Title :
An optimized adaptive neural network for annual midterm energy forecasting
Author :
Tsekouras, George J. ; Hatziargyriou, Nikos D. ; Dialynas, Evangelos N.
Author_Institution :
Sch. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece
Abstract :
The objective of this paper is to present a new methodology for midterm energy forecasting. The proposed model is an adaptive artificial neural network (ANN), which properly transforms the input variables to differences or relative differences, in order to predict energy values not included in the training set. The ANN parameters, such as the finally used input variables, the number of neurons, initial values, and time periods of momentum term and training rate, are simultaneously selected by an optimization process. Another characteristic of the model is the use of a minimal training set of patterns. Results from an extensive analysis conducted by the developed method for the Greek power system and for different categories of customers are compared to those obtained from the application of standard regression methods.
Keywords :
load forecasting; neural nets; optimisation; power engineering computing; Greek power system; adaptive neural network; annual midterm energy forecasting; extensive analysis; initial values; input variables; minimal training set; momentum term; neurons; optimization process; standard regression methods; training rate; Adaptive systems; Artificial neural networks; Input variables; Load forecasting; Neural networks; Neurons; Power system analysis computing; Power system modeling; Predictive models; Standards development; Adaptive artificial neural network (ANN); energy forecasting; optimization of ANN parameters;
Journal_Title :
Power Systems, IEEE Transactions on
DOI :
10.1109/TPWRS.2005.860926