具有反向学习能力的串车调度算法研究
|
摘要
为了避免串车问题,研究了多条线路不同站点间隔的车辆实时串车调度算法.基于车辆自动定位(AVL)数据的分析预测,给出了具备反向学习能力的克隆选择优化算法(Opposition-learning Clonal Selection Algorithm, OCSA)求解避免串车的调度序列,指导车辆调度.算法中设计了反向抗体库,反向抗体库存储了种群迭代过程中多个较差抗体的信息,利用较差基因位置信息,指导部分基因链以较快速度进行反向学习,将其迅速牵引出局部最优区域.反向学习过程可迅速改善抗体的多样性,使得算法在短时间内具有较强的全局寻优能力;且局部学习的缩放因子可随迭代过程动态调整,提高了算法的求解精度.实验结果表明,基于OCSA算法获取的调度序列与经典的调度算法相比有较好的适应性,求得的调度序列能够实时有效地降低站点串车问题.
In order to avoid the tandem traffic problem, a real-time vehicle tandem scheduling algorithm with different station intervals on multiple routes is studied. Based on the data analysis and prediction of AVL data, an Opposition-learning Clonal Selection Algorithm(OCSA) with opposition-learning ability is proposed,the scheduling sequence is used to avoiding tandem traffic and guide vehicle scheduling. In the algorithm, a reverse antibody library is designed, which stores the information of several inferior antibodies during the population iteration. The location information of the inferior genes is used to guide the reverse learning, in order to pull them out of the local optimal region quickly. The opposition-learning process can rapidly improve the diversity of antibodies, so that the algorithm has a strong global optimization ability in a short time, and the scaling factor of local learning can be dynamically adjusted with the iterative process to improve the accuracy of the algorithm. The experimental results show that the scheduling sequence obtained by OCSA algorithm has better adaptability than the classical scheduling algorithm, and the scheduling sequence obtained by OCSA algorithm can effectively reduce the tandem traffic problem in real-time.
In order to avoid the tandem traffic problem, a real-time vehicle tandem scheduling algorithm with different station intervals on multiple routes is studied. Based on the data analysis and prediction of AVL data, an Opposition-learning Clonal Selection Algorithm(OCSA) with opposition-learning ability is proposed,the scheduling sequence is used to avoiding tandem traffic and guide vehicle scheduling. In the algorithm, a reverse antibody library is designed, which stores the information of several inferior antibodies during the population iteration. The location information of the inferior genes is used to guide the reverse learning, in order to pull them out of the local optimal region quickly. The opposition-learning process can rapidly improve the diversity of antibodies, so that the algorithm has a strong global optimization ability in a short time, and the scaling factor of local learning can be dynamically adjusted with the iterative process to improve the accuracy of the algorithm. The experimental results show that the scheduling sequence obtained by OCSA algorithm has better adaptability than the classical scheduling algorithm, and the scheduling sequence obtained by OCSA algorithm can effectively reduce the tandem traffic problem in real-time.
引文
[1] MAZLOUMI E, CURRIE G, ROSE G. Using GPS data to gain insight into public transport travel time variability[J]. Journal of Transportation Engineering,2009, 136(7):623-631.
[2]王殿海,汤月华,陈茜,等.基于GPS数据的公交站点区间行程时间可靠性影响因素[J].东南大学学报(自然科学版), 2015(2):404-412.[WANG D H, TANG Y H, CHEN Q, et al. Factors affecting the reliability of bus station interval travel time based on GPS data[J].Journal of Southeast University(Natural Science Edition), 2015(2):404-412.]
[3] FONZONE A, SCHM?CKERJ D, LIU R. A model of bus bunching under reliability-based passenger arrival patterns[J]. Transport. Res. Part C:Emerg, Technol.,2015(7):164-182.
[4]李梦甜.公共交通车辆串车形成原因及预测研究[D].南京:东南大学, 2016.[LI M T. Causes and prediction of vehicle tandem[D]. Nanjing:Southeast University,2016.]
[5] CHEN G, ZHOU X, ZHANG D, et al. Proportion-based and tendency-based bus trajectory prediction models[J].Journal of Transportation Engineering, 2013, 139(9):896-902.
