A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks
Organizations: School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing 100083, China · Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T 1Z4, Canada · Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan 215316, China · Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada ·
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.
Figures & tables
| Ref. | Year | Domain | Resource Management | Model Evolution | Security Aspects | Computing Paradigms | Applications | ||||||||||
| Task Off. | Res. Alloc. | Model Comp. | Know. Trans. | Security | Privacy | Edge | Cloud | ECC | CETC | AIoT | Manuf. | Transport. | Health | Agri. | |||
| [ 65 ] | 2019 | Edge-Cloud Systems, Application Mgmt. | ● | ● | ◐ | ◐ | ◐ | ○ | ● | ● | ◐ | ○ | ◐ | ◐ | ◐ | ◐ | ○ |
| [ 96 ] | 2019 | Network Architecture, Resource Allocation | ● | ● | ○ | ○ | ○ | ○ | ● | ◐ | ◐ | ○ | ◐ | ◐ | ◐ | ◐ | ◐ |
| [ 204 ] | 2019 | IoT, Distributed Systems | ● | ● | ○ | ◐ | ● | ● | ● | ● | ● | ◐ | ● | ◐ | ◐ | ◐ | ◐ |
| [ 18 ] | 2020 | Resource optimization, AI algorithms | ● | ● | ○ | ◐ | ○ | ○ | ● | ● | ◐ | ○ | ◐ | ◐ | ◐ | ○ | ○ |
| [ 233 ] | 2022 | Metaverse, Digital Twin | ● | ● | ○ | ○ | ○ | ◐ | ● | ◐ | ● | ○ | ◐ | ○ | ◐ | ○ | ○ |
| Acronym | Definition |
| AI | Artificial intelligence |
| AIoT | Artificial intelligence of things |
| CETCI | Cloud-edge-terminal collaborative intelligence |
| CISAIoT | Collaborative intelligence systems for AIoT |
| DDL | Distributed deep learning |
| DP | Differential privacy |
| Metric | Focus in AIoT | Key Optimization Goal |
| Response Time | Inference latency, end-to-end delay | minimize total latency ( ) via optimal offloading |
| Energy Consumption | Battery life, green computing | minimize total energy ( ) across layers |
| Resource Utilization | CPU/GPU/Bandwidth efficiency | maximize utilization ( ) without congestion |
| Quality of Service (QoS) | Reliability, throughput, availability | maintain QoS within feasible region ( ) |
| Quality of Experience | User satisfaction, perceived quality | maximize subjective satisfaction ( ) |
| Method | Key Tech. | Metrics | Limitations | CETC | TO |
| Binh et al. [ 29 ] | Reinforcement Learning (RL) | Tolerance Time | Convergence speed dependent on state space size. | ✗ | |
| ADPRL [ 47 ] | Deep RL (DRL) | Task Completion Time, Energy Consumption | High training overhead and requires extensive data. | ✗ | |
| ECIVA [ 104 ] | Heuristic Algorithm | Accuracy, Throughput | Provides sub-optimal solutions; lacks adaptability. | ✗ | |
| Sharma et al. [ 217 ] | Meta-RL | Time and Energy Consumption | Complex training process for meta-learning. | ✗ | |
| MADDPG [ 218 ] | Multi-Agent RL (MARL) | Offloading Delay, Energy Consumption | Assumes rational agents; complex coordination. | ||
| DARC-DE [ 21 ] | Differential Evolution | Total Delay, Bandwidth Utilization | Prone to converging to local optima. | ✗ |
| Method | Key Tech. | Metrics | Pros & Cons | CETC | RA |
| OTFAC [ 76 ] | Federated Learning + Actor-Critic | Delay, Energy Consumption | Adaptive and communication-efficient; complex to implement. | ✗ | |
| Fang et al. [ 69 ] | Deep Reinforcement Learning | Latency, Resource Utilization | Handles dynamic environments well; can have slow convergence. | ✗ | |
| Huang et al. [ 101 ] | DRL with Hybrid Action Space | Energy Consumption, Latency | Enables joint optimization; high training cost. | ✗ | |
