A dynamic holding strategy in public transit systems with real-time information

作者：Yu Bin^*; Yang Zhongzhen

来源：Applied Intelligence, 2009, 31(1): 69-80.

DOI：10.1007/s10489-007-0112-9

• Dynamic holding strategy
• SVM
• Forecasting
• Genetic algorithm

Holding strategies are among the most commonly used operation control strategies in transit systems. In this paper, a dynamic holding strategy is developed, which consists of two major steps: (1) judging whether an early bus should be held, and (2) optimizing the holding times of the held bus. A model based on support vector machine (SVM), which contains four input variables (time-of-day, segment, the latest speed on the next segment, and the bus speed on the current segment) for forecasting the early bus departure times from the next stop is also developed. Then, in order to determine the optimal holding times, a model aiming to minimize the user costs is constructed and a genetic algorithm is used to optimize the holding times. Finally, the dynamic holding strategy proposed in this study is illustrated with the microscopic simulation model Paramics and some conclusions are drawn.

• 出版日期2009-8
• 单位大连海事大学