An edge-cloud collaborative computing platform for building AIoT applications efficiently

Abstract

The convergence of the Artificial Intelligence (AI) and the Internet of Things (IoT), i.e. the Artificial Intelligence of Things (AIoT), is a very promising technology that redefines the way people interact with the surrounding devices. Practical AIoT applications not only have high demands on computing and storage resources, but also desire for high responsiveness. Traditional cloud-based computing paradigm faces the great pressure on the network bandwidth and communication latency, hence the newly emerged edge computing paradigm gets involved. Consequently, AIoT applications can be implemented in an edge-cloud collaborative manner, where the model building and model inferencing are offloaded to the cloud and the edge, respectively. However, developers still face challenges building AIoT applications in practice due to the inherent heterogeneity of the IoT devices, the declining accuracy of once trained models, the security and privacy issues, etc. In this paper, we present the design of an industrial edge-cloud collaborative computing platform that aims to facilitate building AIoT applications in practice. Furthermore, a real-world use case is presented in this paper, which proved the efficiency of building an AIoT application on the platform.

Arithmetic Framework to Optimize Packet Forwarding among End Devices in Generic Edge Computing Environments

“…In case it is a higher natural number, it needs to apply a correction factor of −1, such as in k + b /k 2 − 1. Luckily, both expressions may be collapsed in just one being useful in both cases by substituting −1 with a special corrector factor included in expression (9), which achieves the expected results in both cases:…”

“…Specifically, those new AI-powered may improve performance in many fields [5], and may allow Internet of Things (IoT) devices to take advantage of them by means of Local Area Network (LAN) links, those having high bandwidth and short round trip times [6]. This situation may facilitate the increase in IoT environments [7], which may induce the need of optimizing their designs [8], and in this regard, it might be useful to obtain a generic regular scheme in order to optimize the resources being put in place when undertaking an IoT deployment [9].…”

Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review

“…An Edge-Cloud collaborative computing platform for Artificial Intelligence of Things (AIoT) is proposed in [120]. Named Sophon Edge, the platform helps to build and deploy AIoT applications efficiently.…”

Modeling of a Generic Edge Computing Application Design

“…The popularization of edge AI along with the integration of cloud AI as a backup and storage service make it possible to carry out the processing of massive amounts of sensing data coming from IoT devices in all kinds of environments. This leads to the convergence of AI and IoT, also known as AIoT [94]; thus, enhancing the computational tools for dealing with big data derived from IoT-based devices in basically any field [95].…”