Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence

Abstract

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, 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 paper, 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 paper provides insights into this new inter-disciplinary field from a broader perspective. It discusses the core concepts and the research road-map, which should provide the necessary background for potential future research initiatives in Edge Intelligence.

13 pages, 3 figures

References in corpus (27)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• A Brief Survey of Deep Reinforcement Learning
• Federated Learning: Strategies for Improving Communication Efficiency
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• UAV Communications for 5G and Beyond: Recent Advances and Future Trends
• Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks
• Fog Computing based Radio Access Networks: Issues and Challenges
• Practical Secure Aggregation for Federated Learning on User-Held Data
• GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent
• Over-the-air Function Computation in Sensor Networks
• Towards an Intelligent Edge: Wireless Communication Meets Machine Learning
• Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy
• Federated Learning via Over-the-Air Computation
• Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues
• Gossip training for deep learning
• Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
• Run-Time Efficient RNN Compression for Inference on Edge Devices
• Vehicular Edge Computing via Deep Reinforcement Learning
• Adaptive Precision CNN Accelerator Using Radix-X Parallel Connected Memristor Crossbars
• Diving deeper into mentee networks
• OpenEI: An Open Framework for Edge Intelligence
• A Graph Neural Network Approach for Scalable Wireless Power Control
• Cache-Aided NOMA Mobile Edge Computing: A Reinforcement Learning Approach
• Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge
• Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge
• Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing
• Toward Runtime-Throttleable Neural Networks

Cited by in corpus (47)

• 6G Internet of Things: A Comprehensive Survey
• AI for Next Generation Computing: Emerging Trends and Future Directions
• Social physics
• SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead
• AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
• Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review
• IoT-based Route Recommendation for an Intelligent Waste Management System
• Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems
• Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multi-Agent DRL Approach
• A Survey on Collaborative DNN Inference for Edge Intelligence
• 6G: The Intelligent Network of Everything
• Continual Learning and Catastrophic Forgetting
• Time-sensitive Learning for Heterogeneous Federated Edge Intelligence
• E-Tree Learning: A Novel Decentralized Model Learning Framework for Edge AI
• Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
• Communication-Efficient Edge AI: Algorithms and Systems
• Model Pruning Based on Quantified Similarity of Feature Maps
• Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs
• Towards Energy Consumption and Carbon Footprint Testing for AI-driven IoT Services
• Edge Devices Inference Performance Comparison
• Wireless for Machine Learning
• Air-Ground Collaborative Mobile Edge Computing: Architecture, Challenges, and Opportunities
• Distributed Redundant Placement for Microservice-based Applications at the Edge
• Tactical Edge IoT in Defense and National Security
• MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure
• Cyber-Physical Systems Security: A Comprehensive Review of Anomaly Detection Techniques
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• Internet of Things (IoT) Connectivity in 6G: An Interplay of Time, Space, Intelligence, and Value
• State-of-the-art Techniques in Deep Edge Intelligence
• The AutoSPADA Platform: User-Friendly Edge Computing for Distributed Learning and Data Analytics in Connected Vehicles
• VEC-Sim: A Simulation Platform for Evaluating Service Caching and Computation Offloading Policies in Vehicular Edge Networks
• An Agentic Framework for Rapid Deployment of Edge AI Solutions in Industry 5.0
• DPoS: Decentralized, Privacy-Preserving, and Low-Complexity Online Slicing for Multi-Tenant Networks
• On Hardware-Aware Design and Optimization of Edge Intelligence
• Offloading Artificial Intelligence Workloads across the Computing Continuum by means of Active Storage Systems
• Ultra-low power on-chip learning of speech commands with phase-change memories
• Rethinking Timing Residuals: Advancing PET Detectors with Explicit TOF Corrections
• A 1-D CNN inference engine for constrained platforms
• Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees
• Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing
• LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy
• Adaptive In-network Collaborative Caching for Enhanced Ensemble Deep Learning at Edge
• Robust error bounds for quantised and pruned neural networks
• Edge Intelligence in Civil Aviation: Paradigms, Techniques, and Applications
• Enabling Edge Cloud Intelligence for Activity Learning in Smart Home