North Carolina State University

Total Solar International

Gonzague Henri

Ning Lu

Carlos Carrejo

A method, system, and device for controlling an energy storage device are provided. The method includes determining an operating schedule for the energy storage device based on at least an initial cost. The initial cost is a function of at least a load profile and a power production profile of at least one renewable energy source associated with the energy storage device. The operating schedule is for a predetermined period. The method further includes determining an updated cost based on at least the operating schedule, identifying an operating mode from a plurality of operating modes for a predetermined operating period based on the updated cost and the operating schedule; and operating using the operating mode for the predetermined operating period.

System, device, and method for mode-based energy storage management

A method, system, and device for controlling energy storage devices are provided, the method including receiving a trained machine learning model from a centralized machine learning system, recording temporal data for a respective energy storage device, periodically transmitting the temporal data to the machine learning system, performing a mode prediction for controlling the energy storage device using the trained machine learning model and the temporal data, and sending a control signal to the energy storage device to operate in the predicted mode. The machine learning system aggregates the temporal data transmitted by each agent and uses the aggregated temporal data to update the machine learning model. By using aggregated temporal data, less data is needed from an individual energy storage device so that when a new energy storage device joins the machine learning system, the new energy storage device can benefit from increased performance with less computation.

Growing community of inventors

Raleigh, NC, United States of America

Gonzague Henri