What is the Input and the Target for this case in the Time Series Tool (Neural Networks Tool)?

1 view (last 30 days)
Hello everyone I have all the daily values for the electricity demand of an installation (from the 1st of January of 2011 to the 31st of December of 2013) and I want to create a forecasting program that predicts the daily energy for each week.
How would the "imput" values be presented in the toolbox? What would be the "target" values?
I want to use fact that the actual month is a strong parameter
Every help I get will be highly appreciated.

Answers (1)

Greg Heath
Greg Heath on 25 Aug 2014
Edited: Greg Heath on 25 Aug 2014
1. Find the statistically significant lags using the autocorrelation function. Search
greg nncorr
2. Use a subset of the significant lags in the positive feedback delay vector, FD
3. help narnet
doc narnet
4. Search
greg narnet
5. Start with
net = narnet(FD);
Hope this helps.
Thank you for formally accepting my answer
Greg

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!