On the Road from Edge Computing to the Edge Mesh

TL;DR

This paper surveys the evolution from traditional edge computing to an intelligent, cooperative edge mesh ecosystem, highlighting hardware, management techniques, and machine learning applications to enable efficient, real-time services.

Contribution

It provides a comprehensive overview of the components, challenges, and research directions for developing an intelligent edge mesh infrastructure for IoT applications.

Findings

Survey of hardware and software components for EC/EM

Discussion of machine learning and optimization techniques used

Identification of challenges and future research directions

Abstract

Nowadays, we are witnessing the advent of the Internet of Things (EC) with numerous devices performing interactions between them or with end users. The huge number of devices leads to huge volumes of collected data that demand the appropriate processing. The 'legacy' approach is to rely on Cloud where increased computational resources can be adopted to realize any processing. However, even if the communication with the Cloud back end lasts for some seconds there are cases where problems in the network or the need for supporting real time applications require a reduced latency in the provision of responses/outcomes. Edge Computing (EC) comes into the scene as the 'solver' of the latency problem (and not only). Any processing can be performed close to data sources, i.e., at EC nodes having direct connection with IoT devices. Hence, an ecosystem of processing nodes can be present at the edge of the network giving the opportunity to apply novel services upon the collected data. Various challenges should be met before we talk about a fully automated ecosystem where EC nodes can cooperate or understand the status of them and the environment to be capable of efficiently serving end users or applications. In this paper, we perform a survey of the relevant research activities targeting to support the vision of Edge Mesh (EM), i.e., a 'cover' of intelligence upon the EC infrastructure. We present all the parts of the EC/EM framework starting from the necessary hardware and discussing research outcomes in every aspect of EC nodes functioning. We present technologies and theories adopted for data, tasks and resource management while discussing how (deep) machine learning and optimization techniques are adopted to solve various problems. Our aim is to provide a starting point for novel research to conclude efficient services/applications opening up the path to realize the future EC form.