While we’ve been publishing release notes for updates to our mobile and web apps for a while now, we haven’t been as good about sharing what’s going on “behind the scenes.” As we continue to try and tackle device detection challenges, our data science and engineering teams are constantly building and releasing new updates that help make small, incremental improvements to Sense’s capabilities. We’ve been trying to come up with a way to share more of this work with the community, to provide a window into what work has been going on and how it might improve device detection for our users. So this is our first shot at some “Device Detection Release Notes.” We won’t make these announcements for every improvement, but we’ll do so when there are particularly noteworthy ones like this.
We’re excited to announce a new device detector for Chevy Volt and Bolt electric vehicles. EVs can represent a significant portion of overall usage, and based on the feedback from our customers and our data analysis, we’re quite sure that many Sense users also have EVs. Sense currently detects certain Teslas (most Model S and Model X, though depends on manufacturing batch), BMWs (i3), and now Chevys (Volt and Bolt). We unfortunately still do not have reliable detectors for Nissan Leaf, Tesla Model 3, or other EVs, but are continuously working on improvements.
As always, please note that due to the nature of device detection and machine learning algorithms, there is no guarantee that if you have one of these devices at home, Sense will detect yours. How often you use a device plays a significant role in its detection. For electric vehicles, if you don’t charge your EV at home every couple days, then Sense may not be able to extract enough examples to train a reliable EV model. For example, if you often charge your EV at work or other parking garage instead of at home, or if you often just “top off” at home rather than going through a full charging process, there likely won’t be enough examples for Sense identify detection. In addition, Chevy detection, at this time, is reliant on use of a 240V EVSE. 120V charging will not be detected at this time.
Still, between the complexities of machine learning and the particularities of individual homes, even with time, Sense might not be able to detect a device. Based on specifics of other devices running in your home, or your unique usage of certain devices, certain devices can be tough for Sense to detect. EVs in particular present a unique set of challenges, due to their long-duration load profiles.
Thanks for your continued patience and feedback as we continue working on device detection. We couldn’t do it without you!