The new battery system uses machine learning to track your activities and learn habits to determine when you need power and when you don't. Photo credit: Gigaom
The new battery system uses machine learning to track your activities and learn habits to determine when you need power and when you don't. Photo credit: Gigaom
Advertisement Advertisement  

Microsoft Research has come up with a brand new laptop battery system which not only learns all your habits but it also provides longer autonomy based on the stuff you do on a computer.

Basically, Microsoft’s new system uses a very simple idea: why not building a laptop battery system which perfectly suits every user’s way of working on the computer and thus make sure that they have the necessary power exactly when they need it, while running at the lowest possible level the rest of the time.

All laptops come with the same kind of battery, which already provides decent autonomy, but every time, these batteries charge and power the device in the exact same way. The hardware is specifically optimized for the battery and the operating system barely has anything to say, other than managing power plans.

More types of batteries under the same roof

In Microsoft’s project, these laptops use more than one type of battery and can provide better results in different scenarios, such as when needing a fast charge. Basically, every built-in battery can be optimized for a specific task, so when you start this process, all the other batteries go in stand-by, thus preserving power for later.

Microsoft explains that “The software-defined battery system takes a different approach. It combines several different kinds of batteries, all of which are optimized for different tasks, into the same computer. Then, it works with the operating system to figure out whether the user is, say, looking at Word documents or editing video footage, and applies the most efficient battery for that task.”

And that’s not all. The new battery system uses machine learning to track your activities and learn habits to determine when you need power and when you don’t. For example, if you recharge your battery every day for 15 minutes before an important presentation, the system would be able to learn that you need a fast charge to get through this presentation without the risk of running out of battery life.

Microsoft says that the very same system can be used on phones and other devices, but for the moment it’s still in development stage, so it could take a while until they go into full production.

[Softpedia]