The gate assignment at an airport is one of the major activities in airport operations.With the increase of passenger traffic volumes and the number of flights, the complexity of this task and the factors to be consid...The gate assignment at an airport is one of the major activities in airport operations.With the increase of passenger traffic volumes and the number of flights, the complexity of this task and the factors to be considered have increased significantly, and an efficient gate utilizationhas received considerable attention. For overcoming the shortcomings of previous gate assignmentapproaches, this paper presents a partial parallel gate assignment approach, by which more factorsconcerning aircraft and gates can be collsidered at the same time. This paper also presents themethod of using a knowledge-based system combined with a mathematical programming method forgetting an optimized feasible assignment solution. By this way, it is more easily to get the solutionthat satisfies both the static and dynamic situations,and thus it may adapt well to meet the needsof actual use to rea-time operations. An experimental prototype has been implemented, and a casestudy is presented at the end of the paper.展开更多
With the rapid development of air transportation in recent years,airport operations have attracted a lot of attention.Among them,airport gate assignment problem(AGAP)has become a research hotspot.However,the real-time...With the rapid development of air transportation in recent years,airport operations have attracted a lot of attention.Among them,airport gate assignment problem(AGAP)has become a research hotspot.However,the real-time AGAP algorithm is still an open issue.In this study,a deep reinforcement learning based AGAP(DRL-AGAP)is proposed.The optimization object is to maximize the rate of flights assigned to fixed gates.The real-time AGAP is modeled as a Markov decision process(MDP).The state space,action space,value and rewards have been defined.The DRL-AGAP algorithm is evaluated via simulation and it is compared with the flight pre-assignment results of the optimization software Gurobiand Greedy.Simulation results show that the performance of the proposed DRL-AGAP algorithm is close to that of pre-assignment obtained by the Gurobi optimization solver.Meanwhile,the real-time assignment ability is ensured by the proposed DRL-AGAP algorithm due to the dynamic modeling and lower complexity.展开更多
With the rapid development of civil aviation in recent years,the management and assignment of airport resources are becoming more and more difficult.Among the various airport resources,gates and taxiways are very impo...With the rapid development of civil aviation in recent years,the management and assignment of airport resources are becoming more and more difficult.Among the various airport resources,gates and taxiways are very important,therefore,many researchers focus on the airport gate and taxiway assignment problem.However,the joint assignment algorithm of airport gates and taxiways with realistic airport data has not been well studied.A greedy algorithm based on joint assignment of airport gates and taxiways using the data of a large hub airport in China is proposed.The objective is maximizing the ratio of fixed gates and minimizing the ratio of taxiway collisions.Simulation results show that it outperforms other assignment schemes.展开更多
本文建立了停机位分配的多商品网络流模型,并以航空器总场面运行时间最小为目标,建立数学模型。将机场场面分为若干区域,建立区域—机位两级分配策略,以降低问题规模。设置机位外等待时间,以省去区域容量相关约束。在传统粒子群算法的...本文建立了停机位分配的多商品网络流模型,并以航空器总场面运行时间最小为目标,建立数学模型。将机场场面分为若干区域,建立区域—机位两级分配策略,以降低问题规模。设置机位外等待时间,以省去区域容量相关约束。在传统粒子群算法的基础上,设计离散粒子群算法,对模型进行求解。选取乌鲁木齐机场某日240架航班和109个机位进行实验,证明了与现有研究中的典型模型相比,多商品网络流模型能使运算时间减少10.1%,并能达到与典型模型相同的精度。全空域和机场模型(total airspace and airport modeller,TAAM)仿真结果表明,和现行机位分配方案相比,多商品网络流模型的机位分配结果能使航空器的场面调配运行时间减少7.49%,延误时间减少8.87%。算例结果进一步表明,提高机场场面运行效率的关键在于均衡航班的进离港滑行距离,同时避免停机位密集分布。展开更多
针对实施机位分配方案时间执行偏差较大的问题,探讨使用全空域与机场建模工具(TAAM,total airspace and airport modeller)模拟场面实际运行缩减机位时间执行偏差的可行性。以旅客总行走时间、总机位占用不均衡度、各航空公司航空器平...针对实施机位分配方案时间执行偏差较大的问题,探讨使用全空域与机场建模工具(TAAM,total airspace and airport modeller)模拟场面实际运行缩减机位时间执行偏差的可行性。以旅客总行走时间、总机位占用不均衡度、各航空公司航空器平均滑行距离均衡为目标建立模型,采用TAAM仿真工具优化机位计划运行时间并取得初始机位分配方案,通过熵权法将多目标问题转化为单目标问题,并使用禁忌搜索算法求解模型。仿真验证机位运行时间优化前后的时间执行偏差,结果显示,机位运行时间经过优化之后,机位时间执行偏差明显改善,有效地提高了机位运行效率。展开更多
文摘The gate assignment at an airport is one of the major activities in airport operations.With the increase of passenger traffic volumes and the number of flights, the complexity of this task and the factors to be considered have increased significantly, and an efficient gate utilizationhas received considerable attention. For overcoming the shortcomings of previous gate assignmentapproaches, this paper presents a partial parallel gate assignment approach, by which more factorsconcerning aircraft and gates can be collsidered at the same time. This paper also presents themethod of using a knowledge-based system combined with a mathematical programming method forgetting an optimized feasible assignment solution. By this way, it is more easily to get the solutionthat satisfies both the static and dynamic situations,and thus it may adapt well to meet the needsof actual use to rea-time operations. An experimental prototype has been implemented, and a casestudy is presented at the end of the paper.
