基于小波-原子分解的超短期风电出力预测模型

为提高含风电场电网经济调度能力以及降低电力系统规划决策的保守性,提出了基于小波-原子分解(WD-AD)的风电出力超短期预测模型。该模型采用小波分解(WD)作为前置环节,以基于原子表达式的自预测和基于最小二乘支持向量机(LSSVM)的残余分量预测为基础构建原子分解(AD)预测模型,分别对风电出力的高低频分量进行预测,并将结果相加得到最终预测值。AD分解过程由衰减线性和Gabor原子库交替分解完成,可自适应匹配不同类型分量。同时,本文提出将细菌群体趋药性和正交匹配追踪算法相结合(BCC-OMP)优化的原子分解法,进一步增强了原子分解能力。实际风电场算例验证了所提方法的自适应性、快速性及有效性。

Ultra short term wind power output forecast model based on wavelet decomposition and atomic decomposition

In order to improve the economic scheduling ability of the power grid including wind power plant and reduce the conservatism of power system planning and decision making, an ultra short term wind power output forecast model is proposed based on wavelet decomposition and atomic decomposition (WD AD) in this paper. In the model, wavelet decomposition (WD) is used as the pre positive step. The self prediction based on atomic expression and the residual component prediction based on least squares support vector machine (LSSVM) are taken as the foundation to establish the atomic decomposition prediction model. Then, the high and low frequency components of wind power output are predicted. At last, the two results are added together to get the final predicted value. The atomic decomposition process is completed through the alternative decomposition of damped liner library and Gabor atomic library, which can match different types of components adaptively. In addition, in this paper the bacterial colony chemotaxis (BCC) and orthogonal matching pursuit (OMP) algorithm are combined as the BCC OMP optimization algorithm to optimize atomic sparse decomposition, which enhances the atomic decomposition ability further. The proposed method is verified by actual wind power plant example, and simulation results verify the adaptability, rapidity and effectiveness of the proposed method.