A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks
2025/08/26 by Wu, Jiaqi, Liu, Jing, Liu, Yang +6
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI)
paper · doi:10.48550/arxiv.2508.18803
Abstract
The proliferation of Internet of things (IoT) devices in smart cities, transportation, healthcare, and industrial applications, coupled with the explosive growth of AI-driven services, has increased demands for efficient distributed computing architectures and networks, driving cloud-edge-terminal collaborative intelligence (CETCI) as a fundamental paradigm within the artificial intelligence of things (AIoT) community. With advancements in deep learning, large language models (LLMs), and edge computing, CETCI has made significant progress with emerging AIoT applications, moving beyond isolated layer optimization to deployable collaborative intelligence systems for AIoT (CISAIOT), a practical research focus in AI, distributed computing, and communications. This survey describes foundational architectures, enabling technologies, and scenarios of CETCI paradigms, offering a tutorial-style review for CISAIOT beginners. We systematically analyze architectural components spanning cloud, edge, and terminal layers, examining core technologies including network virtualization, container orchestration, and software-defined networking, while presenting categorizations of collaboration paradigms that cover task offloading, resource allocation, and optimization across heterogeneous infrastructures. Furthermore, we explain intelligent collaboration learning frameworks by reviewing advances in federated learning, distributed deep learning, edge-cloud model evolution, and reinforcement learning-based methods. Finally, we discuss challenges (e.g., scalability, heterogeneity, interoperability) and future trends (e.g., 6G+, agents, quantum computing, digital twin), highlighting how integration of distributed computing and communication can address open issues and guide development of robust, efficient, and secure collaborative AIoT systems.
Citations
- Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
- Mobile Edge Intelligence for Large Language Models: A Contemporary Survey
- Cloud-Edge-Terminal Collaborative AIGC for Autonomous Driving
- VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework
- Quantum-Edge Cloud Computing: A Future Paradigm for IoT Applications
- Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories
- Quantum Cloud Computing: A Review, Open Problems, and Future Directions
- Cybersecurity in the Quantum Era: Assessing the Impact of Quantum Computing on Infrastructure
- Data-Driven Online Resource Allocation for User Experience Improvement in Mobile Edge Clouds
- Continual Learning for Smart City: A Survey
- Understanding The Effectiveness of Lossy Compression in Machine Learning Training Sets
- Cached Model-as-a-Resource: Provisioning Large Language Model Agents for Edge Intelligence in Space-air-ground Integrated Networks
- Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
- The Fusion of Deep Reinforcement Learning and Edge Computing for Real-time Monitoring and Control Optimization in IoT Environments
- Computation Rate Maximization for Wireless Powered Edge Computing With Multi-User Cooperation
- When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment
- Quantum Leak: Timing Side-Channel Attacks on Cloud-Based Quantum Services
- Joint Offloading and Resource Allocation for Hybrid Cloud and Edge Computing in SAGINs: A Decision Assisted Hybrid Action Space Deep Reinforcement Learning Approach
- Joint Offloading and Resource Allocation for Hybrid Cloud and Edge Computing in SAGINs: A Decision Assisted Hybrid Action Space Deep Reinforcement Learning Approach
- Hybrid Edge-Cloud Collaborator Resource Scheduling Approach Based on Deep Reinforcement Learning and Multiobjective Optimization
- Privacy-Preserving Data in IoT-based Cloud Systems: A Comprehensive Survey with AI Integration
- Cloud-Device Collaborative Learning for Multimodal Large Language Models
- Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
- ADROIT6G DAI-driven Open and Programmable Architecture for 6G Networks
- Equilibrium in the Computing Continuum through Active Inference
- Artificial Intelligence in Sustainable Vertical Farming
- VegaEdge: Edge AI Confluence Anomaly Detection for Real-Time Highway IoT-Applications
- An Exploration on Integrated Sensing and Communication for the Future Smart Internet of Things
- Digital Twin-Empowered Smart Attack Detection System for 6G Edge of Things Networks
- The Power of Internet of Things (IoT): Connecting the Dots with Cloud, Edge, and Fog Computing
- Security assessment of common open source MQTT brokers and clients
- Satellite-MEC Integration for 6G Internet of Things: Minimal Structures, Advances, and Prospects
- Arena: A Learning-based Synchronization Scheme for Hierarchical Federated Learning--Technical Report
- Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization
- Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous Driving
- Autonomous Choreography of WebAssembly Workloads in the Federated Cloud-Edge-IoT Continuum
- Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learning
- Joint Latency-Energy Minimization for Fog-Assisted Wireless IoT Networks
- Learning-based Two-tiered Online Optimization of Region-wide Datacenter Resource Allocation
- Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels
- Recent applications of machine learning, remote sensing, and iot approaches in yield prediction: a critical review
- A Layered Architecture Enabling Metaverse Applications in Smart Manufacturing Environments
- Engineering and Experimentally Benchmarking Open Source MQTT Broker Implementations
- PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information
- Can we Quantify Trust? Towards a Trust-based Resilient SIoT Network
- Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach
- Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services
- Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study
- Quality of Service (QoS)-driven Edge Computing and Smart Hospitals: A Vision, Architectural Elements, and Future Directions
