Title :
Reduction in power system load data training sets size using fractal approximation theory
Author_Institution :
Fac. of Electr. Eng., Beograd Univ., Yugoslavia
Abstract :
Summary form only given. Fractal dimension is further used in reconstruction of forecasting data by iterated function system. Due to the generalisation property of artificial neural networks, the proposed method results in significant savings in computational time. The original fractal structure of data is preserved in forecasting
Keywords :
fractals; load forecasting; neural nets; power engineering computing; power system planning; training; artificial neural networks; computational time; forecasting; fractal approximation theory; power system load; training data set reduction; Approximation methods; Artificial neural networks; Backpropagation algorithms; Fractals; Load forecasting; Power system analysis computing; Power system measurements; Power system modeling; Power system planning; Power systems;
Conference_Titel :
Data Compression Conference, 1991. DCC '91.
Conference_Location :
Snowbird, UT
Print_ISBN :
0-8186-9202-2
DOI :
10.1109/DCC.1991.213315
