An AI adaptive coding transmission method for large-scale passive random access
Shuo Li, Min Zhu · 2025
With the rapid development of communication systems, achieving large-scale passive connections and low-latency transmission has become a core challenge. This article proposes an AI adaptive coding transmission scheme for large-scale passive random access, aiming to solve the performance bottleneck of traditional multi-access technology when facing massive device connections. This article first discusses the semi-authorization-free large-scale passive random access method. This method significantly reduces access delay and signaling overhead by reducing network coordination requirements and improves the overall efficiency of the system. Next, an AI adaptive coding strategy based on a generative adversarial network is introduced, which can dynamically adjust the coding strategy according to real-time data characteristics and optimize data transmission efficiency. Finally, simulation experiments are conducted to verify the advantages of the proposed integrated scheme in terms of high spectrum efficiency and low-latency transmission.