Deep Reinforcement Learning-Based Dynamic Resource Management for Mobile Edge Computing in Industrial Internet of Things
Nowadays, driven by the rapid development ofsmart mobile equipments and 5G network technologies, theapplication scenarios of Internet of Things (IoT) technologyare becoming increasingly widespread. The integration ofIoT and industrial manufacturing systems forms the industrial IoT (IIoT). Because of the limitation of resources,such as the computation unit and battery capacity in theIIoT equipments (IIEs), computation-intensive tasks need tobe executed in the mobile edge computing (MEC) server.However, the dynamics and continuity of task generationlead to a severe challenge to the management of limitedresources in IIoT. In this article, we investigate the dynamicresource management problem of joint power control andcomputing resource allocation for MEC in IIoT. In order to minimize the long-term average delay of the tasks, theoriginal problem is transformed into a Markov decision process (MDP). Considering the dynamics and continuity oftask generation, we propose a deep reinforcement learningbased dynamic resource management (DDRM) algorithm to solve the formulated MDP problem. Our DDRM algorithmexploits the deep deterministic policy gradient and can deal with the high-dimensional continuity of the action and state spaces. Extensive simulation results demonstrate that the DDRM can reduce the long-term average delay of the taskseffectively.
PDF Abstract
