Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture discusses the development and implementation of Grid Sense, a local control technology aimed at optimizing grid operations by managing peak demand and peak infeed situations. The speaker explains how Grid Sense uses neural networks to learn consumption profiles and identify flexibility in household appliances, ultimately improving voltage quality and reducing the need for costly grid expansions. Through a pilot project evaluation, the lecture demonstrates how Grid Sense outperformed traditional ripple control methods in minimizing under voltage events and avoiding infrastructure investments. The presentation highlights the potential of data-driven local load management in enhancing grid efficiency and cost-effectiveness.