A Deep Reinforcement Learning Approach to Multi-component Job Scheduling in Edge Computing

TL;DR

This paper proposes a deep reinforcement learning method for optimizing multi-component job scheduling in edge computing systems, effectively reducing job slowdown amid network delays and dynamic node availability.

Contribution

It introduces a novel DRL actor-critic algorithm tailored for edge job scheduling, demonstrating superior performance over existing algorithms in simulations.

Findings

Outperforms existing algorithms in reducing job slowdown

Effective in both synthetic and real Google cloud data

Addresses interdependence and communication delays in edge scheduling

Abstract

We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network. The scheduling and placement of application jobs in an edge system is challenging due to the interdependence of multiple components of each job, and the communication delays between the geographically distributed data sources and edge nodes and their dynamic availability. In this paper we explore the feasibility of applying Deep Reinforcement Learning (DRL) based design to address these challenges. We introduce a DRL actor-critic algorithm that aims to find an optimal scheduling policy to minimize average job slowdown in the edge system. We have demonstrated through simulations that our design outperforms a few existing algorithms, based on both synthetic data and a Google cloud data trace.