Machine Learning Techniques for Short-Term Electric Load Forecasting

Once produced, electricity is difficult to store in large quantities. Hence, accurate electric load forecasting is of critical importance to balance production and consumption for modern power grids integrating more and more intermittent renewable energy and variable loads such as electric vehicles. Short-term electric load forecasting for local areas is also of interest to efficiently respond to demand at the distribution level. Any significant forecasting error can result in reliability issues, loss of opportunity, or additional costs to the business, while improvements in forecasting performance could benefit both the consumers and utility companies by optimizing resources and costs. Most of the current short-term load forecasting algorithms assume that the load consumption and energy generation patterns are stationary, which is not the case in real world. In this project, we plan to use recent progress in machine learning to improve the performance and robustness of short-term electric load forecasting.

Faculty Supervisor:

Benoit Boulet;Di Wu

Student:

Partner:

Hydro-Quebec

Discipline:

Engineering

Sector:

Professional, scientific and technical services; Utilities

University:

McGill University

Program: