基于灵活性产品的航班网络舱位优化与控制

发布时间：2018-03-31 22:34

本文选题：航班网络　切入点：灵活性产品　出处：《中国民用航空飞行学院》2012年硕士论文

【摘要】：灵活性产品已在服务行业中应用多年，公司采用销售灵活性产品的方式，保留在合适的时候再确定产品细节的权利，以应对需求的不确定性。公司会在产品售出以后和提供服务以前确定产品的具体形式并告知顾客具体细节。实践表明，在资源容量一定且需求预测存在误差时，灵活性产品有助于提高公司的收益。然而人们对灵活性产品的相关问题进行系统的学术性研究的时间还不长，成果也非常有限。本文的研究目的是将灵活性产品的概念引入到航空客运收益管理中，，提出航空公司销售灵活性产品的流程和方法，重点研究基于灵活性产品的网络舱位优化控制。首先从收益管理系统的角度分析了航空公司进行网络舱位优化控制所需要的数据源，以数据源的数据结构为基础，提出了构建灵活性产品的方法和算法流程。以反应航班间时空衔接关系的航班网络结构为基础，构建了不考虑灵活性产品的航班网络舱位优化模型、基于灵活性产品的航班网络舱位优化模型、将灵活性产品分配到确定航班中的模型、分配灵活性产品前的模型和分配灵活性产品后的模型。模拟十二种需求场景，采用遗传算法对算例进行求解，对比分析不销售灵活性产品和销售灵活性产品产生的期望收益的大小。通过数据研究表明，在预订期第一阶段，每种需求场景下销售灵活性产品的期望收益均高于不销售灵活性产品的期望收益；同时发现，在同一预测精度下，销售灵活性产品时期望收益的增加幅度表现出随着需求均值下降而增加的趋势。在销售灵活性产品和不销售灵活性产品的情况下，分别模拟15次订票情形，分析预订期第二阶段分配灵活性产品对期望收益的影响。数据研究表明，分配灵活性产品后的平均期望收益仍然高于不销售灵活性产品的平均期望收益，而且期望收益的增加幅度大于第一阶段。因此得出结论，本文基于灵活性产品的航班网络舱位优化模型有助于航空公司提高整体航班网络的期望收益。
[Abstract]:Flexible products have been used in the service industry for many years. The company adopts the way of selling flexible products and reserves the right to determine product details at the right time to deal with the uncertainty of demand.The company will determine the form of the product and inform the customer of the details after the product is sold and before the service is provided.The practice shows that when the resource capacity is constant and the demand prediction error exists, the flexible product is helpful to improve the company's income.However, the time of systematic academic research on flexible products is not long, and the results are very limited.The purpose of this paper is to introduce the concept of flexible product into the revenue management of air passenger transport, and to put forward the flow and method of airline selling flexible product, especially to study the optimization control of network space based on flexible product.Firstly, the paper analyzes the data sources needed by airlines for optimal control of network space from the point of view of revenue management system. Based on the data structure of the data sources, the method and algorithm flow of constructing flexible products are put forward.Based on the network structure of flight network which reflects the relationship between flight space and time, a flight network space optimization model without flexible product and a flight network space optimization model based on flexible product are constructed.The flexible product is assigned to the model in the determined flight, the model before the assignment of the flexible product and the model after the assignment of the flexible product.Twelve requirement scenarios were simulated, and the numerical examples were solved by genetic algorithm, and the expected income generated by non-sale flexible products and sales flexible products was compared and analyzed.The data study shows that in the first stage of the reservation period, the expected income of selling flexible products in each demand scenario is higher than that of non-selling flexible products. At the same time, it is found that in the same prediction accuracy,The increase of expected income in the sales of flexible products shows an increasing trend with the decrease of the average demand.In the case of selling flexible products and not selling flexible products, the paper simulates 15 bookings respectively, and analyzes the effect of the second stage of the reservation period on the expected income of the distributed flexible products.The data study shows that the average expected income of the distributed flexible product is still higher than that of the non-selling flexible product, and the increase of the expected income is larger than that of the first stage.Therefore, it is concluded that the model of flight network accommodation optimization based on flexible products can help airlines to improve the expected income of the overall flight network.
【学位授予单位】：中国民用航空飞行学院
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：V352;F560

【参考文献】