top of page

AI Case Study

Android is planning to extend battery life in its mobile phones by implementing convolutional neural networks developed by DeepMind

Android is planning to implement research from DeepMind which analyses battery usage by apps on Android-powered phones. These convolutional neural networks predict consumption and adjust battery power accordingly, resulting in longer-lasting batteries.



Technology Hardware And Equipment

Project Overview

Android and Deepmind have partnered to "develop a feature called Adaptive Battery that uses a deep convolutional neural net to predict which apps you’ll use in the next few hours and which you probably won’t use until later. Using that knowledge, Android adapts to your usage patterns so that it only spends battery power on the apps you’ll need."

Reported Results

Android claims that "initial results have been very promising, and we’ve seen a significant reduction in background activity in our internal testing".



R And D

Product Management


"Android has worked to improve battery life with each release of its operating system. That shouldn’t be surprising, since surveys of smartphone users show that battery life is a top priority. Today, battery power is spent keeping apps up-to-date in the background so that they’re fresh when users open them next. But nobody uses all the apps on their phone with the same frequency, so in many cases that battery use might not be necessary."



Energy consumption data

bottom of page