Indeed. Some nice analysis.
I started to assemble data yesterday from my AC and HW (hot water tank). Because I have the AC on the Wemo + Sense#2 Solar CT + Sense#1 native detection, I think it should be quite revealing. That along with the HW on Sense#1 native detection + Sense#2 Mains (dedicated to the HW circuit only) + Sense#2 native detection of the HW on the Mains.
Hopefully I’ll have time tomorrow to put things together.
Also thinking of @samwooly1’s “false notifications”. Though it’s a different issue, it made me think more about the on/off triggering and how that could be disrupted by other activity. It also has me wondering about the ML aspects, more of a raw calculation than raw patterns. e.g. If a 4kW HW tank is on while, say, there’s 500W of “known AO” running, then a 4kW drop in power would be a very strong indication of HW OFF whereas, say, that same 4kW drop to near zero overall load is more unlikely (the AO has had no sign of OFF) … a strong indication that the HW OFF was missed.