arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.05041cs.LGcs.DCcs.MA
收藏

基于Agent的交通仿真并行贝叶斯优化

Parallel Bayesian Optimization of Agent-based Transportation Simulation

Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Marain Inc.(Marain公司)

Kiran Chhatre, Sidney Feygin, Colin Sheppard, Rashid Waraich

摘要:

MATSim(Multi-Agent Transport Simulation Toolkit)是一个开源的大规模基于Agent的交通规划项目,应用于道路交通、公共交通、货运、区域疏散等领域。BEAM(Behavior,Energy,Autonomy,and Mobility)框架扩展了MATSim,使其能够对城市交通系统进行强大且可扩展的分析。BEAM模拟的代理人表现出基于多项logit模型的“模式选择”行为。在我们的研究中,我们考虑了八种模式的选择,即自行车,汽车,步行,乘坐冰雹,驾驶运输,步行运输,乘坐冰雹运输和乘坐冰雹池。每个模式选择的“替代特定常数”是与实验中的特定场景相关的配置文件中的关键超参数。我们使用'Urbansim-10 k' BEAM场景(10,000人口规模)进行所有实验。由于这些超参数以复杂的方式影响模拟,手动校准方法非常耗时。我们提出了一个并行贝叶斯优化方法与早期停止规则,以实现快速收敛到其最优配置给定的多输入多输出问题。我们的模型是基于一个开源的HpBandSter包。这种方法结合了几个一维核密度估计器(KDE)的层次结构和一个廉价的评估器(Hyperband,一个单一的多维KDE)。我们的模型还结合了基于外推的早期停止规则。使用我们的模型,我们可以以完全自主的方式实现大规模BEAM模拟的25% L1范数。据我们所知,我们的工作是第一次应用于大规模多智能体交通模拟。这项工作可以是有用的替代建模的情况下,非常大的人口。

英文摘要:

MATSim (Multi-Agent Transport Simulation Toolkit) is an open source large-scale agent-based transportation planning project applied to various areas like road transport, public transport, freight transport, regional evacuation, etc. BEAM (Behavior, Energy, Autonomy, and Mobility) framework extends MATSim to enable powerful and scalable analysis of urban transportation systems. The agents from the BEAM simulation exhibit 'mode choice' behavior based on multinomial logit model. In our study, we consider eight mode choices viz. bike, car, walk, ride hail, driving to transit, walking to transit, ride hail to transit, and ride hail pooling. The 'alternative specific constants' for each mode choice are critical hyperparameters in a configuration file related to a particular scenario under experimentation. We use the 'Urbansim-10k' BEAM scenario (with 10,000 population size) for all our experiments. Since these hyperparameters affect the simulation in complex ways, manual calibration methods are time consuming. We present a parallel Bayesian optimization method with early stopping rule to achieve fast convergence for the given multi-in-multi-out problem to its optimal configurations. Our model is based on an open source HpBandSter package. This approach combines hierarchy of several 1D Kernel Density Estimators (KDE) with a cheap evaluator (Hyperband, a single multidimensional KDE). Our model has also incorporated extrapolation based early stopping rule. With our model, we could achieve a 25% L1 norm for a large-scale BEAM simulation in fully autonomous manner. To the best of our knowledge, our work is the first of its kind applied to large-scale multi-agent transportation simulations. This work can be useful for surrogate modeling of scenarios with very large populations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