基于实测数据的集中式多谐波源责任评估

Quantifying Harmonic Impacts for Concentrated Multiple Harmonic Sources Using Actual Data

多谐波源的责任量化研究,对于谐波"奖惩性方案"的有效实施具有重要意义。针对如何区分多条馈线所接谐波源负荷对公共耦合点处谐波电压的贡献大小(集中式多谐波源)问题,提出基于实测数据并利用M估计方法和偏最小二乘回归方法进行评估的新思路。各次谐波频率下,基于戴维南等值电路建立集中式多谐波源系统的等效数学模型。根据谐波各量之间的关系,提出"理论电流"和"实际电流"的概念,分析了二者之间的关联规律。进而给出用于评价公共耦合点各谐波源责任的指标,并利用上述两种电流分别进行了基于M估计稳健回归和偏最小二乘回归的谐波责任评估。文中对比了两种方法的评估精度,研究表明,偏最小二乘回归方法性能优异,更适合在工程实践中推广应用。

Quantifying the harmonic impacts of multiple harmonic sources is of great significance for the effective implementation of harmonic ＂rewards and punishment scheme＂. Based on the measured data, this paper proposed a new way to estimate the harmonic contributions of multiple harmonic feeders on the harmonic voltage of the point of common coupling （PCC） by using the M-estimation method and the partial least square regression method. Under harmonic frequencies, the mathematical model for the concentrated multiple harmonic sources system was constructed based on the Thevenin equivalent circuit. According to the relationships among all harmonic phasors, the ＂theory current＂ and ＂actual current＂ concepts were proposed, and their relationship was deeply analyzed. Furthermore, the harmonic impact index to estimate harmonic contribution of each harmonic feeder was proposed. Utilizing the above two currents, the harmonic impact was estimated based on M-estimation regression and partial least square regression method. The paper also analyzed the accuracy of M-estimation method and partial least square regression method. Results show that partial least square regression method has better performance, which is more suitable for practical application.