MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641051573 A) filed by Dr. V. S. Triveni; Dr. Akkili Naresh; Dr. Fahmeeda Faique Shaikh; Dr. B. Krishnaveni; Mrs. Kiran Mayur Patil; Dayananda Sagar Academy Of Technology And Management; Dr. Nagaraj C; Mr. Swaroop Mallick; and Dr Someshwar Siddi, Hyderabad, Telangana, on April 22, for 'a predictive mathematical algorithm for solar and wind energy output forecasting to improve sustainable power management.'
Inventor(s) include Dr. V. S. Triveni; Dr. Akkili Naresh; Dr. Fahmeeda Faique Shaikh; Dr. B. Krishnaveni; Mrs. Kiran Mayur Patil; Dayananda Sagar Academy Technology And Management; Dr. Nagaraj C; Mr. Swaroop Mallick; and Dr Someshwar Siddi.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a novel predictive mathematical algorithm designed to significantly enhance the accuracy and reliability of solar and wind energy output forecasting, thereby improving sustainable power management. The algorithm integrates advanced machine learning techniques, specifically a multi-layered neural network, with a dynamic Bayesian inference engine. This synergistic combination enables the processing of diverse data inputs, including satellite imagery, meteorological data, and historical energy generation records, through sophisticated feature engineering. A key aspect of the invention is its adaptive learning capability, allowing continuous refinement of predictions based on new data and evolving environmental conditions. Furthermore, the algorithm incorporates a robust uncertainty quantification module, providing both point forecasts and crucial probabilistic forecasts for informed decision-making in power grid operations. The output includes short-term, medium-term, and long-term energy output predictions, facilitating comprehensive planning and operational adjustments. This innovative approach aims to minimize discrepancies between forecasted and actual energy generation, reduce reliance on expensive backup power, optimize energy storage utilization, and enhance the overall stability and economic viability of renewable energy systems. The algorithm is designed for scalability and computational efficiency, making it suitable for various power grid environments and easily integrable with existing energy management systems."
Disclaimer: Curated by HT Syndication.
