Convergence of Edge Computing and Deep Learning: A Comprehensive Survey

Abstract

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.

To be published in IEEE Communications Surveys and Tutorials

References in corpus (64)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Distilling the Knowledge in a Neural Network
• Continuous control with deep reinforcement learning
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• TensorFlow: A system for large-scale machine learning
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Mobile Edge Computing: A Survey on Architecture and Computation Offloading
• Federated Learning: Strategies for Improving Communication Efficiency
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Dueling Network Architectures for Deep Reinforcement Learning
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Graph Neural Networks: A Review of Methods and Applications
• All One Needs to Know about Fog Computing and Related Edge Computing Paradigms: A Complete Survey
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• A Survey on Mobile Edge Networks: Convergence of Computing, Caching and Communications
• Towards Federated Learning at Scale: System Design
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Compressing Neural Networks with the Hashing Trick
• Distributed Federated Learning for Ultra-Reliable Low-Latency Vehicular Communications
• Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data
• Asynchronous Federated Optimization
• Fair Resource Allocation in Federated Learning
• FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
• Big Data Caching for Networking: Moving from Cloud to Edge
• Deep Reinforcement Learning in Large Discrete Action Spaces
• NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
• Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
• Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications
• DeepCache: Principled Cache for Mobile Deep Vision
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
• Deep Learning on Graphs: A Survey
• Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
• Asynchronous Stochastic Gradient Descent with Delay Compensation
• Bandit Convex Optimization for Scalable and Dynamic IoT Management
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• A Blockchain-enabled Trustless Crowd-Intelligence Ecosystem on Mobile Edge Computing
• A Joint Learning and Communications Framework for Federated Learning over Wireless Networks
• Federated Deep Reinforcement Learning
• Embedded Binarized Neural Networks
• SparkNet: Training Deep Networks in Spark
• Model Pruning Enables Efficient Federated Learning on Edge Devices
• Federated Learning via Over-the-Air Computation
• Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks
• Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)
• Using Machine Learning for Handover Optimization in Vehicular Fog Computing
• A communication efficient distributed learning framework for smart environments
• Secure Computation Offloading in Blockchain based IoT Networks with Deep Reinforcement Learning
• Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration
• Vehicular Edge Computing via Deep Reinforcement Learning
• Deep Learning Based Caching for Self-Driving Car in Multi-access Edge Computing
• Are FPGAs Suitable for Edge Computing?
• Blockchained On-Device Federated Learning
• Diving deeper into mentee networks
• OpenEI: An Open Framework for Edge Intelligence
• Smart-Edge-CoCaCo: AI-Enabled Smart Edge with Joint Computation, Caching, and Communication in Heterogeneous IoT
• Rethinking Machine Learning Development and Deployment for Edge Devices
• Distributed Machine Learning through Heterogeneous Edge Systems
• SLSGD: Secure and Efficient Distributed On-device Machine Learning
• A Fog Robotic System for Dynamic Visual Servoing

Cited by in corpus (83)

• Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
• Social physics
• Machine Learning at the Network Edge: A Survey
• Industrial Internet of Things Intelligence Empowering Smart Manufacturing: A Literature Review
• AI and 6G into the Metaverse: Fundamentals, Challenges and Future Research Trends
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Modern Computing: Vision and Challenges
• Bringing AI To Edge: From Deep Learning's Perspective
• Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective
• Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey
• Edge Intelligence: Architectures, Challenges, and Applications
• Ground-Assisted Federated Learning in LEO Satellite Constellations
• Aerial Computing: A New Computing Paradigm, Applications, and Challenges
• Deep Learning in Automated Power Line Inspection: A Review
• A Comprehensive Survey on 6G Networks:Applications, Core Services, Enabling Technologies, and Future Challenges
• 6G: The Intelligent Network of Everything
• Applications and Techniques for Fast Machine Learning in Science
• Fast Federated Learning by Balancing Communication Trade-Offs
• Internet of Intelligence: A Survey on the Enabling Technologies, Applications, and Challenges
• A Systematic Survey of Blockchained Federated Learning
• Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
• On-Device Machine Learning: An Algorithms and Learning Theory Perspective
• Design and Prototype Implementation of a Blockchain-Enabled LoRa System With Edge Computing
• A Survey of Deep Learning for Data Caching in Edge Network
• Security-Sensitive Task Offloading in Integrated Satellite-Terrestrial Networks
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Variational Quantum Algorithms for the Allocation of Resources in a Cloud/Edge Architecture
• Split Two-Tower Model for Efficient and Privacy-Preserving Cross-device Federated Recommendation
• AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
• Comparison of edge computing methods in Internet of Things architectures for efficient estimation of indoor environmental parameters with Machine Learning
• Collaborative Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud Network
• Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs
• A Deep Transfer Learning-based Edge Computing Method for Home Health Monitoring
• An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models
• Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence
• BenchFaaS: Benchmarking Serverless Functions in an Edge Computing Network Testbed
• Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism
• Deep Reinforcement Learning for Delay-Oriented IoT Task Scheduling in Space-Air-Ground Integrated Network
• HiveMind: A Scalable and Serverless Coordination Control Platform for UAV Swarms
• Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge
• Wireless for Machine Learning
• DMRO:A Deep Meta Reinforcement Learning-based Task Offloading Framework for Edge-Cloud Computing
• Fast-Convergent Federated Learning with Adaptive Weighting
• Engineering and Experimentally Benchmarking a Serverless Edge Computing System
• Applications of Auction and Mechanism Design in Edge Computing: A Survey
• GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environment
• System Intelligence for UAV-Based Mission Critical with Challenging 5G/B5G Connectivity
• How Can Applications of Blockchain and Artificial Intelligence Improve Performance of Internet of Things? -- A Survey
• Network-Aware Optimization of Distributed Learning for Fog Computing
• Intelligent Radio Signal Processing: A Survey
• FLAGS Framework for Comparative Analysis of Federated Learning Algorithms
• Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
• Tailored Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud System
• Air Computing: A Survey on a New Generation Computation Paradigm in 6G Wireless Networks
• Optimizing AI Service Placement and Resource Allocation in Mobile Edge Intelligence Systems
• Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation
• Binarized Neural Architecture Search for Efficient Object Recognition
• Information Freshness-Aware Task Offloading in Air-Ground Integrated Edge Computing Systems
• Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation
• 6G Vision: An Ultra-Flexible Perspective
• State-of-the-art Techniques in Deep Edge Intelligence
• AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
• Optimal Status Update for Caching Enabled IoT Networks: A Dueling Deep R-Network Approach
• Offloading Artificial Intelligence Workloads across the Computing Continuum by means of Active Storage Systems
• ScissionLite: Accelerating Distributed Deep Neural Networks Using Transfer Layer
• Consensus Based Multi-Layer Perceptrons for Edge Computing
• When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network
• Capacity of Remote Classification Over Wireless Channels
• Security Analysis of Capsule Network Inference using Horizontal Collaboration
• A Distributed Framework to Orchestrate Video Analytics Applications
• Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments
• Internet of Things (IoT) Based Video Analytics: a use case of Smart Doorbell
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• Dynamic DNN Decomposition for Lossless Synergistic Inference
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design
• Cost-efficient and Skew-aware Data Scheduling for Incremental Learning in 5G Network
• Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
• On the Use of Interpretable Machine Learning for the Management of Data Quality
• Management of Resource at the Network Edge for Federated Learning