APP下载

基于支持向量回归机的电能质量评估

2017-01-12吴正玲张楠楠

现代电子技术 2016年23期

吴正玲++张楠楠

摘 要: 针对传统方法和神经网络方法在电能质量评估方面存在的不足,提出了一种新的基于支持向量回归机的电能质量评估方法。依据电能质量标准和有关文献建立了电能质量评估指标体系,给出了电能质量评估指标的等级区间。基于支持向量回归机的原理和电能质量评估指标,建立了基于支持向量回归机的电能质量评估模型。应用实例的仿真结果表明,所建立的评估模型具有较强的推广能力,得出的评估结果与其他评估方法相比更为合理可信。

关键词: 电能质量; 评估模型; 支持向量机; 支持向量回归机

中图分类号: TN915.853?34; TM714 文献标识码: A 文章编号: 1004?373X(2016)23?0148?04

Electric power quality assessment based on support vector regression

WU Zhengling1, ZHANG Nannan2

(1. Jilin Institute of Chemical Technology, Jilin 132022, China;

2. The Forty?seventh Division of the Army Reserve of the People′s Liberation Army, Jilin 132013, China)

Abstract: The traditional method and neural network method have the shortcomings in the aspect of electric power quality evaluation, a new electric power quality evaluation method based on support vector regression is proposed. The electric power quality evaluation indicator system was established according to the electric power quality standards and relevant literatures. The grade interval of the electric power quality evaluation indicator is given. On the basis of the principle of support vector regression and electric power quality evaluation indicator, the electric power quality evaluation model based on support vector regression was established. The simulation results of the application examples show that the established evaluation model has strong generalization ability, and the obtained evaluation result is more reasonable and reliable than that of other evaluation methods.

Keywords: electric power quality; assessment model; support vector machine; support vector regression

0 引 言

近年来随着电力工业和电力电子技术的迅猛发展,电力用户采用了大量时变控制的非线性设备,电网中接入了大量的冲击、非线性负载及不平衡负荷,引起了日益严峻的电能质量问题。同时,智能电网建设及新能源的发展又对电能质量提出了更高的要求。对电能质量进行科学地评估是提升电能使用效率、电能商品按质计价和电能质量治理等的重要保障,已成为电能质量研究中的热点问题。电能质量评估属于多指标非线性评估问题,在评估过程中指标权重确定的是否科学合理直接影响到评估结果的合理性和有效性,文献[1?7]分别采用改进雷达图法、模糊集对分析法、模糊层次分析法、灰色关联度和理想解法相结合的方法、区间数理论、云物元分析理论和可拓云理论对电能质量评估问题进行了深入研究。……

登录APP查看全文