Come meet the poster presenters to ask them questions and discuss their work
Check the programme for our poster viewing moments. For more details on each poster, click on the poster titles to read the abstract.
PO191: Short-term prediction of wind power production using different machine learning models
Minh-Thang DO, Head of Energy Division, Meteodyn
Wind power is a sustainable, renewable energy source with a small impact on the environment. However, fluctuations of wind farm power output resulting from intermittent winds in the atmosphere remains a challenge to the integration of wind energy into power systems. As the share of wind energy grows globally, the question of reliability of wind power generation needs to be better addressed. Power forecasting based on machine learning methods is a technique to predict power output of a wind farm related to different horizons from several days to several hours ahead. The forecast is useful for wind farm operators to estimate energy yield and detect underperforming of wind turbines. In this study, we examine the performance of machine learning models based on neural networks on predicting the short-term wind power output of a wind farm. We define the forecasting task as a single-step, two-hour ahead forecast using available input data during the time lag.
Follow the event on: