考虑旅客选择行为的平行航班舱位控制模型  

Models of seat inventory control for parallel flights with passenger choice behavior

作　　者：高金敏 乐美龙[2] 曲林迟[1] 高涛[1] Gao Jinmin;Le Meilong;Qu Linchi;Gao Tao(School of Economics&Management,Shanghai Maritime University,Shanghai 201306,China;College of Civil Aviation,Nanjing University of Aeronautics&Astronautics,Nanjing 211106,China)

机构地区：[1]上海海事大学经济管理学院,上海201306 [2]南京航空航天大学民航学院,南京211106

出　　处：《计算机应用研究》2018年第4期1107-1110,1116,共5页Application Research of Computers

基　　金：江苏省自然科学基金资助项目(BK20151479);上海海事大学博士研究生创新基金资助项目(2016ycx061);中央高校基本科研业务费专项资金资助项目(NZ2016109)

摘　　要：针对同一航线上的多个平行航班,建立了考虑旅客选择行为的舱位控制数学规划模型。模型根据以往旅客需求时刻分布划分不同的时间段,并且各个时间段内的旅客需求相互独立,当旅客在某个时间段内的需求得不到满足时会出现向上购买、转移到下一时间段的航班或者放弃购买三种行为,同时,模型考虑了旅客取消、no-show现象和超售因素;然后,分别采用遗传算法和LP松弛方法对随机模型和确定性模型进行求解运算,得到了较为稳定的舱位分配方案。最后,通过模拟仿真,从需求满足率、载运率以及总收益三方面对比了两种模型的有效性,结果表明,在需求水平相对不高而需求转移率较高的情况下,随机模型比确定性模型更具优势。For multiple parallel flights on the same route,this paper proposed mathematical programming models of seat inventory control with passenger choice behavior.It obtained different time periods based on previous distribution of passenger demand for flight schedule,and the passenger demand in each period was independent.When passengers’demand in a certain period of time was unavailable,they would buy tickets of the higher fare level,move to flights of the next period or give up buying.At the same time,passenger cancelations,no-shows and over booking were taken into account.Then,it used genetic algorithm and LP relaxation to solve the stochastic model and deterministic model respectively,and obtained stable seat allocations.Finally,the effectiveness of the two models was compared from three aspects:satisfaction rate,load factor and total re-venue by simulations.The results show that,the stochastic model performs better than the deterministic model under the condition of low passenger demand and high demand diversion.

关 键 词：舱位控制 数学规划 旅客选择行为 遗传算法 

分 类 号：U8[交通运输工程]