Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
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.
Abstract
Along with the rapid developments in communication technologies and the surge\nin the use of mobile devices, a brand-new computation paradigm, Edge Computing,\nis surging in popularity. Meanwhile, Artificial Intelligence (AI) applications\nare thriving with the breakthroughs in deep learning and the many improvements\nin hardware architectures. Billions of data bytes, generated at the network\nedge, put massive demands on data processing and structural optimization. Thus,\nthere exists a strong demand to integrate Edge Computing and AI, which gives\nbirth to Edge Intelligence. In this paper, we divide Edge Intelligence into AI\nfor edge (Intelligence-enabled Edge Computing) and AI on edge (Artificial\nIntelligence on Edge). The former focuses on providing more optimal solutions\nto key problems in Edge Computing with the help of popular and effective AI\ntechnologies while the latter studies how to carry out the entire process of\nbuilding AI models, i.e., model training and inference, on the edge. This paper\nprovides insights into this new inter-disciplinary field from a broader\nperspective. It discusses the core concepts and the research road-map, which\nshould provide the necessary background for potential future research\ninitiatives in Edge Intelligence.\n