEEE Transactions on
