Artificial neural networks represent a growing new technology as indicated
by a wide range of proposed applications. At a substation, when the transfo
rmer's windings get too hot, either load has to be reduced as a short-term
solution, or another transformer bay has to be installed as a long-term pla
n. To decide on whether to deploy either of these two strategies, one shoul
d be able to predict the transformer temperature accurately, This paper exp
lores the possibility of using artificial neural networks for predicting to
p-oil temperature of transformers. Static neural networks, temporal process
ing networks and recurrent networks are explored for predicting the top-oil
temperature of transformers. The results using different networks will be
compared with the auto regression linear model.