A review on the young history of the wind power short-term prediction

Abstract

This paper makes a brief review on 30 years of history of the wind power short-term prediction, since the first ideas and sketches on the theme to the actual state of the art on models and tools, giving emphasis to the most significant proposals and developments. The two principal lines of thought on short-term prediction (mathematical and physical) are indistinctly treated here and comparisons between models and tools are avoided, 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). In place of a quantitative description, a qualitative approach is preferred for this review, remarking the contribution (and innovative aspect) of each model. On the basis of the review, some topics for future research are pointed out.

Use of wind power forecasting in operational decisions.

“…5 Wind power producers may therefore benefit from using wind power forecasts to bid into the DA market and thereby receive a higher and less volatile price. 6 It is important to integrate the information in wind power forecasts into the DA market clearing. Wind power will have an increasing impact on the marginal cost of electricity, and this should be properly reflected in the DA market clearing, where most of the energy is settled.…”

“…The demand for more accurate, short-term WPF models has led to solid and impressive development in recent years [4] [6]. Increasing the value of wind generation by improving WPF systems' performance -and furthering its integration into operational management -is one of the priorities in current research [7].…”

Reliability diagrams for non‐parametric density forecasts of continuous variables: Accounting for serial correlation

“…If considering lead times from few minutes up to 2 h ahead, forecasts are then generated from purely statistical methods relying on local measurements only, as for instance in Gneiting, et al (2006) and Pinson and Madsen (2009b). For an overview of motivations, techniques and practical experience with wind-power forecasting, the reader is referred to Giebel, et al (2003) and Costa, et al (2008). Among the various types of forecasting products employed for wind-energy management, maintenance planning and trading, non-parametric density forecasts are becoming more and more popular, since benefits from their use have been demonstrated (Pinson, et al, 2007a;Matos and Bessa, 2009).…”

One day ahead prediction of wind speed class

“…A review of the young history of methods for short term prediction of such a kind of time series was given in [1], while more recent references can be found in [2] and [3]. Unfortunately, literature results seem pointing out that even by using sophisticate modeling techniques, wind speed time series can be predicted with some accuracy only at short time horizon, i.e.…”