Impacts of Heterogeneous Traffic Environments on Vehicle-Infrastructure Collaborative Computing Latency: A Multi-Layer Agent-Based Simulation Approach

Abstract

Achieving efficient task offloading with low latency in cooperative vehicle-infrastructure systems represents a critical challenge influenced by three key factors: heterogeneous vehicle computational capabilities, dynamic traffic conditions, and variable communication reliability. To address the fundamental trade-off between real-time processing performance and cost-effective infrastructure investment, this study develops a multi-layer agent-based modeling (ABM) framework that systematically evaluates how roadside unit (RSU) computation capacity, traffic volume, and vehicular computation capability (VCC) heterogeneity collectively impact collaborative computing latency. The ABM framework comprises three interconnected layers: an infrastructure layer that models RSUs with sensing, communication, and computing functions; a traffic layer that simulates diverse traffic environments; and a collaborative computing layer that manages decentralized task generation and offloading. A modified water-filling algorithm is integrated to dynamically allocate computational tasks based on available resources and latency constraints. Simulation results under signalized intersection scenarios reveal nonlinear latency growth with increasing traffic volume due to queuing effects. When the RSU computing capacity is insufficient, most tasks are offloaded to nearby vehicles. Our results show that when the RSU computational capacity is comparable to the total VCC of all vehicles, the RSU processes approximately 40% of the tasks, primarily due to vehicle–RSU mobility effects and stochastic wireless transmission failures. Furthermore, increasing VCC heterogeneity—while keeping the average constant—leads to both higher average latency and greater variability. These findings provide quantitative insights for optimizing computing resource deployment in real-world cooperative systems.