Stem, an energy startup, has developed a battery that predicts when to store and when to release electricity in order to best save the user money.
The battery is intended for commercial buildings as of now. It allows a buidling owner to analyze energy usage patterns and adjust thermostat settings accordingly, Technology Review reports.
Indeed, many battery management solutions that have lately been emerging focus on this sort of intelligent adaptive algorithms.
The algorithms it uses come from financial sector, and they are used to predict a building’s hourly power usage.
Once it determines this, the battery will supply power during peak use, when prices tend to be higher, allowing the user to avoid additional fees.
From MIT’s Technology Review:
“This sort of thing was not possible five or six years ago. For every given site, we will literally run millions of simulations a day,” says Stem founder and executive vice president Brian Thompson, a former IT professional who developed high-volume e-commerce systems.
The battery itself is similar to an automobile's lithium-ion battery. It is attached to electronics that facilitate the switch from supplying power to charging off a grid.
The measurements are performed via an Internet connection and processed through an on-site computer, which uses an intelligent technique to ‘learn’ patterns.
Stem began at the Wharton Business School at the University of Pennsylvania. The company originally intended to create batteries to store solar power.
Stem currently focuses on the East Coast and on California, hoping to expand further, and it is partnering with 20 industries.