基于能量函数模型的风电功率在线预测方法研究

Research on Wind Power Online Forecasting Method Based on Energy Function Model

提出一种异于传统智能算法的风电功率在线预测方法。通过构造内外力作用和能量函数,将风电功率预测问题转化为无约束优化问题,使得快速、实时、同步功率预测变为可能。在内外力协同作用下,预测朝着承载物理轮廓、匹配波动特征的方向收敛。随着预测进行,同步修正能量函数的权值,进一步提升预测精度。该方法操作简便、运算速度快,克服了传统算法易出现的过拟合、边缘预测误差大、训练时间长的问题。在可再生能源日益发展的形势下,该方法凸显出在风电系统在线、实时、同步功率预测中应用的可行性与重要性。

An online wind power prediction method is proposed,which is different from the traditional intelligence algorithm.By constructing the internal and external force functions and the energy function,the wind power prediction problem is transformed into an unconstrained optimization problem,which makes the quick,realistic and synchronouswind power prediction possible.Under the action of internal and external forces,the prediction converges towards the direction of carrying the physical contour and matching the fluctuation characteristics.With the prediction progress,the weight of the energy function is synchronously corrected,which guarantees the prediction accuracy.The method is simple and fast in operation,which overcomes such problems as being easy over fitting of the traditional algorithm,large edge prediction error,and the long-time training.Under the situation of increasing development of renewable energy,the feasibility and importance of this method applied in real-time and synchronous forecasting of wind power in systems are highlighted.