Subtract Electric Vehicle Usage from Alerts

[kevin1]

My take is that it is hard to do anomaly detection (alerts for unusual usage) unless one can the known and controllable “hogs”, like EV charging out of the picture. I haven’t had any more time to work on my time-series forecasting with EV compensation, but really think I need to do it because the current alerts feel relatively random and not actionable without pulling out EV data.

Forecasting Energy Usage

Based on some recent discussions, I decided to try my hand at forecasting energy usage based on the output of my Sense. Time series forecasting is hot topic in the machine learning world, where past behavior is analyzed to predict future behavior. There are many different techniques that can be applied, but the real trick is matching the technique or model, to the actual behaviors(s) to get a prediction or forecast that is reasonably accurate and doesn’t get out of control (divergence). I’ll t…