MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641108662 A) filed by K. S. Murugesan; Yogeswari P; K. Nandagopal; R. Sudhakar; V. Priya; V. Gopalakrishnan; P. Karunakaran; Shantha Kumar S; P. Loganath; and Manoj Praveen V on September 10, 2026, for An Ai-Enabled Hybrid Prediction System For Real-Time Industrial Load Forecasting And Electric Vehicle Charging Energy Management.
Inventors include K. S. Murugesan; Yogeswari P; K. Nandagopal; R. Sudhakar; V. Priya; V. Gopalakrishnan; P. Karunakaran; Shantha Kumar S; P. Loganath; and Manoj Praveen V.
The application for the patent was published on September 18, 2026, under issue no. 38/2026.
Abstract: The present invention relates to an AI-enabled hybrid prediction system for real-time industrial load forecasting and electric vehicle charging energy management. The system is configured to continuously acquire and analyse industrial electrical load data, operational parameters, historical consumption patterns, and electric vehicle charging requirements to support intelligent energy allocation and demand management. The proposed system comprises a real-time data acquisition module, pre- processing unit, hybrid artificial intelligence prediction engine, industrial load monitoring module, electric vehicle charging management module, energy allocation unit, and decision-making controller. The hybrid prediction engine combines multiple machine learning, deep learning, and statistical forecasting techniques to estimate future industrial electrical demand with improved accuracy and adaptability. Based on the predicted industrial load, current power consumption, permissible demand limits, renewable energy availability, energy storage status, and electric vehicle charging requirements, the system dynamically determines available charging capacity. Charging operations are prioritized and regulated according to battery state of charge, required energy, expected departure time, charging urgency, vehicle priority, and available electrical power. The decision-making controller adjusts charging start time, charging power, duration, and sequence to reduce peak demand, prevent electrical overload, and improve utilization of available energy resources. The system may further integrate electricity tariff information, renewable energy sources, and energy storage systems to support cost-effective and sustainable charging operations. The invention therefore provides an adaptive and coordinated energy management solution capable of improving industrial load forecasting accuracy, optimizing electric vehicle charging, reducing peak electrical demand, lowering operational energy costs, enhancing renewable energy utilization, and improving the reliability and efficiency of industrial electrical infrastructure.
Disclaimer: Curated by HT Syndication.
