IoT Next Generation Smart Grid Meter (NGSM) for On-Edge Household Appliances Detection Based on Deep Learning and Embedded Linux

In recent years, domestic and industrial users have shifted from traditional meters to smart meters. A solution implemented called the Next-Generation Smart Grid Meter (NGSM) is a smart meter device for monitoring electricity consumption. It measures the energy consumption of a household and acts as a smart node in the electricity grid to apply the next generation of Advanced Metering Infrastructure (AMI) systems connected via a smart grid for cluster communication. Various features would be included such as measuring the power, energy…etc., and calculating the costs with a developed Head-End System (HES) which is divided into a web-based system and a smartphone mobile application for the overall monitoring across the supported region and displaying the readings on the meter LCD TFT screen for the user, and tamper detection mechanisms. The smart grid connection is made via the internet which transmits the data over the grid. Moreover, it applies a deep learning model using the data collected in its data storage to make classification and prediction of the working household appliances at different times. The concluded NGSM system is an Embedded Linux-based meter for real-time on-edge processing with a complete HES, web and mobile application. Household appliance detection using the aggregated load achieved 93.75% accuracy with 3 devices operating at the same time.