A Reinforcement Learning-based Orchestrator for Edge Computing Resource Allocation in Mobile Augmented Reality Systems
Weiyang Qian, Rodolfo W. L. Coutinho · 2023
Augmented reality (AR) is gaining increasing attention thanks to its potential for enhancing applications in different domains. However, AR systems will reply to different computation-intensive tasks (e.g., object detection, object classification, and content rendering), which are demanding in terms of energy and latency. The use of multi-access edge computing (MEC) technology can significantly reduce the latency and energy cost of AR systems by providing computational resources closer to mobile AR users. In this paper, we proposed a reinforcement learning-based orchestrator for the management and allocation of networked edge servers’ computing resources for AR mobile users. The proposed Migration Enabled Task Allocation (META) orchestrator takes into consideration the AR tasks and edge servers characteristics when deciding if an incoming AR task will be admitted or not, and in which edge server it will be executed in case it is admitted. Moreover, the proposed orchestrator migrates tasks among edge servers if needed to free resources during the incoming of a new AR task. We also design the deep META-DQN and META-PPO algorithms to be used by the META orchestrator for predicting AR tasks’ arrival and learning the optimal policy in terms of allocating edge computing resources. Obtained results show that our proposed META-PPO model decreased the task blocking rate by up to 180% when compared to related work.