JSM 2013 Home
Online Program Home
My Program

Abstract Details

Activity Number: 173
Type: Topic Contributed
Date/Time: Monday, August 5, 2013 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Mining
Abstract - #310205
Title: The Reactive Point Process Model and Its Application to Electrical Grid Reliability
Author(s): Seyda Ertekin*+ and Tyler H. McCormick and Cynthia Rudin
Companies: MIT and University of Washington, Seattle and Massachusetts Institute of Technology
Keywords: point-process models ; short-term prediction ; electrical grid reliability ; case-control design ; ABC (Approximate Bayesian Computation) ; log-likelihood method
Abstract:

We present a statistical model for predicting discrete events over time. The applications of this model are wide-ranging, though we specifically apply the model to power grid reliability in NYC, where the events we wish to predict are power failures. In power grid reliability, there are past events (power failures); also there are interventions (inspections), where an action is taken to temporarily reduce the probability of an event. Our model is simple yet possesses several desirable properties: i)The model predicts the vulnerability to events smoothly over time, ii)The most recent past events or interventions have the strongest impact for predicting future vulnerability to events. These are self-exciting or self-depressing terms, iii)The effect of a past event or intervention wears off gradually over time, and iv)The effect of several events or interventions occurring close together saturates, keeping the model reasonable. This model, and advances in the preparation of our NYC power grid database from Con Edison, allow us to make short term predictions of power grid failures in NYC, which was not possible a few years ago.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2013 program




2013 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.