Dynamic scheduling method of computing resources in Internet of Vehicles based on an improved NSGAII algorithm

The Internet of Vehicles (IoV) represents a critical component of modern mobile edge computing systems. IoV computing resources encompass backend cloud resources, roadside edge nodes, and vehicle-mounted units. Traditional static scheduling methods struggle to meet the real-time performance and resource utilization demands imposed by the IoV's dynamic and heterogeneous environment. This study introduces a dynamic scheduling approach for IoV computing resources leveraging an enhanced Non-dominated Sorting Genetic Algorithm II (NSGA-II) to address multi-objective optimization challenges in resource allocation. First, the study develops a multi-objective optimization model that integrates key performance metrics, including task delay, energy consumption, and resource utilization. Subsequently, an improved NSGA-II framework incorporating adaptive encoding, selection, crossover, and mutation strategies is formulated to enhance the algorithm's global optimization capabilities in dynamic IoV scenarios. Experimental results demonstrate that the proposed method outperforms traditional approaches in multi-objective optimization efficacy, convergence rate, and algorithmic stability, offering an efficient solution for managing IoV computing resources.