AI / ML techniques for enhancing IoT -based communication

Official URL: https://dx.doi.org/10.1002/9781394337262.ch02

The integration of artificial intelligence (AI) and machine learning (ML) into Internet of Things (IoT) communication systems is reshaping the way devices interact, adapt, and manage data-intensive environments. This chapter presents a comprehensive review of AI/ML techniques applied to optimize IoT-based communication, covering intelligent routing, congestion control, resource allocation, and spectrum management. It further explores architectural paradigms such as edge and fog computing, AI-driven software-defined networking and network function virtualization, as well as federated vs. centralized learning models. Through comparative analyses, we highlight the benefits of these intelligent systems in reducing latency, improving energy efficiency, and enabling context-aware network behavior. Key challenges – ranging from computational constraints and data privacy to model explainability and real-time scalability – are also discussed, along with open issues and future research directions. The findings of this chapter could enable as a roadmap for researchers and practitioners aiming to build intelligent, scalable, and resilient IoT communication infrastructures.