Would appreciate any more specifics you have on heuristics for detecting a 13A and above usage ramps and dropoffs. I’m trying to build an accurate edge detector that “finds” my EV charging cycles. I don’t have access to the same high res usage data as Sense, but I figure my every 15 min read from smart-meter merged with Sense data should be enough, given the 48A and 80A draws of each EV. I have one machine learning model “working” on my 2020 data, but now I need a way to label my 2019 data, since I didn’t collect charger info in 2019. Thoughts appreciated.
1 Like