Reinforcement Learning

In this paper, we propose a deep Q-learning based task offloading solution, DeepTO, for online task offloading. DeepTO learns edge server performance in a model-free manner and takes future battery needs of the mobile device into account.

A mobile edge offloading engine that offloads task from mobile devices to edge and cloud servers based on cloud computation availability, mobile energy, and task execution time. It utilizes reinforcement learning to learn the environment without any previous knowledge.