基于代理模型辅助NSGA-Ⅱ算法的地铁接驳公交优化

Optimization of Metro Feeder Bus Routes Based on Surrogate-Assisted NSGA-ⅡAlgorithm

城市轨道交通与地面公交之间的便利衔接是满足居民多元化出行需求,促进城市公共交通系统发展的关键。现有研究在建立公交线路优化模型时缺少对一些重要微观指标的考虑,例如高峰期需等待多班公交的比例和车内拥挤度等。同时对线路运营中随机性和异质性要求的考虑也存在不足,导致其在实际应用中表现欠佳。为解决上述问题,该文从公交的服务过程出发,以乘客出行成本与企业成本最小化为目标,建立考虑运行速度、车辆类型、发车频率、线路票价、车辆拥挤程度、线路线型等影响因素的优化模型,使用非支配排序遗传算法(NSGA-Ⅱ)进行模型求解,并针对遗传操作部分进行改进。同时为提高求解精度,设计了一种微观仿真算法对解进行评估。在此基础上,采用Kriging代理模型进行辅助计算以提高算法求解效率。最后,以深圳市地铁公交接驳为例,采集地铁与公交IC卡刷卡数据,对提出的算法进行验证。同时,进一步对线路票价、运行速度、运营车型以及客流大小等因素进行了灵敏度分析,依据分析结果提出了运营线路的改善建议。结果表明,该算法相较于传统NSGA-Ⅱ算法能在相同的求解时间下得到更好的线路优化方案,方案平均节省约35.49%的总成本,且迭代速度提高26.94%。由此可见,该文提出的地铁接驳公交优化方法对提升接驳效率与运营水平均具有实际意义。

The connection between urban rail transit and bus transit is the key to meet the various urban travel demand and to promote the development of urban public transportation system.Existing studies lack the consideration of some important micro-indicators,such as the ratio of waiting for multiple buses during peak hours and the level of congestion inside the bus,when constructing the optimization model.Additionally,there is a lack of consideration for the stochastic and heterogeneous requirements in route operation,which results in poor performance in practical applications.To address these issues,this study firstly established an optimization model based on the service process of the bus transit,with the objective of minimizing the travel cost of passengers and the cost of enterprises.The model considers the influencing factors such as operating speed,vehicle type,departure frequency,route fare,vehicle crowdedness,and route line type and it is solved by the non-dominated sorting genetic algorithm(NSGA-Ⅱ),in which the genetic operation part is improved.Furthermore,a microscopic simulation algorithm was designed to evaluate the solution in order to improve the accuracy of the model solution.Accordingly,a Kriging surrogate model was used to assist the calculation to improve the solution efficiency of the algorithm.Finally,taking the connection between metro and bus system in Shenzhen city as an example,the proposed algorithm was validated with the IC card data collected in metro and bus system.The sensitivity analysis was conducted for the factors of route fare,operating speed,operating mode and passenger volume,and the operating improvement was proposed based on the analysis results.The results demonstrate that the algorithm produces superior route solutions compared to the conventional NSGA-Ⅱ,with the same solving time.There is a 35.49%reduction in total cost and a notable 26.94%increase in the iteration speed.The optimization method for connecting between metro and bus transit proposed in this study has practical significance in improving connecting efficiency and operational level.