Sense needs to see devices in their usual context with their regular usage pattern to be able to accurately identify them among all the electrical activity that occurs in your home. 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 some challenges of implementing a “learning” mode here and 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 user base.
- First and foremost, you should work actively with Sense, as you are the expert on what appliances are in your home and when they are running.
- As you set up your account, be sure to answer the few questions about your devices that the system asks you. The answers allow Sense to promptly share valuable information about those appliances as it begins to learn about your home’s usage.
- As Sense proposes a hypothesis about individual appliances, name the identified device in a way that makes sense to you.
- Also help Sense work with complex devices that comprise more than one motor or heating element -- or both. Merge these components of the same complex device into one named device. For example, your clothes dryer turns the clothes bin with one motor, regulates air temp with a heating element, and has at least one lighting element. Sense will likely identify each component as a separate device, but you should merge them. See this article for instructions.
- If you have networked devices, such as your TV or media center, Network Identification allows Sense to see some of the simple “handshake” messages put out by those devices.
- Integrations with smart bulbs from Philips Hue and smart plugs from TP-Link Kasa will net you instant detections for connected devices and provide great data to the Data Science team.
- Renaming your devices, supplying the make/model and taking advantage of the Community Names feature 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 delete that device and give the algorithm a chance to gather more information then try again.
Remember, even before 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. You can turn devices on and off 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.