Abstract—Very short-term load forecasting predicts the loads
in electric power system one hour into the future in 5-min steps
in a moving window manner. To quantify forecasting accuracy in
real-time, the prediction interval estimatesshould also be produced
online. Effective predictions with good prediction intervals are important
for resource dispatch and area generation control, and
help power market participants make prudent decisions. We previously
presented a two level wavelet neural network method based
on back propagation without estimating prediction intervals. This
paper extends the previous work by using hybrid Kalman filters
to produce forecasting with prediction interval estimates online.
Based on data analysis, a neural network trained by an extended
Kalman filter is used for the low-low frequency component to capture
the near-linear relationship between the input load component
and the output measurement, while neural networks trained by unscented
Kalman filters are used for low-high and high frequency
components to capture their nonlinear relationships. The overall
variance estimate is then derived and evaluated for prediction interval
estimation. Testing results demonstrate the effectiveness of
hybrid Kalman filters for capturing different features of load components,
and the accuracy of the overall variance estimate derived
based on a data set from ISO New England.