Group 11 Senior Design

Machine Learning Applications in Power System Fault Location

using ADMS and AMI

Group Members:

          Michael Mederos        Computer Engineering
          Yuejun Guan            Electrical Engineering
          Julio Barreto Tannoux  Electrical Engineering
          David Silvieus         Electrical Engineering
        

Review Board:

          Dr. Zhihua Qu
          Dr. Aleksandar Dimitrovski
          Dr. Mike Borowczak
          Dr. Deepal Rodrigo
        

The objective of this project is to enhance the stability of the power system through the implementation of a machine learning model. By leveraging machine learning techniques to analyze large amounts of real-time data, a robust fault locator solution can effectively narrow down parameters, reducing restoration time, and improving overall efficiency for the utility industry. With real-time and on-demand measurements from ADMS (Advanced Distribution Management System) and AMI (Advanced Metering Infrastructure), the machine learning algorithms can process and reconsolidate grid data to accurately identify fault locations by measuring impedance using controlled currents. This enhanced fault location capability will facilitate expedited response times, leading to minimized downtime for customers and improved grid performance.

Documentation:

        10 Page D&C
        120 Page SD1 Final Report
        8-Page Conference Report
        

        CDR Slides
        Final Presentation Slides
        Final Presentation Video
        

        Final 120 Page Report
        Final Demo Video