Intellectual Property India Publishes Patent Application for Iot-Enabled Intelligent Energy Management System With Real-Time Data Aggregation And Machine Learning-Based Load Forecasting

MUMBAI, India, Sept. 7 -- Intellectual Property India has published a patent application (202641104693 A) filed by Ms. R. Sujitha; Ms. P. Geethanjally; Ms. Sujitha P; Mr. Vetriselvan M; Ms. Jenifa P; Mr. Mustaq Ahamed Bulbul; Ms. Yogeshwari C; Ms. Rinu Rija A; Dr. A. Kingsly Jabakumar; Dr. M. Muthukrishnan; Dr. S. Dinesh Kirupha; and Mr. Samuel J on August 31, 2026, for Iot-Enabled Intelligent Energy Management System With Real-Time Data Aggregation And Machine Learning-Based Load Forecasting.

Inventors include Ms. R. Sujitha; Ms. P. Geethanjally; Ms. Sujitha P; Mr. Vetriselvan M; Ms. Jenifa P; Mr. Mustaq Ahamed Bulbul; Ms. Yogeshwari C; Ms. Rinu Rija A; Dr. A. Kingsly Jabakumar; Dr. M. Muthukrishnan; Dr. S. Dinesh Kirupha; and Mr. Samuel J.

The application for the patent was published on September 04, 2026, under issue no. 36/2026.

Abstract: IoT-Enabled Intelligent Energy Management System with Real-Time Data Aggregation and Machine Learning-Based Load Forecasting is disclosed for intelligent monitoring, prediction, and optimization of electrical energy consumption. The system comprises distributed IoT-enabled energy sensing devices, an IoT communication network, a real-time data aggregation module, a data preprocessing module, a machine learning-based load forecasting module, and an energy optimization module. Electrical parameters collected from multiple loads are continuously transmitted to an IoT gateway and aggregated in real time. Historical and real-time energy data are processed to generate features for a machine learning model that predicts future energy demand. Based on the predicted demand, the energy optimization module generates or executes intelligent actions including load scheduling, peak-demand reduction, renewable-energy utilization, and battery charging or discharging control. Actual energy consumption is compared with predicted consumption to facilitate continuous improvement of the forecasting model. The proposed system enables predictive, adaptive, and efficient energy management for smart buildings, industries, campuses, microgrids, and smart-grid environments.

Disclaimer: Curated by HT Syndication.