English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents a method for non-intrusive load monitoring (NILM) identification which is based on transient analysis and steady-state harmonic analysis. Each appliance has its own characteristics which results in a unique magnitude when it is switched on and have unique frequency spectrum in the steady-state. So based upon these analysis, frequency spectrum is used in combination with time domain analysis to identify loads. And the proposed NILM system employs the Particle Swarm Optimization (PSO) Algorithm with the Support Vector Machines (SVM) to perform load classification. The identification results confirm that the proposed system is suitable for identifying different loads. Introduction Home electrical power monitoring plays an important role in reducing energy usage, and nonintrusive appliance load monitoring (NIALM) techniques are the most effective approach for estimating the electrical power consumption of individual appliances. NILM was addressed originally at MIT by Hart [1] in the 1980’s, and has attracted many interests[4,9] in recent years due to the fast development of smart metering technologies. NILM employs a centralized monitoring device installed at the main breaker level, combined with intelligent load identification technologies to break down the operational information and power consumption of each appliance. NILM can be useful for homeowners and building managers to monitor energy consumption on an appliance-byappliance basis without having to install dedicated sensors. The original and extended NILM methods by MIT [1] use low-frequency hardware devices that only provide steady, coarse, and macroscopic signatures such as active and reactive power (P–Q). Recently, most researchers have agreed that the high-frequency hardware installation, which is capable of providing not only the conventional steady signatures but the microscopic transient signatures, can reach high accuracy of appliance detection and identification. Several intelligent algorithms have been proposed for appliance identification by researchers in the past a few years. In [12], the artificial neural network (ANN) was used to identify the appliance by simply teaching the ANN to learn specific features. In [12, 14], the neural network was also used for the electrical appliance identification. The previous works in the literature based on intelligent systems which are based on a large amount of training from operational data. This training effort work will hinder the industrial application of the NILM technologies. There are still no complete available NILM solutions till now such that further research is still needed [2]. In this paper, an NILM system, which combines feature extraction and load identification methods, is proposed and used to identify the operation status of different types of appliances. The features are extracted from the harmonic analysis of identified transient current waveform. And the SVM with optimized parameters based on PSO is used as load identification to perform load identification. This paper is organized as follows. In Sec. 2, the proposed NILM system is introduced. In Sec. 3. the acquisition of required data and the extraction of feature are given. In Sec.4. the PSO-SVM classification model is introduces. In Sec.5, the experimental results and discussion are described. Finally, the conclusions are presented in Sec. 6.

Load Identification of Non-intrusive Load-monitoring System Based on Time-frequency Analysis and PSO-SVM