This week I spent time revising my methodology for accessing and providing a baseline model for each of our training data sets (load, wind generation, and solar radiation).
In response to learning more about the SUGAR simulation tool we’re using, I decided to do away with the persistence algorithm we were previously using as a baseline algorithm, since recently observed power generation/demand will not be available to our models as a part of the simulation output. Instead, I decided to fit a linear regression model using weather and time as features and power/radiation/demand as the target variable. So far I’ve gathered Relative-MSE scores of 0.59 and 0.41 for our solar and wind data respectively, indicating that we have far to go in terms of improving our predictions. With these results and the results I will soon have for our load data, I am reasonably on pace for my forecasting goals.
Next week, I plan to generate baseline metrics for our load data with a linear regression model as well. Also, as the designated project manager for these two weeks before spring break, I will be devoting much of my time to developing our design report.