A review on the young history of the wind power short-term prediction
Introduction
Short-term prediction is a subclass of the wind power time prediction (in opposition to the wind power spatial prediction). The time scales concerning short-term prediction are in the order of some days (for the forecast horizon) and from minutes to hours (for the time-step). Its purpose is the prediction of the wind farm output either directly or indirectly (first, estimating the wind and, after, converting it into power). Short-term prediction is mainly oriented to the spot (daily and intraday) market, system management and scheduling of some maintenance tasks, being of interest to system operators, electricity companies and wind farm promoters.
This paper makes a review on the 30 decades of history of the wind power short-term prediction, an extremely important field of research not only for the wind energy sector, but also for the energy sector in general (as the system operators must handle an important amount of fluctuating power from the increasing installed wind power capacity). The review tries to give a clear idea on the chronology and evolvement of the short-term prediction.
Practically, since the beginnings, the short-term prediction has awakened expectation in the electricity sector and its evolution has been fomented by competing commercial interests. As a consequence of this pressing emergent claim about the short-term prediction, the major part of the relevant developments has been published in ‘high-speed vehicles’ for the communication: the proceedings of expert meetings and conferences.
The comparison of the performance of the prediction models is not evident, mainly because, on the one hand, a standard for a measure of performance is still not adopted and, on the other hand, it is very important that the data are exactly the same in order to compare two models (this fact makes it almost impossible to carry out a quantitative comparison between a huge number of models and methods). Regarding the former question, model performance is assessed in a variety of ways: mean error (ME), mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), improvement over persistence, correlation with real data, etc. For this reason, this review has not the intent of dealing with quantitative descriptions. On the contrary, its purpose is pointing out some of the most representative models and tools developed since the beginnings of the young history of the wind power short-term prediction, while focusing on the main characteristics of the models and tools described in the second section of this paper.
Based on the review, some points for future research are suggested in the third section of this paper.
Section snippets
Before the 1990s
One of the first attempts to clarify the importance and advantages of the short-term prediction to the electricity companies was carried out at the ends of the 1970s, by a discussion group at the Pacific Northwest Laboratory [1], whose conclusions indicated that sufficiently reliable forecasts could have the following applications (cf. [2]):
- •
weekly forecasts of day-to-day winds for use in maintenance scheduling;
- •
daily forecasts of hourly wind levels to be factored into the load scheduling
Conclusions
This review tries to give a clear idea on the chronology and evolvement of the short-term prediction. Some lessons can be learned from this review. From these lessons, some topics (unsolved, poorly exploited or, even, unexploited yet) are clearly identified as an urgent need for the feasibility of operational (on-line) tools, such as, for instance:
- •
adoption of a standard for measurement of performance of models;
- •
improvement of the accuracy of existing models and tools;
- •
methods which are able to
Acknowledgements
This review was performed during the initial stage of the IN-VENTO Project (CGL2005-06966-C07/CLI), partially funded by the Spanish Ministry of Education and Science.
References (88)
A comparison of various forecasting techniques applied to mean hourly wind speed time series
Renewable Energy
(2000)- et al.
Short-term prediction of the aggregated power output of wind farms—a statistical analysis of the reduction of the prediction error by spatial smoothing effects
J Wind Eng Ind Aerodyn
(2002) - et al.
Forecast of hourly average wind speed with ARMA models in Navarre (Spain)
Sol Energy
(2005) - Wendell L, Wegley H, Verholek M. Report from a working group meeting on wind forecasts for WECS operation. PNL-2513,...
- Bailey B, Stewart R. Wind forecasting for wind power stations. In: Galt J, editor. Proceedings of wind energy...
- Notis C, Trettel D, Aquino J, Piazza T, Taylor L, Trask D, et al. Learning to forecast wind at remote sites for wind...
- Wegley H, Formica W. Test applications of a semi-objective approach to wind forecasting for wind energy applications....
- Wegley H, Kosorok M, Formica W. Subhourly wind forecasting techniques for wind turbine operations. PNL-4894, Pacific...
- Geerts H. Short range prediction of windspeeds: a system-theoretic approach. In: Palz W, editor. Proceedings of...
Short-term prediction—overview and taxonomy
Time series models of average wind speed within synoptic weather categories
Short-term wind prediction using Kalman filters
Wind Eng
Short-term stochastic wind prediction and possible control applications
Models and methods for predicting wind power
A new reference for wind power forecasting
Wind Energy
Short term wind forecasting
Sipreólico—a wind power prediction system based on flexible combination of dynamical models. Application to the Spanish power system
Developing and testing of wind power forecasting techniques for Canada
Experiences with wind forecasting techniques in Norway
Probabilistic wind power forecasts by means of statistical model
Wind energy forecasting in the Pacific Northwestern U.S.
Cited by (575)
A new distributed decomposition–reconstruction–ensemble learning paradigm for short-term wind power prediction
2023, Journal of Cleaner ProductionA fuzzy-based cascade ensemble model for improving extreme wind speeds prediction
2023, Journal of Wind Engineering and Industrial Aerodynamics