In this paper, we develop an improved outlier pointwise elimination rule based on the wind-power observation data and prove that when the stopping-parameter is , the abnormal data can be eliminated maximally, where is the confidence level and m is the number of observation data. Then, by integrating the exponential smoothing method with the time series and the Kalman filter, we obtain an improved wind-power short-term forecasting model which has a high accuracy. Finally, a wind-power numerical experiment shows the simulation results and illustrates the effectiveness of our method.
AkaikeH (1974) A new look at the statistical model identification. IEEE Transactions on Automatic Control19(6): 716–723.
2.
CassolaFBurlandoM (2012) Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output. Applied Energy11(99): 154–166.
3.
GrinstedAMooreJCJevrejevaS (2004) Application of the cross wavelet transform and wavelet coherence to geophysical time series. Nonlinear Processes in Geophysics11(5/6): 561–566.
4.
LiuYZhangDWeiW. (2013) Wind power ultra-short-term forecasting method combined with pattern-matching and ARMA-model. 2013 IEEE Grenoble conference PowerTech, POWERTECH, 16 June, 2013. IEEE Computer Society6(20): 1–4.
5.
PanYLiuHLiY (2008) Wind speed forecasting optimization model for wind farms based on time series analysis and Kalman filter algorithm. Power System Technology32(7): 82–86.
6.
QingWYangY (2014) Combined prediction of wind power with chaotic time series analysis. Open Automation and Control Systems Journal6(1): 117–123.
7.
SideratosGHatziargyriouN (2007) Using radial basis neural networks to estimate wind power production. In: Power engineering society general meeting, IEEE.
8.
TaiNHouZLiT. (2003) New principle based on wavelet transform for power system short-term load forecasting. Proceedings of the CSEE23(1): 45–50 (in Chinese).
9.
TongLZhouH (2001) An improved algorithm for the rejection of outlier data. Chinese Space Science and Technology8(4): 11–49.
10.
WangHHeCFangG. (2011) A gradual optimization model of dispatching schedule taking account of wind power prediction error bands. Automation of Electric Power Systems35(22): 131–135.
11.
WangLLiaoZGaoY. (2009) Summarization of modeling and prediction of wind power generation. Power System Protection and Control, 37(13):118-122.
12.
WangZWangB (1997) One by one-method of outliers rejection in linear regression model. Mathematics in Practice and Theory27(3): 266–274.
13.
WenWHaoZYangX. (2010) Robust least squares support vector machine regression based on hypothesis testing and outlier elimination. Pattern Recognition and Artificial Intelligence23(2): 241–249.
14.
XiuCGuoF (2013) Wind speed prediction by chaotic operator network based on Kalman Filter. Science China Technological Sciences5: 1169–1176.
15.
YaoYYuJ (2011) Multi-objective hybrid optimal dispatch of power systems considering reserve risk due to wind power. Automation of Electric Power Systems35(22): 118–124.
16.
YangXXiaoYChenS (2005) Wind speed and generated power forecasting in wind farm. Proceedings of the CSEE25(11): 3.
