Abstract
Artificial Intelligence (AI) at the edge is the utilization of AI in real-world devices. Edge AI refers to the practice of doing AI computations near the users at the network's edge, instead of centralised location like a cloud service provider's data centre. With the latest innovations in AI efficiency, the proliferation of Internet of Things (IoT) devices, and the rise of edge computing, the potential of edge AI has now been unlocked. This study provides a thorough analysis of AI approaches and capabilities as they pertain to edge computing, or Edge AI. Further, a detailed survey of edge computing and its paradigms including transition to Edge AI is presented to explore the background of each variant proposed for implementing Edge Computing. Furthermore, we discussed the Edge AI approach to deploying AI algorithms and models on edge devices, which are typically resource-constrained devices located at the edge of the network. We also presented the technology used in various modern IoT applications, including autonomous vehicles, smart homes, industrial automation, healthcare, and surveillance. Moreover, the discussion of leveraging machine learning algorithms optimized for resource-constrained environments is presented. Finally, important open challenges and potential research directions in the field of edge computing and edge AI have been identified and investigated. We hope that this article will serve as a common goal for a future blueprint that will unite important stakeholders and facilitates to accelerate development in the field of Edge AI.
| Original language | English |
|---|---|
| Pages (from-to) | 71-92 |
| Number of pages | 22 |
| Journal | Internet of Things and Cyber-Physical Systems |
| Volume | 3 |
| Early online date | 3 Mar 2023 |
| DOIs | |
| Publication status | Published - 31 Dec 2023 |
Bibliographical note
Funding Information:The 5G MiEdge (Millimetre-wave Edge Cloud as an enabler for 5G ecosystem) project, funded by the European Union, is primarily focused on a millimetre wave 5G Radio access network.5 This project has two main goals. Firstly, it considers mmWave access and MEC are combined to reduce the computation task at the edge of the network. The second goal is to develop a novel control plane to maximize resources for mobile users. The project will contribute to the standardization of mmWave access and Radio Access Network Centralised-plan in 3GPP and IEEE. Ultimately, it will demonstrate a joint 5G test-bed in the city of Berlin and the 2020 Tokyo Olympic Stadium. This project involves two private-sector participants: Intel Deutschland and Telecom Italia.Sectors: Moving resources closer to the “fixed edge” represented by surveillance cameras, traffic flow enhancement systems, smart meters, etc., is a feature of FC. Associated long-term data storage can therefore be allocated to cloud computing resources. Mobile MEC users form a transient population with varying requirements. This is a more challenging sector with requirements for hardware and software and functional architectures that are only emerging from demonstration projects. In contrast, mDCs have an already defined segment in the Industrial IoT but could readily be deployed to support FC, MEC and even Cloudlets (although CL would require some form of public funding if open-access platforms are to be implemented)
Funding
The 5G MiEdge (Millimetre-wave Edge Cloud as an enabler for 5G ecosystem) project, funded by the European Union, is primarily focused on a millimetre wave 5G Radio access network.5 This project has two main goals. Firstly, it considers mmWave access and MEC are combined to reduce the computation task at the edge of the network. The second goal is to develop a novel control plane to maximize resources for mobile users. The project will contribute to the standardization of mmWave access and Radio Access Network Centralised-plan in 3GPP and IEEE. Ultimately, it will demonstrate a joint 5G test-bed in the city of Berlin and the 2020 Tokyo Olympic Stadium. This project involves two private-sector participants: Intel Deutschland and Telecom Italia.Sectors: Moving resources closer to the “fixed edge” represented by surveillance cameras, traffic flow enhancement systems, smart meters, etc., is a feature of FC [13]. Associated long-term data storage can therefore be allocated to cloud computing resources [30]. Mobile MEC users form a transient population with varying requirements [96]. This is a more challenging sector with requirements for hardware and software and functional architectures that are only emerging from demonstration projects [33]. In contrast, mDCs have an already defined segment in the Industrial IoT but could readily be deployed to support FC, MEC and even Cloudlets (although CL would require some form of public funding if open-access platforms are to be implemented) [35].
Keywords
- Artificial intelligence
- Cloud computing
- Edge AI
- Edge computing
- Fog computing
- Machine learning
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Networks and Communications
- Computer Science Applications
- Electrical and Electronic Engineering