Title :
Improved load forecasting techniques for the newly electrified areas
Author :
Ijumba, Nelson Mutatina ; Hunsley, J.P.
Author_Institution :
Dept. of Electr. Eng., Durban-Westville Univ., South Africa
fDate :
6/21/1905 12:00:00 AM
Abstract :
This paper presents results of an artificial neural network model used to predict hourly peak demands of loads in a newly electrified area. Average forecast errors of less than 10% were achieved, using only limited historical data of the area´s load patterns
Keywords :
load forecasting; neural nets; power system analysis computing; area load patterns; average forecast errors; hourly peak load demands prediction; limited historical data; load forecasting techniques; newly electrified areas; Africa; Artificial neural networks; Data analysis; Demand forecasting; Design optimization; Feedforward systems; Load forecasting; Power system planning; Predictive models; Voltage;
Conference_Titel :
Africon, 1999 IEEE
Conference_Location :
Cape Town
Print_ISBN :
0-7803-5546-6
DOI :
10.1109/AFRCON.1999.821906
