DELCAS: Deep Reinforcement Learning Based GPU CaaS Packet Scheduling for Stabilizing QoE in 5G Multi-Access Edge Computing

Abstract

Recently, Docker Container as a Service (CaaS) has been provided for multi-user services in the 5G Multi-Access Edge Computing (MEC) environment, and servers that support accelerators such as GPUs, not conventional CPU servers, are being considered. In addition, as the number of AI services is increasing and the computation power required by deep neural network model increases, offloading to edge servers is required due to insufficient computational capacity and heat problem of user devices (UE). However, there is a resource scheduling problem because all users’ packets cannot be offloaded to the edge server due to resource limitations. To address this problem, we suggest deep reinforcement learning-based GPU CaaS Packet scheduling named as Delcas for stabilizing quality of AI experience. First, we design the architecture using containerized target AI application on MEC GPUs and multiple users send video stream to MEC server. We evaluate video stream to identify the dynamic amount of resource requirement among each users using optical flow and adjust user task queue. To satisfy equal latency quality of experience, we apply lower quality first serve approach and respond hand pose estimation results to each user. Finally, we evaluate our approach and compare to conventional scheduling method in the aspect of both accuracy and latency quality.

Supported by Samsung Network (SNIC) and BK21.