Load Balancing in the Internet of Vehicles: A Comprehensive Review of SDN and Machine Learning Approaches

Abstract

Efficient load balancing (LB) is crucial for optimizing network performance in Wireless Sensor Networks (WSN), the Internet of Things (IoT), and Unmanned Aerial Vehicles (UAV), as well as the emerging Internet of Vehicles (IoV). In this paper, we study various LB techniques across these domains, including Software-Defined Networking (SDN) and Machine Learning (ML)-based approaches. SDN enables centralized control and real-time adaptability, while ML enhances decision-making through predictive analytics. Given the limited research on IoV, we leverage insights from WSN, IoT, and UAVs to propose an innovative technique that integrates SDN with ML for intelligent, adaptive LB in IoV. This approach promises to optimize network performance, reduce latency, and improve fault tolerance, offering a new research direction in vehicular networks.