| DRLS-VNE [ 285 ] | DRL | Security, Resource Utilization | Security-aware approach; state space can be very large. | ||
| SA-BPSO [ 48 ] | Hybrid Swarm Optimization | Total User Overhead | Effective heuristic; performance is sensitive to parameters. | ✗ | |
| Hua et al. [ 100 ] | Joint Optimization (Power, Scheduling) | Energy Consumption | Energy-efficient design; assumes accurate state information. | ✗ |
| Method | Key Tech. | Optimization Objectives | Pros & Cons | ECC | CETC |
| PECo [ 56 ] | Point Cloud Compression | Geometric Accuracy, Structural Compactness | Efficient for 3D data; specialized use case. | ✗ | ✗ |
| CDC [ 58 ] | Collaborative Compression | Bandwidth Efficiency, Accuracy | Reduces data transmission; requires coordination. | ✗ | |
| Hawlader et al. [ 90 ] | Knowledge Distillation | Detection Quality, Latency | Improves edge model accuracy; teacher dependent. | ✗ | |
| BPS [ 98 ] | Model Partitioning | Throughput, Latency | Balances load; sensitive to partition point. | ||
| Joshi et al. [ 108 ] | Incremental Learning + DT | Energy, Latency, Accuracy | Adapts to changes; high DT maintenance cost. | ||
| CO-PILOT [ 117 ] | Split Computing | End-to-end Latency, Accuracy | Lowers device computation; network sensitive. | ✗ |
| Method | Learning Paradigm | Metrics | Pros & Cons |
| Zhu et al. [ 299 ] | MARL | Average Age of Information | Decentralized and privacy-preserving; high communication overhead. |
| Park et al. [ 191 ] | MADRL | Quality of Service | Scalable for large agent teams; requires centralized controller. |
| DRL-CCMCO [ 45 ] | Deep RL | Execution Delay, Energy Consumption | Fast convergence and stable; sensitive to hyperparameters. |
| Gao et al. [ 77 ] | MADRL | Optimization Performance, Latency | Handles non-stationary environments; complex actor-critic design. |
| Li et al. [ 136 ] | MARL | Task Completion Latency, Energy Consumption | Simple implementation; struggles with large state spaces. |
| Coop-MADRL [ 223 ] | Cooperative MADRL | Network Utilization, Task Latency | Promotes cooperation; credit assignment is challenging. |
| Method | Scenarios | Performance Metrics | ECC | CETC |
| Yang et al. [ 266 ] | AIoT Data Prediction | Privacy and Accuracy | ✓ | ✓ |
| Rahman et al. [ 200 ] | Industry 4.0 CPS | Security, Detection Performance | ✓ | ✗ |
| Fang et al. [ 70 ] | CETC-AIoT | Computational Complexity | ✓ | ✓ |
| Chen et al. [ 42 ] | Workflow Scheduling | Execution Cost, Deadline Constraints | ✓ | ✗ |
| Wang et al. [ 247 ] | Security Inference | Privacy-Utility Tradeoff | ✓ | ✗ |
| Zhou et al. [ 295 ] | AIoT Services | QoS, Effectiveness, Efficiency | ✓ | ✗ |
| Method | Type | Scenarios | Performance Metrics | ECC | CETC |
| Raj et al. [ 201 ] | Edge MLOps | AIoT Fleet Analytics | Forecasting Accuracy | ✓ | ✗ |
| Becker et al. [ 27 ] | AIOps | Edge Computing | Resource Utilization, Detection Performance | ✗ | ✗ |
| QuAsyncFL [ 159 ] | Federated Learning | Cloud-Edge-Terminal AIoT | Communication Efficiency, Convergence | ✓ | ✓ |
| Underwood et al. [ 232 ] | Data Compression | ML/AI Training | Compression Ratio, Model Quality | ✗ | ✗ |
| Noura et al. [ 186 ] | DL-based Compression | Multimedia IoT | Visual Quality, Compression Ratio | ✓ | ✗ |
| Edge Source Coding [ 165 ] | Lossless Compression | Edge Networks | Number of Bits Needed | ✗ | ✗ |
Appendix figures & tables13 assets
Supplementary material from the paper’s appendix.
