Abstract

This paper proposed new method for online energy monitoring system (OEMS). This method combines Non-Intrusive Load Model (NILM) and Time Series Lag-1 for signal conditioning process. and Neural Network (NN) for decision making process. The advantage of the method is easy to identify energy cosumption of appliance with small number of training data and only need single current sensor for identification of energy consumption of appliances. Signals from current sensors are processed by microprocessor to represent activities of appliance. In this process raw signal from the sensor is modify by lag-1 concept to capture transient condition in magnitude and duration. Then the data is deliver to Neural Network (NN) for final step appliance identification. Data resulted by NN is sent to the display and also sent to the server real time in order to be monitored online, either using website or using Android. From the experiment result, it can be proof that OEMS capable to identify the use of appliances and also capable to monitor the use of energy consumption real time with 5% error tolerance in averages. With this performance the OEMS have big chance to implement in the real systems and mass production.

Original languageEnglish
Pages (from-to)46-53
Number of pages8
JournalInternational Journal of Mechanical and Mechatronics Engineering
Volume18
Issue number3
Publication statusPublished - 1 Jun 2018

Keywords

  • Android
  • Artificial neural network
  • Microprosessor
  • Non-intrusive load monitoring
  • Online energy monitoring system
  • Signal
  • Smart meter
  • Time series modify

Fingerprint

Dive into the research topics of 'Smart meter based on time series modify and neural network for online energy monitoring'. Together they form a unique fingerprint.

Cite this