Title :
Forecasting Distribution system Loads Using Curve Shape Clustering
Author :
Willis, H.L. ; Schauer, A.E. ; Northcote-Green, J.E.D. ; Vismor, T.D.
Author_Institution :
Advanced Systems Technology Division Westinghouse Electric Corporation
fDate :
4/1/1983 12:00:00 AM
Abstract :
Trending using curve fitting to past small area load growth is an economical but not highly accurate method of forecasting loads for distribution planning. A new trending method uses clustering of historical load at the small area level as the forecast algorithm. This new method has significant performance advantages over normal curve fit methods and can be implemented in 16 bit integer arithmetic on most computers. The method and test results are discussed in detail.
Keywords :
Clustering algorithms; Computational modeling; Curve fitting; Digital arithmetic; Economic forecasting; Load forecasting; Power generation economics; Shape; Spatial resolution; Testing;
Journal_Title :
Power Apparatus and Systems, IEEE Transactions on
DOI :
10.1109/TPAS.1983.317953
