Deep Reinforcement Learning-Based Slice-aware Caching for Integrated TN/NTN 6G Networks

Le résumé fourni par la source

The sixth generation (6G) of mobile networks seeks to leverage Integrated Terrestrial and Non-Terrestrial Networks (ITNTN) to support next-generation applications. However, despite increased network densification, meeting the stringent latency requirements—particularly for delay-sensitive applications—remains a significant challenge due to the high latency overhead introduced by non-terrestrial nodes. Content caching offers a potential solution to reduce content access delays and backhaul bandwidth costs by pre-storing content closer to the end users. However, the heterogenity of nodes, the varying content popularity and the distinct Quality of Service (QoS) requirements introduced by network slicing complicate caching decisions in ITNTNs. For instance, prioritizing content related to critical services (e.g., emergency services) over popular content (e.g., social media files) may better address QoS needs, albeit with lower hit ratios, an aspect not explored in existing works. This paper introduces SaCCA-RL (Reinforcement Learning-based Slice-aware Content Caching Algorithm) for selecting which content to cache and its placement under constrained ITNTN node capacities, considering different and varying content popularity and priority. Simulations show that SaCCA-RL results in more than 10% improvement in terms of cache gain compared to baseline algorithms, while guaranteeing 100% hit-ratio for critical content.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.