Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Abstract

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

Network for Distributed Intelligence: a Survey and Future Perspectives

“…In [142] a virtualization layer hosted at the network edge is proposed, which is in charge of the semantic description of AI-embedded IoT devices' capabilities. The virtual replicas expose and augment the cognitive capabilities of the corresponding (potentially constrained) physical devices, in order to feed intelligent IoT applications.…”

Placement of Social Digital Twins at the Edge for Beyond 5G IoT Networks

“…Social Object Relationships (SOR) is established due to sporadic or continuous contact of users/devices. The virtualization layer is responsible for hosting the digital counterparts of physical devices [26], i.e., the SDTs. They offer the typical functionalities a digital counterpart provides, including caching and aggregation of the raw data transmitted by the IoT device, before IoT applications can process them.…”

Comparison of edge computing methods in Internet of Things architectures for efficient estimation of indoor environmental parameters with Machine Learning

“…These solutions are traditionally implemented using a centralised approach, in which IoT sensing nodes collect raw data to be streamed to a concentrator that acts as a gateway, and a remote cloud or another edge device with high processing capacity performs compute-intensive tasks, such as AI model training and inference (Ramos et al, 2019). Although centralisation has the advantage of storing the results of the inference stage and can be later requested by other applications without re-running the computation (Campolo et al, 2021), the vast use of certain central edge nodes with parallelism degree and multiple convolution cores, such as Graphics Processing Units (GPU), are not appropriate for resource-constrained IoT architectures (Shafique et al, 2018). Given this situation, other alternatives are being evaluated with the direct intervention of local nodes in data processing, such as concurrent computing (Shi et al, 2016) and fog computing, acting as a medium layer with fog devices of limited storage and computing capabilities, which collect the data offloaded by IoT sensing devices and decide whether to process it locally or offload to the cloud layer via a fog gateway (Ogundoyin and Kamil, 2023).…”