Using Deep Reinforcement Learning for Application Relocation in Multi-access Edge Computing

Multi-access Edge Computing (MEC) brings data and computational resources near mobile users, with the ultimate goal ofreducing latency, improving resource utilization and leveraging context- and radio-awareness. Relocation policies for applicationsin the MEC environment are necessary to guarantee its effectiveness and performance, and can use a multitude of different data(user position and direction, availability of MEC services and computation resources, etc.). In this paper, we advocate using deepreinforcement learning to relocate applications in MEC scenarios, by having MEC learn during the evolution of the sytem. Weshow the feasibility of this approach and highlight its benefits via simulation, also presenting an environment which can fosterfuture research on this topic.