“滴滴出行”服务数据分析与车辆调度算法设计开题报告
2020-04-13 15:20:18
1. 研究目的与意义(文献综述)
随着移动互联网技术的飞速发展,o2o电子商务模式已成为主流并逐渐改变着人们的衣食住行。互联网时代开启的共享经济模式彻底改变了传统行业的运行环境,形成了一种新的供给模式和交易关系。滴滴出行是智能叫车与互联网技术相结合的典型的o2o模式的软件,用户只需在软件上发布你的打车需求,约定好时间和地点就可以抵达你想去的地方,给人们的生活带来了的便利,在"互联网 "的时代下,它极大程度地影响且引领着用户的出行方式。
滴滴打车采取订单指派或司机抢单的分单模式,据悉,抢单原则以距离作为司机抢单成功的判定标准,当第一位司机提交抢单申请数秒内附近其他司机仍可提交申请参与抢单,但司机与乘客之间的距离成为司机是否获得订单的主要标准,谁离乘客最近谁就可获得订单。滴滴快车指派模式是指向司机推送距离最近的订单,且十五秒内只推送给该司机一人,目前只适用于实时订单。无论采取哪一种分单模式,我们可以发现其共同点都是将司机与乘客的距离作为首要考虑因素,那么如何提前预测用车需求较密集的地点,从而合理调度车辆、提高载客效率就显得至关重要了。
本文依据滴滴出行盖亚数据开放计划所提供真实的脱敏数据资源,进行有效数据分析,实现对用车需求密集区域的可视化数据热点图,后经马尔科夫决策过程等方法建立一套车辆调度算法,从而更加高效的进行车辆的投放,降低空载率,提高司机的收益率,完善用户的优质用车体验。
2. 研究的基本内容与方案
一、研究目的:
课题设计数据分析及可视化和调度算法设计两大方面,预计实现以下几个目标:
(1)利用python及扩展工具包对数据进行分析,整理并熟练调度所需数据资源。
3. 研究计划与安排
经过仔细的分析和研究,现把毕业设计的进度做如下大概的安排:
第1—3 周:英文翻译,完成开题报告和文献综述
第4—6 周:使用pandas等分析数据。
4. 参考文献(12篇以上)
[1] W. McKinney. Python for Data Analysis. O’Reilly, 2013.
[2] M. Puterman. Markov Decision Processes. Wiley, 2005.
[3] https://outreach.didichuxing.com/research/opendata/ . “盖亚”数据开放计划
[4] H. Rong, X. Zhou, C. Yang, Z. Shafiq, A. Liu, "The rich and the poor: A markov decision process approach to optimizing taxi driver revenue efficiency", Proc. 25th ACM Int. Conf. Inf. Knowl. Manage., pp. 2329-2334, 2016.
[5] M. Qu, H. Zhu, J. Liu, G. Liu, H. Xiong, "A cost-effective recommender system for taxi drivers", Proc. 20th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 45-54, 2014.
[6] G. Nagy, S. Salhi, "Heuristic algorithms for single and multiple depot vehicle routing problems with pickups and deliveries", Eur. J. Oper. Res., vol. 162, pp. 126-141, 2005.
[7] J. Yuan et al., "T-drive: Driving directions based on taxi trajectories", Proc. 18th SIGSPATIAL Int. Conf. Adv. Geograph. Inf. Syst., pp. 99-108, 2010.
[8] J. Yuan, Y. Zheng, L. Zhang, X. Xie, G. Sun, "Where to find my next passenger", Proc. 13th Int. Conf. Ubiquitous Comput., pp. 109-118, 2011.
[9] J. W. Powell, Y. Huang, F. Bastani, M. Ji, "Towards reducing taxicab cruising time using spatio-temporal profitability maps", Proc. SSTD, pp. 242-260, 2011.
[10] K. Yamamoto, K. Uesugi, T. Watanabe, "Adaptive routing of cruising taxis by mutual exchange of pathways", Proc. Int. Conf. Knowl.-Based Intell. Inf. Eng. Syst., pp. 559-566, 2008.
[11] B. Li et al., "Hunting or waiting? Discovering passenger-finding strategies from a large-scale real-world taxi dataset", Proc. IEEE Int. Conf. Pervasive Comput. Commun. Workshops (PERCOM Workshops), pp. 63-68, Mar. 2011.
[12] J.-F. Cordeau, "A branch-and-cut algorithm for the dial-a-ride problem", Oper. Res., vol. 54, no. 3, pp. 573-586, 2006.
[13] J.-L. Lu, M.-Y. Yeh, Y.-C. Hsu, S.-N. Yang, C.-H. Gan, M.-S. Chen, "Operating electric taxi fleets: A new dispatching strategy with charging plans", Proc. IEEE Int. Electr. Vehicle Conf. (IEVC), pp. 1-8, Mar. 2012.
[14] H. Jeung, M. L. Yiu, X. Zhou, C. S. Jensen, "Path prediction and predictive range querying in road network databases", VLDB J.-Int. J. Very Large Data Bases, vol. 19, no. 4, pp. 585-602, 2010.
[15] Y. Ge, H. Xiong, A. Tuzhilin, K. Xiao, M. Gruteser, M. Pazzani, "An energy-efficient mobile recommender system", Proc. 16th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 899-908, 2010.