Dr. Ezzat will present his research group’s efforts to develop data-driven methods for forecasting electricity market signals and to further leverage them in informing wind energy operations. He will begin with a multivariate statistical approach for electricity price forecasting designed to capture the operational, economic, and temporal dependencies inherent in electricity price signals. The proposed approach is evaluated using two years of electricity price data from the California Independent System Operator, demonstrating significant improvements in both point and probabilistic forecast metrics relative to well-established statistical methods and emerging deep learning approaches. Independent validation against industry-adopted forecasting systems further demonstrates the method’s competitive performance and practical relevance. He will then turn to how variability in market signals, which is typically viewed as a challenge for power producers, can instead be transformed into an opportunity for improved decision-making. In particular, he will explore how grid-level information, such as electricity prices and curtailment, can create new operational opportunities for condition-based maintenance of wind turbine fleets. Taken together, these results highlight how market signals can be both accurately predicted and effectively utilized for wind energy operations, thereby bridging forecasting and optimization in renewable energy systems. Co-sponsored by: Wayne State University Room: Conference Room, Bldg: Manufacturing Engineering Building, Wayne State University Industry and Systems Engineering, 4815 4th Street, Detroit, Michigan, United States, 48202, Virtual: https://events.vtools.ieee.org/m/554374