The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 42-415
Full Name: Hsueh-Hsien Chang
Position: Assistant Professor
Age: ON
Sex: Male
Address: No. 99, An-Chung Rd., Taipei County, Hsing-Tien City
Country: TAIWAN
Tel: +886 2 82122000 ext. 6813
Tel prefix:
Fax:
E-mail address: sschang@just.edu.tw
Other E-mails: h.h.johnson.chang@gmail.com,sschang@sparqnet.net
Title of the Paper: load identification using artificial neural networks in a non-intrusive load-monitoring system
Authors as they appear in the Paper: Hsueh-hsien Chang
Email addresses of all the authors: sschang@just.edu.tw,h.h.johnson.chang@gmail.com,sschang@sparqnet.net
Number of paper pages: 12
Abstract: The traditional non-intrusive load-monitoring system (NILM) does not perform the identification for different loads with the same real power and reactive power, and transient power signature analysis. In this study, artificial neural networks (ANN), in combination with turn-on transient energy analysis, are used to identify different loads with the same real power and reactive power, and to improve recognition accuracy and computational speed of NILM results. This paper presents case studies applying methods to compare various training algorithms and classifiers in terms of ANN due to various factors whether or not the network is being used for pattern recognition. The experimental results revealed that the incorporation of transient power signature analysis into a NILM system can enhance the efficiency of load identification, particularly for different loads with the same real power and reactive power, and improve ability of computational speed. In addition, in co!
mbination with electromagnetic transient program (EMTP) simulation, calculations of turn-on transient energy facilitated load identification that had significant effect on NILM results.
Keywords: Load identification, Artificial neural networks, Non-intrusive load monitoring, Turn-on transient energy analysis, Electromagnetic transient program
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 218.211.85.53
