Repozytorium publikacji - Politechnika Gdańska

Forecasting a specific wind farm's generation capacity within a 24 hour perpective requires both a reliable forecast of wind, as well as supporting tools. This tool is a dedicated model of wind farm power. This model should include not only general rules of wind to mechanical energy conversion, but also the farm's specific features. This paper present analytical, statistical, and neuron models of wind farm power. The study is based on data from a real wind farm. Most attention is paid to the neuron models, due to a neuron network's capacity to restore farm-specific details. The research aim to answer the headline question: whether and to what extent a wind farm's power can be forecast short-term.

Autorzy

• dr hab. inż. Elżbieta Bogalecka link otwiera się w nowej karcie ,
• mgr Tomasz Rubanowicz