Power load forecasting using neural canonical correlates

We have previously [4,3] derived a neural network implementation of the statistical technique of Canonical Correlation Analysis (CCA). We have then extended the network so that it may find nonlinear correlations in data sets. In this paper, we demonstrate the capabilities of the network (both linear and nonlinear) on an artificial set and demonstrate that the nonlinear network finds greater correlations than any linear network. We then use both networks on a forecasting problem - that of forecasting the next day's power loading given the previous days' loads and forecasts of the temperature. We show that the nonlinear correlation method performs better than standard supervised learning neural networks using backpropagation and also a recent modification of that algorithm.