Loading...
Publication
An optimized probabilistic forecasting approach for hybridized wind power plants
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 377.69 KB | Adobe PDF |
Advisor(s)
Abstract(s)
ABSTRACT: Accurate forecasts are essential for efficiently integrate variable renewable power plants into power systems and electricity markets. Since hybrid power plants are a new area of research, several key challenges need to be addressed. This work presents a probabilistic power forecast approach to hybridised wind power plants with solar power. The forecasting metho dology uses a sequential forward feature selection algorithm, employing distinct objective functions and an artificial neural network approach. The probabilistic power forecasts are obtained using a quantile spline regression technique. The approach supports the identification of the: i) optimal quantile and ii) exogenous features (e.g., meteorological input features from numerical weather prediction – NWP models) to increase the profitability of the hybrid power plants in an electricity market environment. As expected, hybridization increases the remuneration of the producer when compared to existing wind plants, regardless of complementarity levels. This increase in remuneration of hybrid plants is superior for the highest generation complementarity case. The use of quantiles to calibrate the forecast approach proves to be crucial for increasing the remuneration compared to the traditional deterministic approach based on the power forecast expected value.
Description
Keywords
Hybrid renewable power plants Wind power plants Solar power Power forecast
Citation
Couto, A., Algarvio, H. & Estanqueiro, A. (2024) An optimized probabilistic forecasting approach for hybridized wind power plants. In: 8th International Hybrid Power Plants & Systems Workshop (HYB 2024), Azores, Portugal, 14-15 May, 2024, p. 295-301. https://doi.org/10.1049/icp.2024.1852
Publisher
IET