I just read the latest newsletter about the Belkin Wemo Insight and TP-Link Kasa HS110. The newsletter says devices will be detected in minutes. I’m guessing that doesn’t mean the entire power signature was detected such that you could move the smart plug around from device to device to to train the system right away but if you were to give each device a few days or a week or something could these smart plugs be used to effectively train the system?
Additionally and maybe if it doesn’t help with actual training, but I have had my unit for about a year? maybe more? and have a horrible time trying to figure out what devices sense has actually found. I’ve got about 6 heating devices and I don’t really know what many of them are. I tried checking the community suggested device names and none of them turned on in sense when I turned the device on. Maybe It could be used to figure out devices sense has already found. For instance plug the fridge into it and verify the Fridge in sense is on that same smart plug.
No - you can’t move the Smartplug around.
Yes - it will help with training over the long haul
Yes - you can put your fridge on it to see what the fridge is using.
Turn on notifications in the app for all of them. When you’re in the house puttering around and you get a notification on your phone that one of them turned on…ask everyone in the house immediately what they just turned on.
I narrowed down and identified a number of mystery devices this way.
I got a few TP Links once I knew the direction they were going. I put them on items that I wanted better visibility to and Sense is giving me that. I am going to buy more as needed. I may never use the on/off function on a frig, but having an accurate read and helping the community identify the signatures is worth it.
Question for forum members and Sense beginners…is anyone I’m using both? Any advantage of one over the other? I have TP-Link. I am going to grab two Wemo’s and try them out. I have Sense Thermostats and like IFTTT, so maybe there are some additional things I will be able to do. If anyone has first experience with both, please pipe l up! Thanks!!
TP Link is generally less expensive vs Wemo for many/most of their modules.
TP Link has great warranty.
TP Link HS110’s default to on after a power outage vs off. This is a biggie for those using their devices on mission critical things like refrigerators etc.
TP Link HS110’s are 240V compatible out of the box.
I have a lot of Wemo hardware but increasingly am buying TP LInk vs more Wemo stuff.
So much for Sense’s “machine learning” and “signature recognition”. Apparently it needs device by device sensors too, just like monitoring a decade earlier.
@andy
I only use smartplugs on the really tough devices or sets of devices, with the hope that the smartplugs will eventually help with more challenging devices. I have 45 found devices in my house, of which only 11 are smartplugs (3 are merged “found devices” and smartplug). For me, that’s a great compromise given smartplugs have much tighter granularity/specificity than house circuits.
I’ve only been a Sense user for a little over a month and virtually every major consumer in our house has been natively detected short of our EV’s…which ARE actually supported models that would have eventually been detected, but the fact we own 2 identical cars complicated things.
I have no complaints either - it’s unrealistic to expect Sense to be able to identify every single thing in existence, and the option (not a necessity) to use a smartplug to feed in more data on hard to identify devices (and provide ground truth learning possibilities for others in the future) is a plus, not a negative.
Congratulations. Your results are vastly better than ours…Sense engineering tells me that my home (in particular my deep well constant pressure pump) isn’t “Sense friendly” and after 19 months it’s detected very few of our 117+ electrical devices…and those not very reliably. So, when I get a chance, I’m going to pull it out of the various panels (circuits in one, solar in another) and give up.
How are you supposed to hear a conversation across the room with someone yelling in your ear?
That is what you’re expecting of Sense. The sheer amount of electrical noise your house has just from so many devices on it is the constant yelling. It only makes ‘Sense’ that you’re house is challenging is not impossible.
I too recently installed geothermal (open loop with variable speed well pump like you), and depending on how much yours runs I can easily see how devices are ‘missed’ or never learned.
Here is the sequence JUST for the geothermal part of your electrical load:
Heating call pump turns on
Blower moter ramps up (if its a fan coil)
Buffer tank setpoint hit, calls for heat pump to turn on
Before heat pump turns on, open loop solenoid opens and allows your well water to flow
Buffer tank circulation pump turns on
Desuperheater pump turns on (if equipped)
Heat pump compressor turns on (huge power event)
Variable speed well pump may or may not have turned on yet depending on pressure tank size and where the pressure was at before the heat call
Number 8 is a big deal because it looks different almost EVERY TIME the system cycles because it can happen anywhere through the stage at EXACTLY or very close to other devices in sequence.
While I would love for Sense to identify all these things perfectly, its not realistic. If you want precision you’ll have to look into something purpose built like WELServer.
In the meantime I have my variable speed well pump hooked to a HS110…
Correct, but that’s never mentioned in the Sense marketing….have also never seen it in the FAQ.
I installed a WELserver a decade ago when we built our home, and it’s worked perfectly. It monitors the biggest consumers (Geothermal, hot water heater, radiant system, A/C, Solar, etc), but the reason I bought Sense was to get a handle on all the other devices (washer, dryer, stove, ovens, refridge, computers, printers, entertainment center, etc) and it’s done none of that…sigh. So, I’m giving up.
I bought a Wemo just to make a fair comparison. The default power on feature is a big deal. The Wemo community has been asking for this for several YEARS.
Because of this, I can’t put the Wemo on any critical devices.
TP-Link was also real easy to install and Sense found it faster.
Sense Team,
Do you get useful data to help with your machine learning for finding devices that are not plugged into smart plugs? By using these devices, are we helping the process or just prolonging the eventual detection?
The short answer is yes, we absolutely get useful data and that was one of the main impetuses behind this integration. Finally, we can get real ground truth data from devices that are otherwise pretty tough to nail down. As the blog states, this does not net immediate benefits for ML detection, i.e., you can’t “train” Sense with smart plugs, but it gives us loads of great data to build better models, which will improve detection for everyone down the line.
Machine Learning is typically done by training the ML/AI engine though, so I continue to question why Sense keeps insisting you can’t “train” Sense with more data? All ML things I’ve done/seen are typically done by training the models to recognize things by providing it lots and lots and lots of data samples. For example training an AI engine to recognize a cat in a photo you build your models and then feed it 1 million pictures of cats and your recognition should be somewhere in the > 99% recognition range.
Granted I understand there’s not 1 million Sense users (yet) and certainly not 1 million Sense users that would have the same device (make/model/etc) on one of these Smart Plugs to create that kind of an accuracy, but you definitely should be able to use the data from the Smart Plugs as “training” data for the ML engine to “recognize” that this particular set of data belongs to “device type x” of “brand y” and model “z” (assuming people fill this out in the fields available) to use that to train the ML engine. Every data point is another data point that will make the ML engine smarter/better, so feeding this data to the ML engine seems like the correct way to “help” the engine learn more/faster/better/etc.