A GRL-aided federated graph reinforcement learning approach for enhanced file caching in mobile edge computing

The exponential growth of data and user density in mobile networks has led to increased latency in delivering content, particularly in mobile edge computing (MEC). Edge caching strategies, which store frequently accessed data closer to users, are crucial to minimize latency. However, traditional caching methods struggle to adapt to the dynamic environment of MEC, where user mobility and data popularity are highly variable. This paper addresses the problem of optimizing caching strategies to reduce content transmission delay in MEC while preserving user privacy. We propose a federated graph reinforcement learning (CFGRL) approach that integrates graph neural networks with federated learning and deep reinforcement learning (DRL). This model predicts popular content and updates caching strategies dynamically, improving latency without sharing user data. Simulations on real-world datasets show that CFGRL achieves a 32% reduction in content transmission delay and an 11.9% increase in cache hit ratio compared to existing methods like CFDRL and Thompson sampling. The CFGRL model demonstrates superior scalability and efficiency, making it well-suited for real-time applications in highly dynamic mobile environments. These results suggest that the proposed approach can significantly enhance the performance of MEC systems, making it a vital solution for modern mobile networks.