Loading…
  • Sessions appear in the color of their primary track
  • Sessions can be filtered using Products on the right
  • Use the Search bar for more flexibility
See this link for hints on how to search the schedule or sign up for sessions

View analytic
Tuesday, March 20 • 3:35pm - 4:05pm
Forecasting the storm recovery resource allocation in electric utility network

Log in to save this to your schedule and see who's attending!

Feedback form is now closed.
A leading cause of power outages in the US is weather driven equipment failure events. Oracle utility customers are seeking machine learning techniques (recommended by the USDOE) to improve real-time risk assessment for critical assets based upon incoming weather forecast. Given an accurate prediction for the location, type, and amount of the storm-damaged equipment, the utility company can position the right number of specialized crews and material resources ahead of time. We develop a novel machine-learning model trained on the history of asset failures and reported weather. Since the weather-reporting stations might be far from the assets and some weather data measurements might be missing, we interpolate the weather conditions at the asset locations using a triangularization function computed with a barycentric coordinates technique implementation. We report performance comparison of multiple machine learning models to recommend the best damage prediction tool.

Speakers
avatar for Kenny  Gross

Kenny Gross

Solutions Architect, Oracle
Kenny C Gross, PhD, is an AI Architect in Oracle's Physical Sciences Research Center in San Diego, CA. Kenny specializes in advanced pattern recognition and prognostic anomaly discovery for Big Data applications in IoT industries, life sciences, and business business-critical data center assets and networks. Kenny has 251 US patents issued and pending, 208 scientific publications, and was awarded a 1998... Read More →
avatar for Andrew Vakhutinsky

Andrew Vakhutinsky

Consulting Member of Technical Staff, Oracle
Andrew Vakhutinsky is a Consulting Member of Technical Staff at Oracle Labs. He has Ph.D. in Operations Research from University of Maryland, College Park, and M.Sc. in Physics and Applied Mathematics from Moscow University of Physics and Technology. Andrew's previous experience... Read More →


Tuesday March 20, 2018 3:35pm - 4:05pm
4-Rm 104

Twitter Feed