A GPU-accelerated Large-scale Simulator for Transportation System Optimization Benchmarking

TL;DR

This paper introduces a GPU-accelerated microscopic traffic simulator capable of large-scale transportation system optimization, significantly improving computational efficiency and supporting diverse optimization scenarios with open-source tools and benchmarking.

Contribution

It presents the first open-source GPU-accelerated large-scale traffic simulator supporting extensive optimization scenarios and benchmarking, enabling more realistic and efficient transportation system analysis.

Findings

Achieves 88.92x speedup over CityFlow in large-scale scenarios.

Supports multiple transportation optimization algorithms and scenarios.

Provides an accessible platform for no-code traffic system trials.

Abstract

With the development of artificial intelligence techniques, transportation system optimization is evolving from traditional methods relying on expert experience to simulation and learning-based decision and optimization methods. Learning-based optimization methods require extensive interactions with highly realistic microscopic traffic simulators. However, existing microscopic traffic simulators are inefficient in large-scale scenarios and thus fail to support the adoption of these methods in large-scale transportation system optimization scenarios. In addition, the optimization scenarios supported by existing simulators are limited, mainly focusing on the traffic signal control. To address these challenges, we propose the first open-source GPU-accelerated large-scale microscopic simulator for transportation system simulation and optimization. The simulator can iterate at 84.09Hz, which achieves 88.92 times computational acceleration in the large-scale scenario with 2,464,950 vehicles compared to the best baseline CityFlow. Besides, it achieves a more realistic average road speeds simulated on real datasets by adopting the IDM model as the car-following model and the randomized MOBIL model as the lane-changing model. Based on it, we implement a set of microscopic and macroscopic controllable objects and metrics provided by Python API to support typical transportation system optimization scenarios. We choose five representative scenarios and benchmark classical rule-based algorithms, reinforcement learning algorithms, and black-box optimization algorithms in four cities. These experiments effectively demonstrate the usability of the simulator for large-scale traffic system optimization. The code of the simulator is available at https://github.com/tsinghua-fib-lab/moss. We build an open-registration web platform available at https://moss.fiblab.net to support no-code trials.