MSL Leads Advanced Grid Tech Seminar with NMSU

On May 19, 2023 MSL organized and led a seminar on advanced grid modernization technologies as part of a grant awarded to New Mexico State University by the U.S. Department of Energy’s Established Program to Stimulate Competitive Research (EPSCoR) program. MSL and The National Renewable Energy Laboratory are collaborators on the grant. Seminar presenters included the NMSU research team; researchers from Los Alamos, Sandia, and the National Renewable Energy Laboratories; and Camus Energy (all MSL consortium Members).

The day-long event began with a site visit to the Mesa del Sol research microgrid operated by the University of New Mexico (also an MSL Member), led by UNM Assistant Professor Ali Bidram. Following this tour and discussion, the seminar kicked off with NMSU Computer Science faculty and students, led by Professor Jay Misra, describing their research into “Building a federated learning framework for trustworthy and resilient energy internet of things (eIoT) infrastructure,” which focuses on Federated Machine Learning (FML) and will approach several FML-related aspects of smart grid data architectures and applications. In addition to Dr. Misra, NMSU faculty included Dr.’s Tao Wang, Roopa Vishwanathan, and Joshua Reynolds.

This was followed by the NREL grant collaborators, led by Richard Macwan, describing the facilities and resources that Lab is contributing to the research project, and additional expert presentations given by the other participants, as follows:

Richard Macwan, The National Renewable Energy Laboratory, presented on NREL’s Advanced Research on Integrated Energy Systems (ARIES) platform, which will support the NMSU research. He is a senior researcher with the Energy Security and Resilience Center at NREL.

Vivek Kumar Singh, PhD, The National Renewable Energy Laboratory, presented on “Federated Machine Learning-based Anomaly Detection Approach for Energy Systems.” He is a senior researcher for the Cybersecurity Evaluation and Application Group within NREL’s Energy Security and Resilience Center.

Juan Jose Ospina Casa, PhD, Los Alamos National Laboratory, presented on “Modeling and Co-optimizing Integrated Transmission-Distribution Systems.” He is currently a Post-Doctoral Researcher with the A-1 Information Systems and Modeling Group at LANL.

Summer Ferreira, PhD, Sandia National Laboratories, presented on “Resilient Microgrids to Meet Human Needs.” She is the Manager for the Renewable and Distributed Systems Integration program at Sandia, which promotes the research and development of technologies that enable grid modernization and resiliency.

Chin-Yao Chang, PhD and Xinyang Zhou, PhD, National Renewable Energy Laboratory, presented on “Autonomous Energy Systems and Algorithm Development.” Chin-Yao Chang is a researcher at NREL focused mainly on control and optimization with applications to power systems and microgrids. Xinyang Zhou’s research aims to design distributed optimization and control algorithms for networked systems.

Birk Jones, Camus Energy, presented on “Machine Learning Informed Controls to Manage Distribution Grid Networks.” He is Director, Customer Solutions at Camus Energy, a grid orchestration software company, and an expert in Distributed Energy Resource and Electric Vehicle grid integration analytics.

The seminar objective, which all participants felt had been well met, was to familiarize the NMSU research team with advanced developments in grid technology that may bear on the “energy internet of things” (eIoT) concept. eIOT is a promising technical aid for the energy-management change drivers, such as rising demand for electricity, the prominence of clean and distributed energy resources (DERs), the emergence of electrified transportation, deregulation of power markets, and innovations in smart grid technology.

The convergence of cyber, physical, and economic frameworks in the energy sector depends primarily on the distributed heterogeneous eIoT devices and their collaborative management. These eIoT devices will increasingly get integrated into the power grid providing unparalleled visibility into energy generation, use, and operations. This proliferation will create a deluge of operational and information technology data, from geographically diverse and heterogeneous sources, necessitating use of data-driven machine learning (ML) applications.

The ML applications will digest the data volume, preferably close to the devices themselves, and help increase grid scalability and efficiency. Given the data volumes, the need for resilience, and user/data privacy needs, federated machine learning (FML) can be used as a foundation to improve not only visibility and optimization, but also security of the eIoT infrastructure.