MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079684 A) filed by Sona College Of Technology on June 29, 2026, for An Artificial Intelligence Based Electricity Usage Prediction And Personalized Energy Optimization System And Method Thereof.
Inventors include Sasirekha K; Harini Sri R; and Kiruthika S.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: ABSTRACT The present invention relates to an explainable artificial intelligence-based electricity usage prediction and optimization system for smart energy management. The system comprises a data acquisition module, a preprocessing module, a feature engineering module, a forecasting engine employing a Bidirectional Long Short-Term Memory (BiLSTM) model, an explainability engine, and a recommendation generation engine. Historical electricity consumption data are collected, processed, and analyzed to generate accurate future electricity consumption forecasts. The explainability engine utilizes feature attribution analysis to identify and quantify the influence of individual consumption-related parameters on predicted outputs. Based on the identified influential factors, the recommendation generation engine automatically produces personalized energy optimization recommendations for reducing electricity consumption and improving energy efficiency. The invention establishes a functional linkage between prediction, explainability, and recommendation generation, thereby providing interpretable forecasting results and actionable energy-saving guidance. The system enhances transparency, user trust, decision-making capability, and sustainable energy management across residential, commercial, institutional, and industrial environments.
Disclaimer: Curated by HT Syndication.
