Real-Time Appliances Recognition for Non-Intrusive Load Monitoring Using Convolutional Neural Networks
Keywords:
Convolutional Neural Networks (CNN), Current Sensor (CT), Envelope Signal, Non-intrusive Load Monitoring (NILM), Power Factor (PF), Root Mean Square (RMS), Spectrogram,Abstract
Up to now, the details of the load-level power consumption are generally not available to the customers who wish to get more information about their power usage. This paper shows the result of using Convolutional Neural Networks (CNN) to recognize the type of any electrical appliance while operating as well as its power consumption. This approach allows the monitoring on a loads power consumption on every electrical appliance individually. By applying an envelope function to the signal, the appliance can be recognized successfully even it only consumes a small amount of energy during its operation. The performance was evaluated on three electrical appliances at different power consumption level.Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Journal of Telecommunication, Electronic and Computer Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)