基于局域一阶加权法的风电功率超短期预测研究

摘要

准确的风电功率实时预测，对电力系统安全、经济高效运行有着重要作用。基于相空间重构理论，提出了一种局域一阶加权法，以马式距离作为邻近相点的判据，权值的选择以邻近相点和参考相点的距离为依据，构建预测模型。以东北某风电场的实测风电功率时间序列为例，进行仿真分析，结果表明模型可有效地提高预测精度。%The accurate wind power forecasting is important to the safe and efficient operation of electrical power system. Base on the phase space reconstruction theory, the weighted-one rank local region method is presented. In the method,the Mahalanobis distance is taken as the criterion for determining the adjacent phase points,and it is also determines the weight of points. Taking the wind power time series of a wind farm in Northeast China as an example,the simulation analysis shows that the model is effective.