MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641105932 A) filed by G. Pullaiah College Of Engineering And Technology Autonomous on September 02, 2026, for System And Method For Low Power Risc V Based Edge Ai Accelerator For Real Time Iot Applications.
Inventors include Dr K. Rajkumar; Dr K. C. T. Swamy; Dr B Ravi Chandra; and S. Towseef Ahmed.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: ABSTRACT SYSTEM AND METHOD FOR LOW POWER RISC V BASED EDGE AI ACCELERATOR FOR REAL TIME IOT APPLICATIONS The invention discloses a system and method for designing a low-power RISC-V based edge AI accelerator for real-time IoT applications. The system integrates a lightweight RISC-V processor core with specialized AI acceleration modules, including matrix multiplication engines, convolution accelerators, and activation function units. A hierarchical memory subsystem ensures efficient data flow, while dynamic voltage and frequency scaling optimizes energy consumption. Security is embedded through cryptographic accelerators and secure boot mechanisms, safeguarding sensitive IoT data. The architecture adheres to the open RISC-V standard, ensuring interoperability and reducing vendor lock-in. Novelty lies in the combination of low-power operation, modular AI acceleration, and integrated security, enabling real-time inference within constrained energy budgets. Advantages include reduced latency, improved efficiency, enhanced privacy, and scalability across diverse IoT applications. The invention provides a foundation for next-generation IoT ecosystems where intelligence is distributed, adaptive, and secure.
Disclaimer: Curated by HT Syndication.
