EaaS: A Service-Oriented Edge Computing Framework Towards Distributed Intelligence

TL;DR

This paper proposes EaaS, a service-oriented edge computing framework that enables distributed intelligence through collaboration among heterogeneous edge nodes, addressing the needs of ultra-low latency and dynamic service provision for advanced applications.

Contribution

The paper introduces EaaS, a novel framework for managing large-scale, geo-distributed edge resources to facilitate autonomous, collaborative, and elastic edge services.

Findings

EaaS enables flexible deployment of services across edge nodes.

EaaS supports real-time applications like video surveillance and metaverse.

The framework enhances edge autonomy and resource elasticity.

Abstract

Edge computing has become a popular paradigm where services and applications are deployed at the network edge closer to the data sources. It provides applications with outstanding benefits, including reduced response latency and enhanced privacy protection. For emerging advanced applications, such as autonomous vehicles, industrial IoT, and metaverse, further research is needed. This is because such applications demand ultra-low latency, hyper-connectivity, and dynamic and reliable service provision, while existing approaches are inadequate to address the new challenges. Hence, we envision that the future edge computing is moving towards distributed intelligence, where heterogeneous edge nodes collaborate to provide services in large-scale and geo-distributed edge infrastructure. We thereby propose Edge-as-a-Service (EaaS) to enable distributed intelligence. EaaS jointly manages large-scale cross-node edge resources and facilitates edge autonomy, edge-to-edge collaboration, and resource elasticity. These features enable flexible deployment of services and ubiquitous computation and intelligence. We first give an overview of existing edge computing studies and discuss their limitations to articulate the motivation for proposing EaaS. Then, we describe the details of EaaS, including the physical architecture, proposed software framework, and benefits of EaaS. Various application scenarios, such as real-time video surveillance, smart building, and metaverse, are presented to illustrate the significance and potential of EaaS. Finally, we discuss several challenging issues of EaaS to inspire more research towards this new edge computing framework.