The Smart Grid lets utilities pinpoint or prevent electrical outages by monitoring intelligent devices and sensors along the route in real time. However, conventional machine learning and statistics approaches are not efficient in handling the resulting amount and types of data.

“The availability and complexity of large-scale sensor and network data make conventional machine learning and statistics approaches to monitoring this data operationally useless,” said Ramin Moghaddass of the UM College of Engineering. So UM researchers are working with Florida Power & Light to develop advanced network-based data mining and deep learning tools that can analyze the massive amounts of smart grid data collected across Florida for smart decision making and control.

• Ramin Moghaddass