Asee peer logo

Board 70: Development and Implementation of a Non-Intrusive Load Monitoring Algorithm

Download Paper |

Conference

2019 ASEE Annual Conference & Exposition

Location

Tampa, Florida

Publication Date

June 15, 2019

Start Date

June 15, 2019

End Date

June 19, 2019

Conference Session

Energy Conversion and Conservation Division Poster Session

Tagged Division

Energy Conversion and Conservation

Tagged Topic

Diversity

Page Count

14

DOI

10.18260/1-2--32411

Permanent URL

https://peer.asee.org/32411

Download Count

96

Request a correction

Paper Authors

biography

Robert J. Kerestes University of Pittsburgh

visit author page

Robert Kerestes, PhD, is an assistant professor of electrical and computer engineering at the University of Pittsburgh's Swanson School of Engineering. Robert was born in Pittsburgh, Pennsylvania. He got his B.S. (2010), his M.S (2012). and his PhD (2014) from the University of Pittsburgh, all with a concentration in electric power systems. Robert’s academic focus is in education as it applies to engineering at the collegiate level. His areas of interest are in electric power systems, in particular, electric machinery and electromagnetics. Robert has worked as a mathematical modeler for Emerson Process Management, working on electric power applications for Emerson’s Ovation Embedded Simulator. Robert also served in the United States Navy as an interior communications electrician from 1998-2002 on active duty and from 2002-2006 in the US Naval Reserves.

visit author page

biography

Dekwuan Stokes University of Pittsburgh

visit author page

Dekwuan is a senior electrical engineering major at University of Pittsburgh.
He plans to enroll in the PhD program with a focus in power, as well as, achieve his MBA throughout the process.
His career choice and long term goal is to become a professor and to start his own businesses.
Outside of school, Dekwuan likes to play basketball, video games and enjoy time with his family and friends.

visit author page

biography

Ryan M. Brody University of Pittsburgh

visit author page

Ryan Brody graduated in April 2018 from the University of Pittsburgh with a bachelor's degree in electrical engineering with a concentration in electric power systems and a minor in computer science. He has since started a master's degree at the University of Pittsburgh studying electrical engineering and electric power systems. He is interested in researching power electronic converters and battery management systems for electric vehicle fast charging and distributed energy resources in smart grids. He is also interested in engineering education, aspiring to be a professor when he is older.

visit author page

biography

Adam Emes University of Pittsburgh

visit author page

Adam Emes completed his B.S. in electrical engineering, with a concentration in electric power engineering, from the University of Pittsburgh in 2018. In his time as an undergraduate, he completed three co-op rotations at Curtiss-Wright EMD, and worked part time as an undergraduate student researcher. From his co-op position, he gained experience with electric motor and generator design. In his undergraduate research, he contributed to projects that utilized signal processing in fault classification and load detection applications. He is currently a second year M.S. student in the electric power systems group at Pitt. His research interests include power converter stability analysis for renewable energy systems.

visit author page

biography

Alexander Williams University of Pittsburgh

visit author page

Undergraduate Electrical Engineering Student at the Swanson School of Engineering

visit author page

Download Paper |

Abstract

Smart grid technologies are becoming ever more present in electric power infrastructures. One of the most important aspects of having a smart grid is to be able to detect loads, and use this detection information for automation. This research paper focuses on a non-intrusive load monitoring (NILM) algorithm that was developed as part of a senior design project and then carried over into a summer research project. The goal of this research is two-fold; to produce a working load detection algorithm for purely resistive, inductive, or capacitive loads; and to use this experience as the basis for creating a new laboratory assignment for undergraduate students. The NILM algorithm was developed in MATLAB and tested with both simulated data and real data collected in the institution’s power lab. Current transformers were used to read the three-phase voltage and current waveforms. Real data was collected and used to train the machine learning algorithm and confirm its ability to successfully identify purely resistive, inductive, and capacitive loads. While research shows much more advanced algorithms in development, the purpose of this project was to act as a proof-of-concept for prototyping a NILM algorithm in MATLAB that can be recreated by students in a classroom setting. As a lab assignment, this project combines knowledge of power systems, signal processing, and coding –providing students with a relevant assignment that relates to modern day challenges in smart grid and smart home technology. This paper describes the motivation for the project, the technical background, the procedure for experimentation and development, results, a plan for the future laboratory assignment and its assessment, and a conclusion of the work.

Kerestes, R. J., & Stokes, D., & Brody, R. M., & Emes, A., & Williams, A. (2019, June), Board 70: Development and Implementation of a Non-Intrusive Load Monitoring Algorithm Paper presented at 2019 ASEE Annual Conference & Exposition , Tampa, Florida. 10.18260/1-2--32411

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2019 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015