Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence

Интеллектуальные периферийные вычисления: объединение периферийных вычислений и искусственного интеллекта
Shuiguang Deng, Hailiang Zhao, Weijia Jia Fang, Jianwei Yin, Schahram Dustdar, Albert Y. Zomaya
2020-04-01

AI for edgeAI on edgeartificial intelligenceedge computingedge intelligence
Along with the rapid developments in communication technologies and the surge in the use of mobile devices, a brand-new computation paradigm, edge computing, is surging in popularity. Meanwhile, the artificial intelligence (AI) applications are thriving with the breakthroughs in deep learning and the many improvements in hardware architectures. Billions of data bytes, generated at the network edge, put massive demands on data processing and structural optimization. Thus, there exists a strong demand to integrate edge computing and AI, which gives birth to edge intelligence. In this article, we divide edge intelligence into AI for edge (intelligence-enabled edge computing) and AI on edge (artificial intelligence on edge). The former focuses on providing more optimal solutions to key problems in edge computing with the help of popular and effective AI technologies while the latter studies how to carry out the entire process of building AI models, i.e., model training and inference, on the edge. This article provides insights into this new interdisciplinary field from a broader perspective. It discusses the core concepts and the research roadmap, which should provide the necessary background for potential future research initiatives in edge intelligence.
1
Edge intelligence addresses demands created by rapid growth in mobile devices, communication technologies, edge-generated data, and advances in deep learning and hardware architectures.
2
Edge intelligence emerges from integrating edge computing with artificial intelligence to process and optimize massive data generated at the network edge.
3
The article establishes core concepts and a research roadmap intended to guide future interdisciplinary research in edge intelligence.
4
The field is divided into AI for edge, which applies AI to optimize edge-computing problems, and AI on edge, which performs AI model training and inference at the edge.

edge intelligence, integrating edge computing with artificial intelligence

the use of AI to optimize edge-computing problems and to perform AI model training and inference at the network edge

Publication Details
Publication Date
2020-04-01
Journal
IEEE Internet of Things Journal
Publisher
Institute of Electrical and Electronics Engineers
ISSN
2327-4662
Cited by
1476
Access Type
Author Information
Authors
Shuiguang Deng
Hailiang Zhao
Weijia Jia Fang
Jianwei Yin
Schahram Dustdar
Albert Y. Zomaya
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%