LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Artificial Neural Network for Non-Intrusive Electrical Energy Monitoring System

Photo by mbrunacr from unsplash

This paper discusses non-intrusive electrical energy monitoring (NIEM) system in an effort to minimize electrical energy wastages. To realize the system, an energy meter is used to measure the electrical… Click to show full abstract

This paper discusses non-intrusive electrical energy monitoring (NIEM) system in an effort to minimize electrical energy wastages. To realize the system, an energy meter is used to measure the electrical consumption by electrical appliances. The obtained data were analyzed using a method called multilayer perceptron (MLP) technique of artificial neural network (ANN). The event detection was implemented to identify the type of loads and the power consumption of the load which were identified as fan and lamp. The switching ON and OFF output events of the loads were inputted to MLP in order to test the capability of MLP in classifying the type of loads. The data were divided to 70% for training, 15% for testing, and 15% for validation. The output of the MLP is either ‘1’ for fan or ‘0’ for lamp. In conclusion, MLP with five hidden neurons results obtained the lowest average training time with 2.699 seconds, a small number of epochs with 62 iterations, a min square error of 7.3872×10-5, and a high regression coefficient of 0.99050.

Keywords: intrusive electrical; system; energy; energy monitoring; non intrusive; electrical energy

Journal Title: Indonesian Journal of Electrical Engineering and Computer Science
Year Published: 2017

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.