基金Supported by the National Natural Science Foundation of China(No.U1633115)the Science and Technology Foundation of Beijing Municipal Commission of Education(No.KM201810005027)。
文摘With the rapid development of air transportation in recent years,airport operations have attracted a lot of attention.Among them,airport gate assignment problem(AGAP)has become a research hotspot.However,the real-time AGAP algorithm is still an open issue.In this study,a deep reinforcement learning based AGAP(DRL-AGAP)is proposed.The optimization object is to maximize the rate of flights assigned to fixed gates.The real-time AGAP is modeled as a Markov decision process(MDP).The state space,action space,value and rewards have been defined.The DRL-AGAP algorithm is evaluated via simulation and it is compared with the flight pre-assignment results of the optimization software Gurobiand Greedy.Simulation results show that the performance of the proposed DRL-AGAP algorithm is close to that of pre-assignment obtained by the Gurobi optimization solver.Meanwhile,the real-time assignment ability is ensured by the proposed DRL-AGAP algorithm due to the dynamic modeling and lower complexity.
基金the National Natural Science Foundation of China(No.U1633115,61571021)the Science and Technology Foundation of Beijing Municipal Commission of Education(No.KM201810005027).
文摘With the rapid development of civil aviation in recent years,the management and assignment of airport resources are becoming more and more difficult.Among the various airport resources,gates and taxiways are very important,therefore,many researchers focus on the airport gate and taxiway assignment problem.However,the joint assignment algorithm of airport gates and taxiways with realistic airport data has not been well studied.A greedy algorithm based on joint assignment of airport gates and taxiways using the data of a large hub airport in China is proposed.The objective is maximizing the ratio of fixed gates and minimizing the ratio of taxiway collisions.Simulation results show that it outperforms other assignment schemes.
文摘本文建立了停机位分配的多商品网络流模型,并以航空器总场面运行时间最小为目标,建立数学模型。将机场场面分为若干区域,建立区域—机位两级分配策略,以降低问题规模。设置机位外等待时间,以省去区域容量相关约束。在传统粒子群算法的基础上,设计离散粒子群算法,对模型进行求解。选取乌鲁木齐机场某日240架航班和109个机位进行实验,证明了与现有研究中的典型模型相比,多商品网络流模型能使运算时间减少10.1%,并能达到与典型模型相同的精度。全空域和机场模型(total airspace and airport modeller,TAAM)仿真结果表明,和现行机位分配方案相比,多商品网络流模型的机位分配结果能使航空器的场面调配运行时间减少7.49%,延误时间减少8.87%。算例结果进一步表明,提高机场场面运行效率的关键在于均衡航班的进离港滑行距离,同时避免停机位密集分布。
文摘针对实施机位分配方案时间执行偏差较大的问题,探讨使用全空域与机场建模工具(TAAM,total airspace and airport modeller)模拟场面实际运行缩减机位时间执行偏差的可行性。以旅客总行走时间、总机位占用不均衡度、各航空公司航空器平均滑行距离均衡为目标建立模型,采用TAAM仿真工具优化机位计划运行时间并取得初始机位分配方案,通过熵权法将多目标问题转化为单目标问题,并使用禁忌搜索算法求解模型。仿真验证机位运行时间优化前后的时间执行偏差,结果显示,机位运行时间经过优化之后,机位时间执行偏差明显改善,有效地提高了机位运行效率。
