Region: All regions
Region: All regions
Once you have created your account with Sense and set-up details are complete, Sense begins to collect data and run its device detection algorithms. This is how Sense learns about your home’s electrical use.
Sense uses a high-resolution sampling rate to analyze changes in the magnitude, phase, and frequency of electricity throughout your home, using our complex machine learning algorithms to identify unique signatures of devices in your home. Because Sense needs to “see” a device run a number of times before it can recognize, verify, and ultimately label a device's electrical signature, the first devices identified are likely common devices that cycle frequently and consume large amounts of power, such as your refrigerator or washing machine. Lower usage or smaller load devices like game consoles and televisions tend to take longer for Sense to find.
You should begin to see devices detected within the first one to two weeks after Sense activation. Sense is always learning, and over the next several weeks it will continue to detect new devices and ask for you to name and verify its hypothesis. You will want to participate in the process, and this article explains how you can do that.
Note: You may be tempted to “train” Sense, since you know your devices, but please let Sense lead the way. Respond to the periodic messages the Sense app sends to you and study the reports Sense provides. Here is a discussion of why trying to “train” won’t really work, and could interfere with how Sense learns.
Due to variances across homes in terms of power quality and in the types of device present, 100% detection is unlikely. However, Sense is always learning and our detection algorithms are always improving. The more homes Sense works with, and the more users contribute by doing things like turning on networked device detection (article here) and renaming their detected mystery devices, the better our detection algorithms get!
For more information on our state-of-the-art device detection systems, take a look at this blog article on the topic.
For more information on our device detection systems, take a look at this blog article on the topic.