基于相似日和风速连续性的风电场短期功率预测

Short-term Wind Power Prediction Based on Similar Days and Wind Speed Continuity

对风电场进行短期功率预测能够有效减小风电场出力波动对电力系统的影响,降低电力系统的运行成本和旋转备用。综合考虑天气因素以及风速连续性的影响,提出基于相似日和风电连续性的风电场短期功率预测方法。首先,完成BP神经网络训练样本的选择,然后利用预测日前一天的风速作为输入,完成预测日功率的预测,最后将此模型运用于威海某风电场,并与仅考虑风速连续性得到的预测结果相比较,分析预测误差,结果表明前者预测精度更高。

Short-term wind power prediction is an effective approach for reducing both negative effects of wind power fluctuation on the power system and the operating cost and spinning reserve of power system. Taking weather factor and the continuity of the wind together as a whole, a short-term wind power forecasting method is proposed based on similar days and wind speed continuity. First of all, the training sample is selected for the BP neural network. Then the wind speed data of the prediction-day before are taken as input, and the wind power prediction is finished. At last, the proposed model is used in a wind farm located in Weihai. Analysis results show that this method possesses high accuracy.