基于k-NN结合核Fisher判别的非侵入式负荷监测方法

非侵入式负荷监测是目前智能用电领域一个重要的研究方向,而负荷识别是非侵入式负荷监测的核心内容。以负荷的奇次谐波电流幅值作为特征建立负荷特征库,通过分析负荷样本在特征空间的分布,设计了一种AdaBoost样本筛选算法以精简负荷特征库。利用k近邻(k-NN)算法的简捷性和核Fisher判别算法的非线性分类能力,通过误判风险控制将k-NN与核Fisher判别相结合用于家庭负荷识别,兼顾识别精度和计算复杂度,以提高对负荷特征相近电器的识别能力及整体识别速度。经实测数据检测,结果表明所提方法能够快速准确地实现居民负荷识别。

Non-intrusive Load Monitoring Method Based on k-NN and Kernel Fisher Discriminant

Non-intrusive load monitoring is an important research direction in the field of intelligent power utilization, and the load identification is the core of non-intrusive load monitoring. The load feature library is built based on the load amplitudes of the odd harmonic current. An AdaBoost sample screening algorithm is designed to simplify the load feature library through analyzing the distribution of load samples in the feature space. By using the simplicity of k-nearest neighbor(k-NN)classification algorithm and the nonlinear classification ability of the kernel Fisher discriminant algorithm, a method combined k-NN with kernel Fisher discriminant is proposed for load identification by controlling the risk of misclassification. The identification accuracy and computational complexity are considered in the method aforementioned to improve the identification ability of loads with similar characteristics and the speed of identification. The measured data shows that the proposed method can realize the resident load identification quickly and accurately.