Nonintrusive load monitoring system based on the Wavelet transform

• Main Authors: Yi-Ching Su, 蘇易清
• Other Authors: Kuo-Lung Lian
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/66753655934641758540

碩士 === 國立臺灣科技大學 === 電機工程系 === 100 === Nonintrusive load monitoring systems (NILMs) can determine the operating intervals and power consumptions of electrical loads in a system from measurements made at a centralized location, such as the power service entrance. In contrast to the conventional monitoring system, NILMs reduces sensor costs by installing sensors only at the power service entrance point. The power signature for each load is then extracted from these measurements. In this thesis, the multiresolution-analysis technique of Discrete Wavelet Transform (DWT) is employed to extract the Power Intensity (PI) from the raw current signal measured from the power service entrance point. Compared to the traditional power signatures such as real power, reactive power, and ture-on transient energy, the PI exhibits strong uniqueness. In fact, as shown in the thesis, the loads can be easily identified by means of the inner product or neural network.