Скачать или смотреть No Code ML for Smart Grid Stability | Business Statistics

I show an example of using machine learning to predict grid stability.

I'm using a data set that's been curated by UCI and is available through Kaggle. The data set is in really great shape, which is unusual for the real world, but it's a great learning tool.

I'm going to use Amazon SageMaker Canvas, which is a no-code tool that makes it easy to build machine learning models.Canvas offers three different build options:

Preview model: This is a quick and easy way to see if the data is even useful to predict the target variable.
Quick build: This builds a larger model that runs multiple passes through the data and does some additional techniques like transformations of the data.
Standard build: This builds the most comprehensive model, but it takes the longest to run.
For this example, I'm going to use the preview model and the quick build.

The preview model takes about two minutes to run. Once it's finished, Canvas shows me the accuracy of the model. In this case, the model is accurate 97% of the time.

The quick build takes a few minutes longer to run. Once it's finished, Canvas shows me the accuracy of the model. In this case, the model is accurate 98% of the time.

The accuracy of the model is pretty good, but it's important to note that this is a very clean data set. In the real world, the data is often not as clean, so the accuracy of the model may be lower.

Overall, I'm pretty happy with the results. I was able to build a machine learning model to predict grid stability in a very short amount of time.

I hope you found this video helpful.