CrowdAmp crowdsources, predicts app energy usage

Share this post:

Mobile app usage in 2013 posted 115 percent year-over-year growth. From social networks and games, to banking and fitness tracking, and much more, we often choose these apps based on their popularity ratings. IBM Research is working on another way to evaluate apps: by their energy ratings.
Today, there’s no way to rate how quickly an app might drain your specific phone battery. But a power-hungry app – especially those running ads – can quickly drain a smartphone’s battery.
Scientists Raghavendra Singh, Ravi Kothari and Vijay Mann, at IBM’s research lab in India, patenteda system they’re calling CrowdAmp to predict the battery drain caused by apps – before a potential user installs them. The system makes its predictions based on a smartphone owner’s usage pattern, current device setting, and hardware configuration, as well as the application’s power profile as observed on other users’ phones.
The power of the crowd
Today, there’s no way to rate how quickly an app might drain your specific phone battery. 

But a power-hungry app – especially those running ads – can quickly drain a smart- phone’s battery.

CrowdAmp is a lightweight application that records the usage of various hardware units on a smartphone, including: back light, cellular service, WiFi and bluetooth. It also records the battery’s profile for its age and drain time. Based on this data, CrowdAmp uses an app-matching algorithm to predict the power drain of any app – so, now a smart device owner will know an app’s predicted battery usage on his or her device before he or she even installs it.
While not publicly available yet, when users want to download and install a new app, they could run CrowdAmp to check the battery usage of an app they want. Through their individual user profile, which combines a user’s device hardware usage patterns, battery drain time and age, and other software and hardware details (which get uploaded to a repository), CrowdAmp compares it with other stored hardware and battery profiles of other users who already installed the desired application.
CrowdAmp users would also get a chart of their own device’s usage profile, letting them see which hardware device (and related activity) is draining their battery the most. The battery drain time statistics can also be sent to application developers to help them improve their app’s energy efficiency.
This will be the first time that mobile app power usage can be predicted before installation, and also compared between other apps, with respect to their impact on battery life. As the app market continues to grow, there is no question that it is important to design and install apps that minimize power consumption in mobile devices.
IBM has led in total U.S. patents for 21 year in a row in 2013. Read more about patents like #8,452,352, here.

More stories

A new supercomputing-powered weather model may ready us for Exascale

In the U.S. alone, extreme weather caused some 297 deaths and $53.5 billion in economic damage in 2016. Globally, natural disasters caused $175 billion in damage. It’s essential for governments, business and people to receive advance warning of wild weather in order to minimize its impact, yet today the information we get is limited. Current […]

Continue reading

DREAM Challenge results: Can machine learning help improve accuracy in breast cancer screening?

        Breast Cancer is the most common cancer in women. It is estimated that one out of eight women will be diagnosed with breast cancer in their lifetime. The good news is that 99 percent of women whose breast cancer was detected early (stage 1 or 0) survive beyond five years after […]

Continue reading

Computational Neuroscience

New Issue of the IBM Journal of Research and Development   Understanding the brain’s dynamics is of central importance to neuroscience. Our ability to observe, model, and infer from neuroscientific data the principles and mechanisms of brain dynamics determines our ability to understand the brain’s unusual cognitive and behavioral capabilities. Our guest editors, James Kozloski, […]

Continue reading