Process-Oriented Modeling and Performance Optimization of Intelligent Traffic Systems Using Stochastic Petri Nets

To address the dynamic characteristics of data collection, risk assessment, and response execution in intelligent traffic warning systems, this study proposes a modeling and performance analysis framework based on Stochastic Petri Nets (SPN). An SPN model of the warning-information evolution process is constructed and transformed into a continuous-time Markov chain (CTMC), for which the steady-state probability equations are derived to quantify system performance. The transition rates in the model are assigned according to national technical specifications and practical operational scenarios. A sensitivity analysis is conducted on several key rates (λ2, λ3, λ9, λ10, λ11, λ12) to examine their influence on the steady-state distribution. The simulation results indicate that increasing λ2 (data-cleaning rate) improves processing efficiency in the data-fusion stage, while insufficient values of λ10 or λ11 may lead to system congestion or delayed responses. To further evaluate system behavior, performance indicators such as the average number of tokens and transition utilization are introduced to assess resource occupancy and process activation frequency. These measures help identify potential bottlenecks and guide targeted optimization. The findings demonstrate that appropriate adjustment of critical transition rates can enhance operational efficiency and warning accuracy, providing theoretical support and practical insights for the modeling, optimization, and resource allocation of intelligent traffic systems.