Machine Learning at the Network Edge: A Survey

Abstract

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However, deploying machine learning models on such end-devices is nearly impossible. A typical solution involves offloading data to external computing systems (such as cloud servers) for further processing but this worsens latency, leads to increased communication costs, and adds to privacy concerns. To address this issue, efforts have been made to place additional computing devices at the edge of the network, i.e close to the IoT devices where the data is generated. Deploying machine learning systems on such edge computing devices alleviates the above issues by allowing computations to be performed close to the data sources. This survey describes major research efforts where machine learning systems have been deployed at the edge of computer networks, focusing on the operational aspects including compression techniques, tools, frameworks, and hardware used in successful applications of intelligent edge systems.

35 pages, 4 figures; restructured text to combine ML/DL into a single section; updated tables/figures; added a new table summarizing major ML edge applications, fixed typos

References in corpus (7)

• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• Machine learning for Internet of Things data analysis: A survey
• Toward Intelligent Vehicular Networks: A Machine Learning Framework
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• A Programmable Approach to Neural Network Compression
• EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference
• Using Apple Machine Learning Algorithms to Detect and Subclassify Non-Small Cell Lung Cancer

Cited by in corpus (20)

• AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions
• Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
• Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey
• A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions
• EdgeAISim: A Toolkit for Simulation and Modelling of AI Models in Edge Computing Environments
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
• Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained Models
• Decentralized LLM Inference over Edge Networks with Energy Harvesting
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• A Multi-Modal IoT Node for Energy-Efficient Environmental Monitoring with Edge AI Processing
• Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
• Role Identification based Method for Cyberbullying Analysis in Social Edge Computing
• GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
• Improving inference time in multi-TPU systems with profiled model segmentation
• Design and implementation of intelligent packet filtering in IoT microcontroller-based devices
• Balanced segmentation of CNNs for multi-TPU inference
• David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edge
• Early Exiting Predictive Coding Neural Networks for Edge AI
• Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting