LF Energy Summit 2024

Load forecasting is an essential activity for a company like Hydro-Québec. It can be used to assist in efficient energy generation scheduling, real-time energy dispatching, or grid infrastructure maintenance. Any significant load forecasting error can result in reliability issues, loss of opportunity, or additional costs to the business. In recent years, with the wide deployment of smart meters, applying advanced machine learning methods for power grids has become applicable. On the other hand, with the wide deployment of different kinds of electrical appliances and renewable energy generation and the changes induced by the energy transition, more and more challenges have also been introduced in power grids. This presentation will show how Hydro-Quebec leverage machine learning approaches and open AI framework to tackle these challenges and fully automated the short-term load forecasting on the grid.