Enhancing Power System Economics, Reliability, and Resilience with AI/ML

Enhancing Power System Economics, Reliability, and Resilience with Artificial Intelligence and Machine Learning
Economics, reliability, and resilience are three key priorities in power system operations and planning. In recent years, artificial intelligence (AI) and machine learning (ML) have been increasingly applied to address these challenges. In this talk, we will present three AI/ML-driven approaches that enhance power system performance.

First, we will explore the unit commitment problem, a fundamental optimization task that schedules energy production and clears electricity markets. We will demonstrate how AI accelerates mixed-integer programming solvers, improving computational efficiency and economic outcomes.

Second, we will examine asset health management, a critical component of grid reliability. We will showcase how AI/ML leverages condition-monitoring sensor data to predict asset remaining useful life, optimizing inspection and maintenance strategies.

Third, we will analyze nationwide electricity outage data and introduce a spatio-temporal ML model that predicts outages based on weather forecasts. This model not only enhances outage preparedness but also provides insights into regional grid vulnerabilities.

These AI/ML applications demonstrate how advanced analytics can transform power system operations, leading to more cost-effective, reliable, and resilient energy infrastructure.

Bio:

Feng Qiu received his Ph.D. from the School of Industrial and Systems Engineering at the Georgia Institute of Technology in 2013. He has a B.S. in Automatic Control and a M.S. in Systems Engineering from Huazhong University of Science and Technology. Prior to his PhD study, he was a software developer in IBM ILOG Solution Center (China). He joined Argonne in 2013 and is currently a principal computational scientist and a section leader with the Energy Systems Division at Argonne National Laboratory. His current research interests include power system modeling and optimization, electricity markets, power grid resilience, machine learning and data analytics. He is PIs for a number of DOE projects over ten million dollars across multiple offices, such as Solar Energy Technology Office, Water Power Technology Office, Office of Electricity, etc.. He is also the Lab Relationship Manager for the Office of Electricity Advanced Grid Modeling program. He also holds joint positions at Iowa State University as Affiliate Associate Professor and at Northwestern University as a NAISE Fellow.

Host or Publisher LSU Institute for Energy Innovation