arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.04571eess.SYcs.SY
收藏

实时预测控制策略优化

Real-Time Predictive Control Strategy Optimization

Samarth Gupta, Ravi Seshadri, Bilge Atasoy, A. Arun Prakash, Francisco Pereira, Gary Tan, Moshe Ben-Akiva

AI总结:

本文提出一种结合实时控制策略优化与预测网络状态引导的框架,通过可扩展遗传算法求解动态通行费优化问题,在新加坡路网实验中使出行时间最高减少9%且满足实时计算要求。

摘要:

交通拥堵促使人们日益重视管理措施,以更高效地利用现有基础设施。在此背景下,本文提出了一种新颖的框架,将控制策略(通行费、匝道调节率等)的实时优化与使用预测网络状态为Dynamic Traffic Assignment系统生成引导相结合。通过一个固定需求动态通行费优化问题证明了该框架的有效性,该问题被表述为非线性规划,以最小化预测网络出行时间。应用一种利用并行计算的可扩展高效遗传算法来求解此问题。在Singapore的大规模道路网络上采用闭环方法进行实验,以研究所提方法的性能。结果表明,网络范围内的出行时间显著改善了高达9%,并具备实时计算性能。

英文摘要:

Traffic congestion has lead to an increasing emphasis on management measures for a more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with guidance generation using predicted network states for Dynamic Traffic Assignment systems. The efficacy of the framework is demonstrated through a fixed demand dynamic toll optimization problem which is formulated as a non-linear program to minimize predicted network travel times. A scalable efficient genetic algorithm is applied to solve this problem that exploits parallel computing. Experiments using a closed-loop approach are conducted on a large scale road network in Singapore to investigate the performance of the proposed methodology. The results indicate significant improvements in network wide travel time of up to 9% with real-time computational performance.

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。

↑