univariate time series prediction with artificial neural network

1 view (last 30 days)
I am new to MATLAB and time series and need help. I have a two column data of electricity consumption (Date, Consumption in kWd). I need a MATLAB code or procedure to enable me predict consumptions. I have 154 days of data and I want to prediction each consumption and plot it on a graph (actual, predicted) and calculate the root mean squared error. Thanks.
  3 Comments
Osman Yakubu
Osman Yakubu on 27 Dec 2018
Edited: Osman Yakubu on 28 Dec 2018
Thanks for your reply, it was really helpful. How do I plot the predicted and actual values? I also need the RMSE.
Please help.
Thanks
Kevin Chng
Kevin Chng on 4 Jan 2019
Edited: madhan ravi on 4 Jan 2019
Sorry for my late reply,
(Actual - Predicted) % Errors
(Actual - Predicted).^2 % Squared Error
mean((Actual - Predicted).^2) % Mean Squared Error
RMSE = sqrt(mean((Actual - Predicted).^2)); % Root Mean Squared Error

Sign in to comment.

Accepted Answer

Kevin Chng
Kevin Chng on 4 Jan 2019
refer to the link : https://www.mathworks.com/help/deeplearning/ref/narnet.html. Replace the dataset with your dataset.
For Calculating RMSE,
RMSE = sqrt(mean((Actual - Predicted).^2));

More Answers (0)

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!