@larryk ,
You’re asking a good question. I’m going to give you a longer answer than you might want, but understanding the different kinds of a Sense detections/identifications will help in understanding how to get the most out of your Sense.
There are four different general technical types of device identifications in Sense-land. And there could be more in the future.
-
Native Detections - for devices that have “clean” on and off transitions in the timeframe Sense is looking for (1/2 second transitions). Sense learns these on/off pairs as detections using machine learning and tries to categorize these based on the physics of the on/off measurements (Heat, Motor, Microwave, Light, Fridge). Unfortunately a wide range of devices don’t have clear transition-based on/off cycles, like most consumer electronics, PCs, etc., so Sense has added additional methods of detection (below).
-
Direct Measurement - These networked smart devices have built-in power meters that regularly update Sense over the network with the actual usage based on a measurements. This data can be used as “ground truth” for training Sense, but isn’t directly used to “learn” the specific waveforms of the connected devices. Measurement comes in a few flavors today:
- Smart plugs like your KP115 - report back to Sense monitor every 2 seconds or so
- DCM (dedicated circuit monitoring) - additional Sense CTs that report power usage on 1-2 specific 120V/240V circuits in your house.
- Hue lights - the Hue hub sends calculated usage info to the Sense monitor.
-
Special Native Detections - for devices that use lots of power, but don’t have on and off transitions that fit Sense’s 1/2 second detection windows, mostly HVAC and EV charging. Sense has developed special models for these, but they are very dependent on picking up the complex power ramps and waveforms that specific electric vehicle / AC / Heat pump models kick out. My Tesla detections have been found, then lost numerous times because Tesla software often changes charge.
-
Smart Assist - Sense uses readings from a smart device that doesn’t do power measurement, to assist with learning. The actual device still needs to have clear on and off transitions, but Sense gets clues from data coming from the device. Two flavors of this that I am aware of:
- NDI (network device identification) - Sense monitor uses network traffic to spot ons and off of some very specific smart TV models.
- Ecobee Historic - Uses Ecobee 5 minute updates to better refine HVAC detection. The data from the Ecobee comes too infrequently to be monitored on Sense directly (bubble would be off even though AC has kicked in), but is very useful in training Sense and improving Sense HVAC models.
-
Sense is also working on an improvement called Progressive Device Detection - more on it here:
[Video] 2021 Data Science Device Detection Updates
Native detections and Direct Measurement (via a smart plug) see the same devices in your house differently. Many complex devices, like your fridge, can generate a number of different native detections - one for the light (Light), one for the defroster (Heat), one for the compressor (Fridge/Motor), and one or two for the ice maker (Motor and possibly Heat). There are also some devices like electric burners or ovens that can show up as multiple devices based on their heat settings - High heat on a range can show up as a different native detection than Med. Or native detection might totally miss devices that don’t have nice on/off patterns altogether. Direct measurement detections (your KP115) faithfully shows the entire power that is flowing to the device or outlet strip plugged into it. As you have seen with your fridge, you can get into situations where Sense sees both native detections and direct measurements for the same device. You have two options in those situations:
-
If the native detections are picking up almost all of your devices usage, then you can pull your smartplug from that device (i.e. your fridge), and repurpose the KP115.
-
If the direct measurements from the KP115 are picking up substantially more usage than native detection, than you can tell Sense which detection(s) are included in that direct measurement from the KP115. There’s an option under Settings > Manage, that allows you to mark the native detections via “What’s connected to this?”. That does a special kind of merge, that avoids double counting.
