Experience-driven resource management for mobile edge computing in 6G: A comprehensive survey
Is Version Of
Mobile edge computing (MEC) is a promising network paradigm for delay-sensitive and computation intensive applications for the beyond fifth-generation (B5G) and sixth-generation (6G). However, due to the complex and random nature of the wireless systems, traditional optimization techniques formulated for the resource allocation in B5G result in non-optimal solutions. To address the issue, reinforcement learning (RL) has shown promising results in learning the optimal resource allocation policy for complex B5G networks. This paper provides comprehensive literature survey for RL-empowered resource allocation techniques in MEC for B5G. Moreover, federated RL is also investigated in detail for resource management in MEC. Finally, open challenges and future research directions are presented for addressing the resource allocation challenges in MEC.
Attribution-NonCommercial-NoDerivs 3.0 United States, 2023