Summary: An Online Learning System for the Prediction
of Electricity Distribution Feeder Failures
Hila Becker
Columbia University
hila@cs.columbia.edu
Marta Arias
Center for Computational Learning Systems
marta@ccls.columbia.edu
Experiments
This work has been partly supported by a research contract from
Consolidated Edison Company of New York
Motivation
Electrical feeder cables are an essential part of the network
that distributes electricity to the boroughs of New York City
The feeders have a significant failure rate, and many
resources are devoted to their maintenance and repair
We would like to produce a ranking of these feeders
according to their failure susceptibility, in order to monitor
them and take preventive action
Since we can gather a lot of data about feeder

Source: Arias, Marta - Departament of Llenguatges i Sistemes Informátics, Universitat Politècnica de Catalunya

Collections: Computer Technologies and Information Sciences