Energy forecasting for the Global Energy Forecasting Competition

Energy forecasting is a key problem in the energy industry, as different types of forecasts are needed, such as demand, generation, price and so on. The Global Energy Forecasting Competition (GEFCom) is one of the largest energy forecasting competition known. For this project, you will build a forecasting model for one of the tracks of GEFCom2014 (demand, price, wind and solar). You will have the freedom to chose the technique you find more suitable or comfortable with, such as regressions, ARMA models, machine learning etc. And if your model is good, there’s the possibility of winning a nice price.

NOTE: this project is already assigned.

If you have any question, just drop us an email, or come to our office:

• Matteo Vasirani (BC114): [email protected]
• Tri Kurniawan Wijaya (BC147): [email protected]

Prerequisites

• Autonomous and with a strong interest for data exploration
• Familiar with (or at least having desire to learn) time-series analysis and/or machine learning techniques
• Programming skills in at least one well-known language such as Python, Java, R, or Matlab