Intelligence Stratum for IoT. Architecture Requirements and Functions

Abstract

The use of Artificial Intelligence (AI) is becoming increasingly pervasive and relevant in many different application areas. Researchers are putting a considerable effort to take full advantage of the power of AI, while trying to overcome the technical challenges that are intrinsically linked to almost any domain area of application, such as the Internet of Things (IoT). One of the biggest problems related to the use of AI in IoT is related to the difficulty of coping with the wide variety of protocols and software technologies used, as well as with the heterogeneity of the hardware resources consuming the AI. The scattered IoT landscape accentuates the limitations on interoperability, especially visible in the deployment of AI, affecting the seamless AI life-cycle management as well. In this paper, it is discussed how to enable AI distribution in IoT by introducing a layered intelligence architecture that aims to face the undertaken challenges taking into account the special requirements of nowadays IoT networks. It describes the main characteristics of the new paradigm architecture, highlighting what are the implications of its adoption from use cases perspective and their requirements. Finally, a set of open technical and research challenges are enumerated to reach the full potential of the intelligence distribution's vision.This article has been accepted for publication in the 17th IEEE International Conference on Pervasive Intelligence and Computing (PICom 2019) © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

The Challenges of Artificial Intelligence in Wireless Networks for the Internet of Things: Exploring Opportunities for Growth

“…AI system running as a virtual function) between multiple edge nodes, and between edge nodes and centralized monitoring and control systems is visualized. Intelligent AI services for IoT can be decoupled much like Network Function Virtualization (NFV) with the unique requirements of IoT and AI, as elaborated in [58]. AI system or service mobility, along with synchronizing the needed AI processing among multiple edge nodes [56], can be achieved through the novel technological development in communication and computing technologies such as SDN and MEC, as explained with examples in [59].…”

Semantic Descriptor for Intelligence Services

“…Other steps have been taken to decouple AI from applications through using RESTful APIs to remotely execute models(e.g., [15] and [16]). However, [2] and [3] argued that for many IoT devices this approach does not suffice because API updates for the targeted devices will be heavily complicated due to compatibility issues. Also, the semantic tools outlined here does not target the particularities of the device heterogeneity and their context might only be restricted to very few domains of deployment or use case.…”

“…Currently, this coupling is one of the most challenging aspect of deploying AI in real-world applications. The high, and still increasing, level of coupling of AI solutions to the applications is discussed in detail in [2] and [3]. Coupling basically enforces the provision of one-of and tailor-made AI solutions that fits only or a small number of implementations.…”

“…A device might execute one or multiple "intelligent" applications and the "perception" of their intelligence comes from how they are able to learn, or process data in a way that seems to resemble human-like reasoning. As it has been defined in [3], "An intelligent application makes use of one or several intelligent services that allows it to fulfill its task which is closely related to a use case". Therefore an application makes use of specific AI or ML models that can be abstracted as " s" (IS).…”