Artificial Intelligence in Edge Computing and IoT Devices: A Comprehensive Survey on Distributed Intelligence

Abstract

The rapid proliferation of Internet of Things (IoT) devices has led to an exponential increase in data generated at the network edge, creating significant challenges for traditional cloud-centric computing architectures in terms of latency, bandwidth consumption, and data privacy. Edge computing has emerged as a promising paradigm that enables localized data processing closer to the data source, thereby improving real-time responsiveness and reducing network overhead. When integrated with advanced Artificial Intelligence (AI) techniques, edge computing systems can perform intelligent analytics, autonomous decision-making, and predictive processing directly at the edge of the network. This paper presents a comprehensive survey of recent advancements in AI-enabled edge computing for IoT environments. The study reviews fundamental architectures, machine learning and deep learning techniques employed for edge intelligence, and key application domains including smart cities, healthcare monitoring, industrial automation, and autonomous systems. In addition, a comparative analysis of existing research contributions is provided to highlight emerging trends and technological developments in distributed intelligence systems. The survey also identifies major research challenges such as resource constraints, model optimization, privacy preservation, and scalability in large-scale IoT deployments. Finally, potential future research directions are discussed to support the development of efficient, secure, and scalable AI-driven edge computing frameworks for next-generation intelligent IoT systems.