| 要約: | Traffic simulations play a crucial role in urban planning and mobility management by providing insights into transportation systems. However, their effectiveness heavily depends on accurate demand calibration, often requiring large amounts of observational data. This poses a challenge in settings with limited data availability. In this paper, we propose a methodology for calibrating SUMO scenarios under data-scarce conditions. To contextualize our approach, we first review existing SUMO scenarios and their demand calibration strategies. We then introduce the Mannheim SUMO Traffic Model (MaST) as a case study and employ the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to optimize route probabilities as input for the existing routeSampler tool provided by SUMO. Results indicate that our method significantly improves calibration accuracy compared to baseline approaches both for 3-hour and 24-hour scenarios. While our findings suggest that the proposed methodology can support demand calibration in data-limited environments, further research is needed to assess its generalizability and effectiveness in different contexts.
|
|---|
