基于数据流的非侵入式负荷识别与分类

Load identification and classification in Non-intrusive load monitoring system based on data stream

为了配合非侵入式系统对于负荷的监测、识别和分类,提高识别功能的可靠性和准确度,提出了新的典型负荷投切检测方法。该方法基于改进滑动双边窗法对于暂态过程的起始和终点确定,运用相关函数法和暂态能量算法。对比运用暂态能量法确定最具区分度的计算结束点,引入基于信息融合理论的判定结果作为判据,确定数据融合误差率阈值进行判定。应用相关函数法进行校验。算例中通过MATLAB仿真验证了该系统对于区分不同负荷投切事件的有效性。

In order to enhance the classification accuracy and reliability of load detection in non-intrusive load monitoring system, novel approaches for general load switch detection were proposed. Based on improved CUSUM algorithm which can determine the start and ending point of transient process, transient energy algorithm and correlation method were applied. Further, the comparison results of different ending points show the different differentiation degree. The information fusion as criterion was added and the data fusion error rate threshold was determined to enhance reliability. After that, correlation method was applied to verify the results. In the case study simulation, the effectiveness of this novel system was proved.