Reinforcement-Learning-Based Edge Caching for IoT in Compute-First Networks

Abstract

6G networks require ultra-low latency and intelligent resource management in IoT environments. Compute-First Networking (CFN), integrating distributed computing and edge caching, addresses backhaul congestion. This paper proposes CaRL, a DRL-based caching framework using TD3 algorithm. CaRL optimizes cache placement at edge nodes by incorporating real-time network state, content popularity, and resource utilization. Simulations show CaRL improves cache hit ratio, reduces latency, and enhances bandwidth efficiency, and ensures secure caching decisions under dynamic network conditions. Unlike existing methods, CaRL adapts to dynamic network conditions by integrating latency, CPU, and memory metrics, demonstrating scalability and adaptability in CFN-driven 6G environments.