Smart Energy Tracker

Abstract

The Smart Energy Tracker is a web-based IoT and machine learning system for real-time monitoring and prediction of household electricity consumption. By integrating an ESP32 NodeMCU with ZMPT-101B and ACS712 sensors, the system transmits data to a server for visualization and analysis. Machine learning models predict electricity bills, while anomaly detection algorithms identify irregular consumption patterns. This system addresses energy challenges in India, where 70% of electricity is derived from coal and households contribute to 25% of the demand. The tracker encourages efficient electricity usage, contributing to emission reduction goals and promoting sustainability. Prototype testing demonstrated high prediction accuracy and reliable monitoring capabilities. The system’s performance underscores its potential to reduce financial costs associated with energy consumption and minimize environmental impacts. By enabling accurate forecasting and timely identification of abnormal usage, the Smart Energy Tracker supports both economic and environmental benefits at the household level. This approach offers a scalable solution to enhance energy efficiency and reduce the carbon footprint of residential electricity consumption.