ACE: Towards Application-Centric Edge-Cloud Collaborative Intelligence

TL;DR

This paper introduces ACE, a unified platform designed to facilitate scalable, efficient, and application-centric edge-cloud collaborative intelligence, addressing current limitations in infrastructure management, workload handling, and performance optimization.

Contribution

ACE is the first comprehensive platform that manages diverse resources and workloads for scalable, high-performance edge-cloud collaborative AI applications.

Findings

Successfully built an ACE-based intelligent video query application

Demonstrated customizable performance optimization techniques

Discussed limitations and future directions of ACE

Abstract

Intelligent applications based on machine learning are impacting many parts of our lives. They are required to operate under rigorous practical constraints in terms of service latency, network bandwidth overheads, and also privacy. Yet current implementations running in the Cloud are unable to satisfy all these constraints. The Edge-Cloud Collaborative Intelligence (ECCI) paradigm has become a popular approach to address such issues, and rapidly increasing applications are developed and deployed. However, these prototypical implementations are developer-dependent and scenario-specific without generality, which cannot be efficiently applied in large-scale or to general ECC scenarios in practice, due to the lack of supports for infrastructure management, edge-cloud collaborative service, complex intelligence workload, and efficient performance optimization. In this article, we systematically design and construct the first unified platform, ACE, that handles ever-increasing edge and cloud resources, user-transparent services, and proliferating intelligence workloads with increasing scale and complexity, to facilitate cost-efficient and high-performing ECCI application development and deployment. For verification, we explicitly present the construction process of an ACE-based intelligent video query application, and demonstrate how to achieve customizable performance optimization efficiently. Based on our initial experience, we discuss both the limitations and vision of ACE to shed light on promising issues to elaborate in the approaching ECCI ecosystem.