The Interaction of Macroscopic Optimization and Microscopic Traffic Flow With Communication Uncertainty in Intelligent Vehicle Cyber-Physical System

This study addresses the challenge of bridging macroscopic optimization and microscopic driving behavior under communication uncertainty in Intelligent Vehicle Cyber-Physical Systems (IVCPS). A multi-objective macroscopic optimization model is first developed to generate recommended speeds, with different evolutionary algorithms systematically compared. Through experiments with Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Real-Coded Genetic Algorithm (RCGA), RCGA is identified as the most effective solver. The recommended speeds are subsequently integrated into the microscopic layer, where a modified Intelligent Driver Model (IDM) accounts for both multi-preceding vehicle interactions and macroscopic guidance. Communication uncertainty in the transmission process is modeled and quantified using soft set theory, enabling robust adaptation of vehicle behaviors. Simulation results under both ideal and uncertain communication conditions demonstrate that: (i) the proposed framework consistently outperforms the baseline IDM and the conventional IDM with recommended speeds, validating its effectiveness; (ii) variations in optimization weights significantly influence the performance of the modified IDM; and (iii) the modified IDM achieves superior traffic efficiency and fuel economy across different traffic demand scenarios. Overall, the findings highlight the necessity of incorporating uncertainty-aware speed guidance to effectively link macroscopic optimization with microscopic control, offering new insights into building resilient and efficient intelligent transportation systems.