- SDN-AAA: Towards the standard management of AAA infrastructures
- Extensions for Shared Resource Orchestration in Kubernetes to Support RT-Cloud Containers
- Coordinated Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Swarms in Autonomous Mobile Access Applications
- Scalable Hybrid Learning Techniques for Scientific Data Compression
- Privacy-preserving Security Inference Towards Cloud-Edge Collaborative Using Differential Privacy
- Corn Yield Prediction based on Remotely Sensed Variables Using Variational Autoencoder and Multiple Instance Regression
- Pushing AI to Wireless Network Edge: An Overview on Integrated Sensing, Communication, and Computation towards 6G
- Edge, Fog, and Cloud Computing : An Overview on Challenges and Applications
- Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals
- Near Lossless Time Series Data Compression Methods using Statistics and Deviation
- AI Augmented Edge and Fog Computing: Trends and Challenges
- Verifiable Encodings for Secure Homomorphic Analytics
- AutoDiCE: Fully Automated Distributed CNN Inference at the Edge
- A Decentralized Framework with Dynamic and Event-Driven Container Orchestration at the Edge
- TRUST XAI: Model-Agnostic Explanations for AI With a Case Study on IIoT Security
- A Conceptual Trust Management Framework under Uncertainty for Smart Vehicular Networks
- Enabling All In-Edge Deep Learning: A Literature Review
- Privacy-preserving Anomaly Detection in Cloud Manufacturing via Federated Transformer
- SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT
- Container Orchestration in Edge and Fog Computing Environments for Real-Time IoT Applications
- A Survey on Scheduling Techniques in the Edge Cloud: Issues, Challenges and Future Directions
- Securing the data in cloud using Algebra Homomorphic Encryption scheme based on updated Elgamal(AHEE)
- Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors
- SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
- Integration of FogBus2 Framework with Container Orchestration Tools in Cloud and Edge Computing Environments
- REMR: A Reliability Evaluation Method for Dynamic Edge Computing Network under Time Constraints
- MSCET: A Multi-Scenario Offloading Schedule for Biomedical Data Processing and Analysis in Cloud-Edge-Terminal Collaborative Vehicular Networks
- Hierarchical Federated Learning based Anomaly Detection using Digital Twins for Smart Healthcare
- Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
- At the Edge of a Seamless Cloud Experience
- Blockchain for Edge of Things: Applications, Opportunities, and Challenges
- Accelerating Encrypted Computing on Intel GPUs
- Stand-alone device for IoT applications
- IGrow: A Smart Agriculture Solution to Autonomous Greenhouse Control
- Caching and Computation Offloading in High Altitude Platform Station (HAPS) Assisted Intelligent Transportation Systems
- Machine Learning-based Orchestration of Containers: A Taxonomy and Future Directions
- ECO: Edge-Cloud Optimization of 5G applications
- The Hidden cost of the Edge: A Performance Comparison of Edge and Cloud Latencies
- A Network-based Compute Reuse Architecture for IoT Applications
- Pilot-Edge: Distributed Resource Management Along the Edge-to-Cloud Continuum
- Exploring Task Placement for Edge-to-Cloud Applications using Emulation
- A Deep Learning Scheme for Efficient Multimedia IoT Data Compression
- Edge Intelligence for Empowering IoT-based Healthcare Systems
- AVEC: Accelerator Virtualization in Cloud-Edge Computing for Deep Learning Libraries
- Resource Provisioning in Edge Computing for Latency Sensitive Applications
- Reliable Fleet Analytics for Edge IoT Solutions
- Optimizing IoT and Web Traffic Using Selective Edge Compression
- FLEAM: A Federated Learning Empowered Architecture to Mitigate DDoS in Industrial IoT
- Virtual Network Function Placement in Satellite Edge Computing with a Potential Game Approach
- Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
- Network Traffic Control for Multi-homed End-hosts via SDN
- Cloud Fog Architectures in 6G Networks
- A Survey on Security and Privacy Issues in Edge Computing-Assisted\n Internet of Things
- Self-healing Dilemmas in Distributed Systems: Fault Correction vs. Fault Tolerance
- Improving Software Defined Cognitive and Secure Networking
- Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
- CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning
- Software-Defined Elastic Provisioning of IoT Edge Computing Virtual Resources
- HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing
- Detecting DDoS Attack on SDN Due to Vulnerabilities in OpenFlow
- Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
- Industrial Internet of Things (IIoT) Applications of Edge and Fog Computing: A Review and Future Directions
- IDEALEM: Statistical Similarity Based Data Reduction
- Collaborative Homomorphic Computation on Data Encrypted under Multiple Keys
- Resource Allocation Using Gradient Boosting Aided Deep Q-Network for IoT in C-RANs
- Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges
- A View on Edge caching Applications
- Blockchain Methods for Trusted Avionics Systems
- User Preference Aware Lossless Data Compression at the Edge
- Decentralized Smart Surveillance through Microservices Platform
- Smart-Edge-CoCaCo: AI-Enabled Smart Edge with Joint Computation, Caching, and Communication in Heterogeneous IoT
- PI-Edge: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services
- Learning and Management for Internet-of-Things: Accounting for Adaptivity and Scalability
- MQTT+: Enhanced Syntax and Broker Functionalities for Data Filtering, Processing and Aggregation
- NetO-App: A Network Orchestration Application for Centralized Network Management in Small Business Networks
- Container-based Cluster Orchestration Systems: A Taxonomy and Future\n Directions
- Container‐based cluster orchestration systems: A taxonomy and future directions
- ThingPot: an interactive Internet-of-Things honeypot
- EdgeChain: An Edge-IoT Framework and Prototype Based on Blockchain and Smart Contracts
- WSN and Fog Computing Integration for Intelligent Data Processing
- A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving
Related