期刊
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
卷 71, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2022.3181897
关键词
Event detection; Data models; Feature extraction; Forestry; Probabilistic logic; Standards; Sensitivity; Energy consumption; event detection; nonintrusive load monitoring (NILM); time shift downsampling matching (TSDM); voting improved isolated forest (VIIF)
资金
- Key Projects of Science and Technology Plan of Zhejiang Province [2021C01144]
Nonintrusive load monitoring is a technology that identifies users' energy consumption using data measured at a single point. This study proposes an event detection algorithm combining probability and expert heuristic models, which achieves high sensitivity and accuracy.
Nonintrusive load monitoring is a technology that can identify the users' internal energy consumption by using the data measured at a single point on the bus and event detection is a key technical problem that needs to be solved. An algorithm combining probability and expert heuristic models is proposed for event detection in this study, including an event predetection subalgorithm called voting improved isolated forest (VIIF) for high-sensitivity event predetection and an event verification subalgorithm called time shift downsampling matching (TSDM) for high-accuracy event verification. VIIF is used to detect suspicious events quickly from the low-frequency characteristics of the signal; TSDM identifies real events from suspicious events by analyzing high-frequency characteristics of the signal. To evaluate the proposed algorithm, three datasets are used. Compared with the state-of-the-art algorithms, the proposed algorithm has great adaptability and accuracy to long-transient events and small-signal events.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据