Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Конвергенция периферийных вычислений и глубокого обучения: комплексный обзор
2020-01-01
SCID: 54.1/66xs37rq
Discuss with AI
deep learningdeep learning training and inferenceedge computingedge intelligenceintelligent edge
Figures from the paper
Abstract (AI)
Ubiquitous sensors and smart devices from factories and communities are generating massive amounts of data, and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network. As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications and services are thriving. However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of “providing artificial intelligence for every person and every organization at everywhere”. Thus, unleashing DL services using resources at the network edge near the data sources has emerged as a desirable solution. Therefore, edge intelligence, aiming to facilitate the deployment of DL services by edge computing, has received significant attention. In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management. With regard to mutually beneficial edge intelligence and intelligent edge, this paper introduces and discusses: 1) the application scenarios of both; 2) the practical implementation methods and enabling technologies, namely DL training and inference in the customized edge computing framework; 3) challenges and future trends of more pervasive and fine-grained intelligence. We believe that by consolidating information scattered across the communication, networking, and DL areas, this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of edge intelligence and intelligent edge, i.e., Edge DL.
Key Findings
1
By consolidating communication, networking, and deep-learning perspectives, the survey clarifies the mutual relationship between edge intelligence and intelligent edge.
2
Deep learning can make edge-computing frameworks intelligent by enabling dynamic, adaptive edge maintenance and management.
3
Edge intelligence deploys deep-learning services near data sources to address the efficiency and latency limitations of cloud-only architectures.
4
The paper identifies challenges and future trends toward more pervasive and fine-grained intelligence at the network edge.
5
The survey organizes Edge DL around application scenarios, practical training and inference methods, and enabling technologies in customized edge frameworks.
Research Object
the convergence of edge computing and deep learning (Edge DL)
Research Subject
application scenarios, implementation methods, enabling technologies, challenges, and future trends for deploying and integrating deep-learning services at the network edge
Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
1520
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
Deep Residual Learning for Image Recognition2016
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
Distilling the Knowledge in a Neural Network2015
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
Graph neural networks: A review of methods and applications2020
An efficient k-means clustering algorithm: analysis and implementation2002
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing2019
Federated Learning in Mobile Edge Networks: A Comprehensive Survey2020
Deep Learning on Graphs: A Survey2020
All one needs to know about fog computing and related edge computing paradigms: A complete survey2019
Graph Neural Networks: A Review of Methods and Applications2018
Cited by10
Federated Learning in Mobile Edge Networks: A Comprehensive Survey2020
Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence2020
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications2021
Edge Computing with Artificial Intelligence: A Machine Learning Perspective2022
Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree2023
FedCPF: An Efficient-Communication Federated Learning Approach for Vehicular Edge Computing in 6G Communication Networks2021
Modern computing: Vision and challenges2024
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey2026
Machine learning algorithms for manufacturing quality assurance: A systematic review of performance metrics and applications2025
Multisensory Metaverse-6G: A New Paradigm of Commerce and Education2024