Fisher判别分类法在光伏并网系统稳态电能质量评估中的应用

Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system

针对稳态电能质量综合评估的复杂性以及单项指标在反映电能质量综合水平的局限性,首次提出将Fisher判别分类法用于并网光伏稳态电能质量的评估,进而确定光伏并网可行性。根据已知的电能质量国家标准,通过构造样本来得到判别模型,然后利用回代估计法对模型进行检验,并对实际系统进行判别分析。实验结果表明所提方法所得误判率小,具有较强的判别能力。

Aiming at the complexity of steady-state power quality evaluation and the limitation of single comprehensive power quality index,Fisher discriminant analysis is proposed to evaluate the steady-state power quality of grid-connected photovoltaic system for checking its grid-connection feasibility. A discriminant model is established based on the samples constructed according to China＇s national standard of power quality,which is checked by the back-substitution estimation method and applied to a practical system.Experimental result shows that,the proposed method has small misjudgment rate and excellent discriminating performance.