[6]季彦婕,陆佳炜,陈晓实,等.基于粒子群小波神经网络的公交到站时间预测[J].交通运输系统工程与信息, 2016, 16(3):60-66.[JI Y J, LU J W, CHEN X S,et al. Bus arrival time prediction based on particle swarm wavelet neural network[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3):60-66.]
[7] YU H, WU Z, CHEN D, et al. Probabilistic prediction of bus headway using relevance vector machine regression[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(7):1772-1781.
[8] SáNCHEZ-MARTíNEZ G E, KOUTSOPOULOS H N,WILSON N H M. Optimal allocation of vehicles to bus routes using automatically collected data and simulation modelling[J]. Research in Transportation Economics,2016, 59(1):268-276.
[9]王健,曹阳,王运豪.考虑出行时间窗的定制公交线路车辆调度方法[J].中国公路学报, 2018, 31(5):143-150.[WANG J, CAO Y, WANG Y H. A method of customized bus route vehicle scheduling with travel time window[J]. Journal of China Highway, 2018, 31(5):143-150.]
[10] SEIF Z, AHMADI M B. An opposition-based algorithm for function optimization[J]. Engineering Applications of Artificial Intelligence, 2015, 37(2):293-306.
[11] DE CASTRO L N, VON ZUBEN F J. Learning and optimization using the clonal selection principle[J].IEEE Trans. Evol. Comput, 2002, 6(3):239-251.
[12] LIU X H, SHAN M Y, ZHANG R L, et al. Green vehicle routing optimization based on carbon emission and multiobjective hybrid quantum immune algorithm[J].Mathematical Problems in Engineering, 2018, 2018(7):1-9.
[2]王殿海,汤月华,陈茜,等.基于GPS数据的公交站点区间行程时间可靠性影响因素[J].东南大学学报(自然科学版), 2015(2):404-412.[WANG D H, TANG Y H, CHEN Q, et al. Factors affecting the reliability of bus station interval travel time based on GPS data[J].Journal of Southeast University(Natural Science Edition), 2015(2):404-412.]
[3] FONZONE A, SCHM?CKERJ D, LIU R. A model of bus bunching under reliability-based passenger arrival patterns[J]. Transport. Res. Part C:Emerg, Technol.,2015(7):164-182.
[4]李梦甜.公共交通车辆串车形成原因及预测研究[D].南京:东南大学, 2016.[LI M T. Causes and prediction of vehicle tandem[D]. Nanjing:Southeast University,2016.]
[5] CHEN G, ZHOU X, ZHANG D, et al. Proportion-based and tendency-based bus trajectory prediction models[J].Journal of Transportation Engineering, 2013, 139(9):896-902.
[6]季彦婕,陆佳炜,陈晓实,等.基于粒子群小波神经网络的公交到站时间预测[J].交通运输系统工程与信息, 2016, 16(3):60-66.[JI Y J, LU J W, CHEN X S,et al. Bus arrival time prediction based on particle swarm wavelet neural network[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(3):60-66.]
[7] YU H, WU Z, CHEN D, et al. Probabilistic prediction of bus headway using relevance vector machine regression[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(7):1772-1781.
[8] SáNCHEZ-MARTíNEZ G E, KOUTSOPOULOS H N,WILSON N H M. Optimal allocation of vehicles to bus routes using automatically collected data and simulation modelling[J]. Research in Transportation Economics,2016, 59(1):268-276.
[9]王健,曹阳,王运豪.考虑出行时间窗的定制公交线路车辆调度方法[J].中国公路学报, 2018, 31(5):143-150.[WANG J, CAO Y, WANG Y H. A method of customized bus route vehicle scheduling with travel time window[J]. Journal of China Highway, 2018, 31(5):143-150.]
[10] SEIF Z, AHMADI M B. An opposition-based algorithm for function optimization[J]. Engineering Applications of Artificial Intelligence, 2015, 37(2):293-306.
[11] DE CASTRO L N, VON ZUBEN F J. Learning and optimization using the clonal selection principle[J].IEEE Trans. Evol. Comput, 2002, 6(3):239-251.
[12] LIU X H, SHAN M Y, ZHANG R L, et al. Green vehicle routing optimization based on carbon emission and multiobjective hybrid quantum immune algorithm[J].Mathematical Problems in Engineering, 2018, 2018(7):1-9.