基于PCA-SSA-ELM的非侵入式负荷识别方法

Non-Intrusive Load Identification Method Based on PCA-SSA-ELM

针对目前非侵入式负荷监测方法对电气量特征相近的电器识别准确率不高的问题,提出了一种基于主成分分析法和麻雀搜索算法优化极限学习机的负荷识别方法。该方法在传统的电气量特征基础上,引入了一种融合电器投切时间、电器运行时长、电器运行周期等非电气量的新特征,利用主成分分析法对多维特征进行降维得到综合变量,然后使用麻雀搜索算法对极限学习机的权值和偏置进行优化,建立负荷识别模型。最后采用AMPds数据集对算法进行测试,通过对比分析验证该方法具有良好的辨识效果。

In view of the low accuracy of current non-intrusive load monitoring methods in identifying electrical appliances with similar electrical characteristics,a load identification method based on extreme learning machine optimized by principal component analysis and sparrow search algorithm is proposed.On the basis of traditional electrical signatures,new features which combine non-electrical quantities such as load switching time,the length of operation time and working period are also adopted.The principal component analysis method is used to reduce the dimension of multidimensional features,and the comprehensive variables are obtained after processing.Then the sparrow search algorithm is used to optimize the weight and bias of the extreme learning machine,and the load identification model is established.Finally,the algorithm is tested on AMPds data set,the comparative analysis verifies that the method has good identification effect.