Massive data acquisition for the short term wind power forecasting in a large grid: The hydro-Québec SAGIPE system experience

The province of Quebec in Canada has begun a decisive move towards wind energy with a series of wind farm projects totaling 4,000 MW in capacity. This paper describes the SAGIPE system that gathers in real time, through multiple data links, a very large volume of wind generation and weather data. It then uses this data to produce, using external forecasting engines, the short term wind generation forecast for most of the wind farms in the province. It also includes a massive data bank for statistical analyses that permits running fruitful studies on the characteristics of wind generation models.