MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202511034662 A) filed by Indian Institute Of Technology Delhi on April 09, 2025, for System And Method For Ai/Ml-Based Latency Reduction In Wireless Retransmission Mechanisms.
Inventors include Aggrawal, Monika; Dube, Puja; and Pandey, Brijesh Chander.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: The invention introduces an AI/ML-based Hybrid Automatic Repeat Request (HARQ) bit predictor to reduce latency and enhance data transmission reliability in 5G and emerging 6G networks. By predicting HARQ bits, the system initiates immediate retransmissions, minimizing delays associated with traditional feedback mechanisms. The predictor processes input features such as path loss, SINR, and CQI to forecast acknowledgment (ACK) or negative acknowledgment (NACK) for each data packet. Integrated within the Distributed Unit (DU) or as an xApp in the near real-time RAN Intelligent Controller (RIC), the system dynamically allocates resources, optimizing throughput and reducing unnecessary retransmissions. The invention supports real-time applications requiring ultra-low latency, such as autonomous vehicles and virtual reality streaming, by ensuring data integrity through feedback comparison and higher layer interventions. This approach enhances network efficiency, scalability, and adaptability, providing a future-proof solution for modern wireless communication challenges.
Disclaimer: Curated by HT Syndication.
