基于风速数值预报的两种风电功率预测方法

摘要

Aiming at the wind power forecast,this paper discussed two kinds of methods of using neural network to put numerical wind speed prediction into wind power prediction values according to the measured wind speed data and output power data from November to December 2011 in a northern large-scale wind farm.1)Dynamic correction of delay errors from velocity numerical forecast was made by using neural network to revise wind speed.So the wind power was predicted by the revised wind speed.2)The interpretation method is to establish the neural network model by using the relationship between numerical forecast wind speed and wind power output.The wind power prediction of the 0-4 h test was carried out according to the measured data and BJ-RUC model output data.Results showed that two above methods make the error indicators of predicting wind power improve obviously.In the first method,mean absolute error of wind speed decreased by 48.7% and mean absolute error of wind power down 58.2%.In the second method,the mean absolute error of wind power reduced of 60.4%.%针对风电场风功率预测,根据2011年11-12月的北方某大型风电场132台风机的实测风速资料与输出功率资料,以及BJ-RUC数值预报模式在该风电场风机高度(50 m)的预报风速资料,探讨了2种利用神经网络将风速数值预报转化为风功率预测值的途径:1)利用神经网络对风速数值预报进行预测后延误差动态订正,以订正后的风速预测风功率;2)用风速的数值预报值直接与风功率输出建立神经网络模型的释用方法.根据该风电场的实测资料和BJ-RUC模式输出资料,对0-4 h的风功率预报进行了试验,结果表明2种方法相较直接使用BJ-RUC模式风速得到的风功率预报效果有明显改进,第1种方法,风速的绝对误差下降了48.7%,风功率的平均绝对误差下降了58.2%,第2种方法,风功率的平均绝对误差下降了60.4%.