Pittsburgh, PA
Explore how machine learning is reshaping the energy management landscape and develop strategies to leverage this technology at your agency. This workshop introduces fundamental machine learning concepts and their application in energy management, presents results of real-world applications, and then guides participants through interactive exercises to determine potential applications at their facilities. The session will also cover special considerations for procuring machine learning applications and any constraints for federal facilities. Attendees will leave the workshop with a high-level roadmap for determining where and when to leverage the power of "thinking" machines in their energy management programs.
Instructors
Mark Chung, Chief Executive Officer, Verdigris Read Bio
Mark Chung is the CEO and co-founder of Verdigris, a Silicon Valley firm advancing AI in energy efficiency for enterprises. Verdigris provides real-time, precise electrical intelligence to enhance mission critical facility reliability, reduce CO2 emissions, and ensure compliance. Before Verdigris, Mark developed significant chips like Opteron, A7, XLP at companies including Nexgen (AMD) and Pasemi (Apple), and Netlogic (Broadcom) A recognized climate tech leader, he serves on the American Council for Energy Efficient Economy's board, mentors at Stanford-StartX, and is a Yope Foundation fellow. He also advises Silicon Valley startups, highlighted by his "40 under 40" recognition from Silicon Valley Business Journal in 2017. Mark's engineering foundation was built at Stanford University, earning both Bachelors and Masters degrees, driving his passion for sustainable technology.
Mario Bergés, Professor, Civil and Environmental Engineering, Carnegie Mellon University Read Bio
Mario Bergés is a professor in Carnegie Mellon University's (CMU) Department of Civil and Environmental Engineering. He is interested in making our built environment more operationally efficient and robust through information and communication technologies to better deal with future resource constraints and a changing environment. Currently his work focuses on developing approximate inference techniques to extract useful information from sensor data coming from civil infrastructure systems, with a focus on buildings and energy efficiency. Bergés is faculty co-director of the Smart Infrastructure Institute at CMU and director of the Intelligent Infrastructure Research Lab. He received the Professor of the Year Award by the ASCE Pittsburgh Chapter in 2018, Outstanding Early Career Researcher award from FIATECH in 2010, and the Dean's Early Career Fellowship from CMU in 2015. Bergés received his B.Sc. from the Instituto Tecnológico de Santo Domingo and his M.Sc. and Ph.D. in Civil and Environmental Engineering from CMU.
Charles Liles, Geographic Information System Lead, NASA Langley Research Center Read Bio
Charles Liles focuses on the development of operational technology (OT) and IT system to build data-enabled, smart infrastructure at NASA. He currently also serves as the Geographic Information System Lead at Langley Research Center. He has supported projects for the application of artificial intelligence and machine learning tools across scientific, engineering, and business process fields. Charles's BS is in History with a minor in French (United States Naval Academy), and his MS is in Computer Science (Old Dominion University). He served 11 years on active duty as a Naval Aviator and has served at NASA since 2013.
Learning Objectives
Upon completion of this course, attendees will be able to:
- Identify the basic principles of big data and big data analytics;
- Select basic principles of machine learning;
- Identify what types of energy/facilities management applications have machine learning capability;
- Identify and articulate the value proposition for leveraging machine learning in energy management;
- Identify a high-level playbook/road map for determining where and when to leverage the power of machine learning in their energy management programs.
