Sense listens to those voices through two current sensors clamped on the service mains in your home electric panel.
Sense samples current and voltage 1 million times per second. That’s 900 million times faster than utility “smart” meters.
Sense consumes just four watts, about the same as charging a smartphone.
Sense uses this high-resolution data to detect small changes in magnitude, phase and frequency, and then applies machine learning algorithms to distinguish one appliance from another — to recognize individual voices in that noisy conversation.
As the filament heats up, it draws a lot of current, but then stabilizes. The current and voltage are in phase with each other, so Sense knows it’s a resistive load. These are distinctive voices that stand out from the crowd.
It's irregular because the clothes are sloshing around inside the drum. These squiggly lines show the washer's agitation cycles. Sometimes Sense detects the heater and motor individually, and you can just combine them into one device that you name “Washer.”
First there's a surge to get started, it continues running, then turns off completely. Then kicks back on to maintain its temperature. You might think a refrigerator runs all the time, but it actually cycles on and off throughout the day to maintain its temperature.
There are many devices Sense can’t yet detect, but as the Sense community grows, the machine learning algorithms gather more data. And with more data, Sense will start to identify new devices, so your Sense will just keep getting smarter!