Even before Sense discovers devices in your home, it’s easy to see how much energy they consume just by turning them on and off and watching the Power Meter in real time. Check this video to learn more.

Once Sense completes the signal check process, it will start detecting devices in your home. Sense is able to identify many electrical devices in typical homes, and we continue to expand our device detection abilities via crowdsourced data as more Sense monitors come online. However, it likely won’t detect everything. Low-wattage consumer electronics like computers, smart devices, and game consoles can be especially tough to track. In the meantime, many users have had great success tracking these more challenging loads via a smart plug integration.

Learn more about the machine learning technology that undergirds Sense here.

Sense should only be installed by a licensed electrician. Installation itself is quick and easy, but it requires opening up your electrical panel and connecting current sensors to the service mains. These wires are live, even with your main breaker switched off, and are thus very dangerous. Only a licensed electrician is qualified to work in these conditions.

When speaking with your electrician, let them know that Sense is an energy monitor that installs in your electrical panel with two clamp-on current sensors around the mains, and a 240V breaker which Sense uses for its power supply and also to measure voltage on both legs. Unless you have a spare 240V breaker in your panel, your electrician will likely need to provide a new one.

You may also wish to share with your electrician this blog post and video to help them get a better idea for what’s required.

A set of installation instructions is also included in the package, and available online.

All communications between the Sense monitor, the Sense cloud servers, and Sense apps are encrypted with AES 128-bit encryption and TLS/SSL (HTTPS). Sense uses Amazon Web Services (AWS) for cloud servers and online storage. Personally identifiable information like email address and account information is stored in physically separate systems from any application data. Physical security is managed by Amazon and access to these production systems is limited to a very small group of Sense engineering team members.

Automated systems process the data collected from Sense monitors to detect devices, send notifications, generate report emails, and power the Sense apps. Sense never shares any of this data with 3rd parties without explicit user opt-in on a case-by-case basis (for example, when a utility wishes to provide discounts/services to their customers in exchange for sharing limited power data.) Sense support employees will on occasion need to access some of this data to troubleshoot issues, but again we will only access this data with explicit permission from you.

You can read Sense’s full privacy policy here.

After your Sense monitor is installed and the signal check process is complete, Sense will start pulling in data to feed its device detection algorithms. The device detection process is not immediate; Sense needs to see many on/off event cycles of a device in order start building up a model for it. Most customers will start seeing detections within the first one to two weeks. The first devices identified are often common devices that cycle frequently and consume large amounts of power, like your refrigerator or washing machine. Less commonly used, smaller load, or complex signature devices like coffee makers, televisions, and electric vehicles tend to take longer to find.

Please note that due to variances across homes in terms of power quality and in the types of device present, total detection coverage of your entire home is unlikely. To better understand how you can help Sense learn about your home, please see this Help Center article.

Sense needs to see devices in their usual context with their regular usage pattern to be able to accurately identify them. That means that “training” Sense by turning devices on/off and labeling them is not an effective method to help Sense learn. You can learn more about the challenges of implementing a “learning” mode here.

While you cannot “train” Sense in such a way, we have introduced a variety of features that take advantage of user input to help improve device detection in your home and for the entire userbase.

– Network Identification allows Sense to see some of the simple “handshake” messages put out by your networked devices.
‍
– Integrations with smart bulbs from Philips Hue and smart plugs from TP-Link Kasa and Belkin Wemo will net you instant detections for connected devices and provides great data to the Data Science team.
‍
– Renaming your devices, supplying the make/model, taking advantage of the Community Names feature, and filling out your Home Details feeds the Data Science team great data that improves detection for everybody.
‍
– When Sense finds a device, but you’re finding the detections to be inaccurate, you can report it as “not on.” This feeds our Data Science team valuable information so they can continue to refine the detection model.
‍
Remember, even without native detections, you can still take advantage of Sense insights. The Power Meter is a fantastic tool that provides a real-time view of your energy consumption. Try turning on and off your devices while watching in the Power Meter, to identify how much they consume. You can do the same for the “Always On” devices in your home, identifying how much they’re costing you every day.