DeepEdge: A Deep Reinforcement Learning based Task Orchestrator for Edge Computing

TL;DR

DeepEdge is a deep reinforcement learning-based task orchestrator designed for edge computing environments, capable of adaptive, autonomous task offloading under dynamic network conditions to improve task completion rates.

Contribution

The paper introduces DeepEdge, a novel DRL-based task orchestrator for edge computing that learns to optimize task offloading without human intervention in highly dynamic environments.

Findings

DeepEdge outperforms existing methods in task completion percentage.

It effectively adapts to various applications and network loads.

The approach models task offloading as a Markov process and uses DDQN for learning.

Abstract

The improvements in the edge computing technology pave the road for diversified applications that demand real-time interaction. However, due to the mobility of the end-users and the dynamic edge environment, it becomes challenging to handle the task offloading with high performance. Moreover, since each application in mobile devices has different characteristics, a task orchestrator must be adaptive and have the ability to learn the dynamics of the environment. For this purpose, we develop a deep reinforcement learning based task orchestrator, DeepEdge, which learns to meet different task requirements without needing human interaction even under the heavily-loaded stochastic network conditions in terms of mobile users and applications. Given the dynamic offloading requests and time-varying communication conditions, we successfully model the problem as a Markov process and then apply the Double Deep Q-Network (DDQN) algorithm to implement DeepEdge. To evaluate the robustness of DeepEdge, we experiment with four different applications including image rendering, infotainment, pervasive health, and augmented reality in the network under various loads. Furthermore, we compare the performance of our agent with the four different task offloading approaches in the literature. Our results show that DeepEdge outperforms its competitors in terms of the percentage of satisfactorily completed tasks.