Vehicular Cloud Computing for Enhanced Data Management in Intelligent Transportation

The research describes a Vehicular Cloud Computing (VCC)-based technique for improving data management in Intelligent Transportation Systems (ITS). Traditional ITS has a centralized design with semi-static sensors, which limits scalability, real-time processing, and adaptability. A VCC system is proposed as a decentralized communication system that can directly access vehicle communication technologies such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication modules, allowing for the real-time sharing of both vehicular and road-side infrastructure information, as well as edge computing for latency-sensitive applications, resulting in significant improvements in traffic flow and transportation resource allocation. The proposed system uses machine learning (ML) to estimate traffic and dynamically allocate resources, thereby boosting both scalability and road safety. The simulation results show that the proposed system outperforms existing systems in terms of latency (42-44% reduction), congestion (28-33% reduction), and throughput (25-44% increase). The result assesses the proposed system's capability for addressing traffic challenges, resulting in an appropriate solution for the urban transportation system.