• Energy Research

Efficient regional forecasting is a critical task for system operators and utilities that manage the generation of various wind farms spread over a region. This paper proposes an aggregate prediction method based on the search for similarities between the current wind speed predictions in a set of locations, and historical wind speed predictions. The aggregate power prediction is constructed from the measures of aggregate power generated during moments from a historical data set in which the wind speed predictions were similar to the current ones, using smoothing techniques. The methodology is applied to the hourly wind power forecast for the Spanish peninsular system, and compared with the predictions obtained with SIPREOLICO, the wind power prediction tool used by the Spanish system operator, and also with the aggregate predictions provided by another forecasting agency. The proposed methodology shows considerably smaller prediction errors than the competitors.

The participation of wind energy in electricity markets requires providing a forecast for future energy production of a wind generator, whose value will be its scheduled energy. Deviations from this schedule because of prediction errors could imply the payment of imbalance costs. In order to decrease these costs, a joint operation between a wind farm and a hydro-pump plant is proposed; the hydro-pump plant changes its production to compensate wind power prediction errors. In order to optimize this operation, the uncertainty of the wind power forecast is modeled and quantified. This uncertainty is included in an optimization problem that shifts the production of the hydro-pump plant in an optimal way, aiming at reducing the imbalance costs. The result of such a method is profitable for both participants, the wind farm and the hydro-pump plant. A realistic test case is used to evaluate the proposed method.