The RELAY project at UiT The Arctic University of Norway is centered on pioneering basic research and applications within energy analytics. It focuses on advancing machine learning for analyzing time series and graphs, specifically through the development of novel tools and methods for processing spatio-temporal data and enhancing deep learning models. The project encompasses four key research areas: randomized architectures, multi-scale representations, uncertainty quantification, and interpretability. Additionally, it aims to apply these advancements to address challenges in energy systems, collaborating with industrial partners in Northern Norway to improve load forecasting, optimize power flow dynamically, and localize outages more effectively.

The project was funded by the Norwegian Research Council and will last 4 years. For more detailed information, please visit the project’s page here.