Architecture and Performance Evaluation of Distributed Computation Offloading in Edge Computing

TL;DR

This paper introduces a novel edge computing architecture that combines serverless and distributed offloading techniques, along with a new evaluation framework, to improve low-latency application performance in heterogeneous environments.

Contribution

It proposes an integrated architecture and distributed algorithm for task offloading, plus a specialized evaluation framework for heterogeneous edge environments.

Findings

Achieves comparable or better delay performance than centralized solutions.

Reduces network utilization significantly.

Effective in both small- and large-scale scenarios.

Abstract

Edge computing is an emerging paradigm to enable low-latency applications, like mobile augmented reality, because it takes the computation on processing devices that are closer to the users. On the other hand, the need for highly scalable execution of stateless tasks for cloud systems is driving the definition of new technologies based on serverless computing. In this paper, we propose a novel architecture where the two converge to enable low-latency applications: this is achieved by offloading short-lived stateless tasks from the user terminals to edge nodes. Furthermore, we design a distributed algorithm that tackles the research challenge of selecting the best executor, based on real-time measurements and simple, yet effective, prediction algorithms. Finally, we describe a new performance evaluation framework specifically designed for an accurate assessment of algorithms and protocols in edge computing environments, where the nodes may have very heterogeneous networking and processing capabilities. The proposed framework relies on the use of real components on lightweight virtualization mixed with simulated computation and is well-suited to the analysis of several applications and network environments. Using our framework, we evaluate our proposed architecture and algorithms in small- and large-scale edge computing scenarios, showing that our solution achieves similar or better delay performance than a centralized solution, with far less network utilization.