The Internet-of-Things (IoT) paradigm can be scaled up to the level of civil, commercial, and residential infrastructure. The prevalence of smart-grids, smart-home technologies, and Building Automation Systems make energy optimization within the reach of distributed AI approaches.

 

The Smart Grid is a networked system of sensors, controllers, and machines that share data to collectively optimize for a global objective. Smart Grids can intelligently manage energy usage to save costs, improve safety, and ensure human comfort. However, the availability of large amounts of data presents inherent privacy risks and computational costs.

 

Federated Learning can be used to keep data private while sharing intelligence to collectively increase performance. Additionally, Deep Reinforcement Learning can be used to provide adaptive controllers that tailor their operations to changing environments and individual requirements of machines in the smart grid. The STADLE platform combines these two approaches to provide private, adaptive, and distributed AI.