Appendix
| Method | Year | Venue | Algorithm Type | Scenarios | Metrics | Performance Results |
| TIGO [ 93 ] | 2024 | IEEE TSC | Two-stage Iterated Greedy Optimization | Cloud-Edge Collaborative Computing | Average Response Time | Better response times in less time compared to existing methods |
| DSCF [ 118 ] | 2024 | IEEE IoTJ | CMDP-based Framework | Distributed Serverless Edge Clouds | Inference Latency | Less than half the inference latency compared to local computing |
| AWSH [ 121 ] | 2024 | IEEE TMC | Hyper-Heuristic Algorithm | 5G Mobile Edge Clouds | Latency, Load Balancing | Superior performance compared to SOTA solutions |
| Lu et al. [ 166 ] | 2024 | IEEE TVT | Multi-Agent Reinforcement Learning | IoV Edge Cloud | Quality of Service | Effective performance in complex network situations |
| Nguyen et al. [ 180 ] | 2024 | IEEE TCC | Alternating Optimization | Space-Air-Ground Networks | Energy Consumption, Delay | Superior effectiveness compared to baselines |
| Qiu et al. [ 196 ] | 2024 | IEEE TMC | Online Algorithm | Edge Intelligence Cloud | Security, Reliability, Throughput | Promising performance compared to baseline algorithms |
| Application | IoT Device | Key Requirements | Edge Role |
| Smart Manufacturing | High-speed cameras, acoustic sensors, vibration sensors, robotic arms | Ultra-low latency ( 10ms), high bandwidth, high reliability, data security | Real-time inference for defect detection, predictive maintenance analytics, data filtering and aggregation, robotic control |
| Smart Transportation | LiDAR, radar, HD cameras, V2X communication units, roadside units (RSUs) | Ultra-low latency ( 5ms), extreme reliability (99.999%), high mobility support, security | Cooperative perception, sensor fusion, real-time trajectory prediction, offloading autonomous driving tasks, local traffic management |
| Smart Healthcare | Wearable sensors (ECG, SpO2), smart beds, remote monitoring devices, medical imaging equipment | Low latency, high privacy and security (HIPAA compliance), high reliability, data integrity | Real-time anomaly detection in vital signs, preprocessing of medical data, secure data aggregation, executing local alerts, FL for diagnostics |
| Smart Cities | Surveillance cameras, environmental sensors (air/water quality), smart meters, traffic sensors | Varies by application: real-time for public safety, delay-tolerant for environmental monitoring, high bandwidth for video | Real-time video analytics for surveillance, event detection (e.g., traffic incidents), data aggregation from sensors, smart grid management |
| Smart Agriculture | Soil moisture sensors, drones with multispectral cameras, weather stations, automated farm machinery | Generally delay-tolerant, low-to-medium bandwidth, long battery life for sensors, wide-area coverage | Data preprocessing from sensors, drone control and navigation, localized analytics for precision irrigation, initial pest/disease detection |
| Domain | Key IoT Devices | Key Requirements | Edge Role | Cloud Role | Primary Pattern |
| Smart Manufacturing | Industrial sensors, robots, PLCs | Ultra-low latency ( 1 ms), reliability | Real-time control, anomaly detection | Global scheduling, DT management | Edge-first closed loop |
| Smart Transportation | Cameras, LIDAR, V2X | Latency 10 ms, safety-critical | Local collision avoidance, traffic flow | Route optimization, fleet management | Edge-first closed loop |
| Smart Healthcare | Wearables, medical sensors | Privacy, regulatory compliance | Vital monitoring, local diagnosis | Longitudinal training, research aggregation | Privacy-preserving cloud aggregation |
| Smart Cities | Cameras, env. sensors, meters | Scalability, bandwidth efficiency | Real-time threat detection, local analytics | Smart grid optimization, city-wide models | Event-driven model refresh |
| Smart Agriculture | Soil sensors, drones, weather | Intermittent connectivity, bandwidth | Precision irrigation, local prediction | Yield modeling, FL aggregation | Bandwidth-aware filtering/caching |
Edge-Cloud Computing
Edge-cloud computing distributes data processing and AI workloads between nearby devices and remote cloud services to balance latency, cost, energy, and scale.
See all 70 papers