Wind Power Forecasting Algorithms and Application

Abstract

The importance of forecasting wind power has grown in parallel with the increase in penetration of wind power generation on power systems. It can be loosely said, for the short term, that the uncertainty in wind power prediction is higher than in load forecasting. This very fact has strong implications for the security and costs associated with decision making in systems with high penetration of wind power. Furthermore, an accurate representation of forecasting uncertainty also has an important function in controlling the trade-off between risk and return when wind energy participates in the electricity market. First, a brief introduction to the wind power forecasting problem is presented, followed by results of the application of neural network training criteria based on information theoretic learning (entropy and correntropy) for producing point forecasts. Since the information provided by single point forecasts may not be enough for some decision-making problems, a kernel density forecast method based on quantile-copula is also presented for producing probabilistic forecasts. Finally, a practical example that uses wind power probabilistic forecasts is presented. Further reading: C. Monteiro, R.J. Bessa, V. Miranda, A. Botterud, J. Wang, G. Conzelmann, “Wind power forecasting: state-of-the-art 2009,” Report ANL/DIS-10-1, Argonne National Laboratory, 2009, pag. 216. (http://www.dis.anl.gov/pubs/65613.pdf) R.J. Bessa, V. Miranda, J. Gama, “Entropy and correntropy against minimum square error in offline and online three-day ahead wind power forecasting,” IEEE Transactions on Power Systems, vol. 24, no. 4, pp. 1657-1666, 2009. (http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5238550&tag=1) R.J. Bessa, V. Miranda, A. Botterud, J. Wang, “‘Good’ or ‘bad’ wind power forecasts: a relative concept,” Wind Energy, vol. 14, no.5, pp. 625-636, Jul. 2011. (http://onlinelibrary.wiley.com/doi/10.1002/we.444/pdf) R.J. Bessa, V. Miranda, A. Botterud, J. Wang, Z. Zhou, “Time-adaptive quantile-copula for wind power probabilistic forecasting,” Renewable Energy, In Press, 2011. (http://www.sciencedirect.com/science/article/pii/S0960148111004587) M.A. Matos and R.J. Bessa, “Setting the operating reserve using probabilistic wind power forecasts,” IEEE Transactions on Power Systems, vol. 26, no. 2, pp. 594-603, May 2011. (http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5565529)