MUMBAI, India, Sept. 7 -- Intellectual Property India has published a patent application (202641101494 A) filed by Dayananda Sagar Academy Of Technology And Management; and Dayananda Sagar University on August 22, 2026, for A Carbon-Adaptive Federated Learning System And Method With Ai-Based Node Scheduling For Sustainable Edge Intelligence.
Inventors include Prof. Ashalatha N S; Dr. Gousia Thahniyath; Prof. Radhika K; Dr. D. Srikanth; Dr Mouleeswaran S K; Prof. Sharanabasappa Tadkal; Prof. Mala B A; Prof. Bharath M B; and Dr. Santosh Kumar J.
The application for the patent was published on September 04, 2026, under issue no. 36/2026.
Abstract: The present invention relates to a carbon-adaptive federated learning system and method with AI-based node scheduling for sustainable edge intelligence. The system comprises a plurality of edge nodes, a carbon monitoring module, an energy and resource monitoring module, a communication monitoring module, a node reliability module, an AI-based node scheduling module, and a federated learning coordinator. The system dynamically evaluates carbon intensity, renewable energy availability, residual energy, computational capability, communication conditions, and node reliability to determine a participation priority for each edge node. The AI-based node scheduling module selects suitable nodes for successive federated learning rounds based on the determined priority. Selected nodes perform local model training and transmit model updates to the federated learning coordinator for aggregation into a global model. The proposed invention reduces energy consumption, communication overhead, and carbon emissions while maintaining efficient distributed model training and is applicable to IoT, healthcare, industrial, smart-city, and other edge- computing environments.
Disclaimer: Curated by HT Syndication.
