Machine Learning for Smart Maintenance of NYC's Secondary Electrical Grid

Dr. Cynthia Rudin
Columbia University

Abstract: Dr. Rudin will describe work from a long-term collaborative effort between Columbia University's Center for Computational Learning Systems and Con Edison, which is New York City's electrical utility company. There are a few hundred manhole events (fires, explosions, smoking manholes) in NYC every year, often stemming from problems in the secondary (low voltage) electrical distribution network that provides power to residential and commercial customers. The goal of our project is to predict manhole events in order to assist Con Edison with its pre-emptive maintenance and repair programs. The success of this project relied heavily on an understanding of the current state of Manhattan's grid, which has been built incrementally over the last century. Several different sources of Con Edison data are used for the project, the most important of which is the ECS (Emergency Control Systems) database consisting of trouble tickets from past events. These tickets are mainly recorded in free text by Con Edison dispatchers.

Dr. Rudin will discuss the data mining process by which they transformed extremely raw historical Con Edison data into a ranking model that predicts manhole vulnerability. Their ranked lists are currently assisting with the prioritization of future inspections and repairs in Manhattan, Brooklyn, and the Bronx.

This is joint work with Becky Passonneau, Axinia Radeva, and several others at the Center for Computational Learning Systems at Columbia University, and Delfina Isaac and Steve Ierome at Con Edison.

Bio: Cynthia Rudin is an assistant professor at the MIT Sloan School of Management in the operations research and statistics group, and an adjunct research scientist at the Center for Computational Learning Systems, Columbia University. She works on machine learning and knowledge discovery problems relating to data-driven prioritization. Dr. Rudin holds undergraduate degrees from the University at Buffalo, and received a PhD in applied and computational mathematics from Princeton University in 2004. From 2004-2007, she was an NSF postdoctoral research fellow at NYU, before starting work as a research scientist at Columbia in 2007, and joined MIT Sloan in 2009. She is the recipient of several awards, most recently including the NSF CAREER award and a Solomon Buchsbaum Research Fund grant. Her work on smart energy grid maintenance was featured in articles appearing in IEEE Computer, ScienceNews, WIRED Science, U.S. News and World Report, Slashdot, Discovery Channel, CIO magazine, and Energy Daily.

Sponsored by the Interdisciplinary Center for Network Science & Applications.