Airports around the world commonly face challenges in managing airport slot allocation.Effective management of limited slot resources by civil aviation authority often requires redistributing requested slots among air...Airports around the world commonly face challenges in managing airport slot allocation.Effective management of limited slot resources by civil aviation authority often requires redistributing requested slots among airlines.The allocation process must operate within the prescribed capacity limits of the airport while adhering to established priorities and regulations.Additionally,ensuring market fairness is a key objective,as the value of airport slots plays a significant role in the adjustment process.This transforms the traditional time-shift-based problem into a complex multi-objective optimization problem.Addressing such complications is of significant importance to airlines,airports,and passengers alike.Due to the complexity of fairness metrics,traditional integer programming models encounter difficulties in finding effective solutions.This study proposes a neighborhood search strategy to tackle the single airport slot allocation,making it adaptable to both static and rolling capacity scenarios.Two Genetic Algorithms(GAs)are introduced,corresponding to time adjustment and sequence adjustment strategies,respectively.The GA based on the time adjustment strategy demonstrates high robustness,while the sequence adjustment strategy builds upon this GA to develop a simple heuristic algorithm that offers rapid convergence.Case studies conducted at seven airports in China confirm that all three algorithms yield high-quality adjustment solutions suitable for the majority of applications.Further,Pareto analysis reveals that these algorithms effectively balance the adjustment shifts and fairness metrics,demonstrating high practical value and broad applicability.展开更多
Siting low-altitude takeoff and landing platforms(vertiports)is a fundamental challenge for developing urban air mobility(UAM).This study formulates this issue as a variant of the capacitated facility location problem...Siting low-altitude takeoff and landing platforms(vertiports)is a fundamental challenge for developing urban air mobility(UAM).This study formulates this issue as a variant of the capacitated facility location problem,incorporating flight range and service capacity constraints,and proposes SPID,a deep reinforcement learning(DRL)-based solution framework that models the problem as a Markov decision process.To handle dynamic coverage,the designed DRL framework-based SPID uses a multi-head attention mechanism to capture spatiotemporal patterns,followed by integrating dynamic and static information into a unified input state vector.Afterward,a gated recurrent unit(GRU)is used to generate the query vector,thereby enhancing sequential decision-making.The action network within the DRL network is regulated by a loss function that integrates service distance costs with unmet demand penalties,enabling end-to-end optimization.Subsequent experimental results demonstrate that SPID significantly enhances solution efficiency and robustness compared with traditional methods under flight and capacity constraints.Especially,across the social performance metrics emphasized in this study,SPID outperforms the suboptimal solutions produced by traditional clustering and graph neural network(GNN)-based methods by up to approximately 29%.This improvement comes with an increase in distance-based cost that is kept within 10%.Overall,we demonstrate an efficient,scalable approach for vertiport siting,supporting rapid decisionmaking in large-scale UAM scenarios.展开更多
The dynamic joint pricing and seat inventory control is more practical but complicated in both formulation and solving.This paper presents a three-stage decision approach(TSDA)to attack this problem.In the first stage...The dynamic joint pricing and seat inventory control is more practical but complicated in both formulation and solving.This paper presents a three-stage decision approach(TSDA)to attack this problem.In the first stage,the relationship between dynamic prices and their pre-sale periods is built.The game process between passengers and the airline based on maximisation of both passenger utility and airline’s network revenue is applied.Passenger’s booking and cancellation processes are simulated according to respective distributions.In the second stage,the seat allocation model for different itineraries is built based on presented unified prices.It greatly decreases computation complexity since prices,itinerary legs and pre-sale time periods are excluded from combination.In the third stage,itinerary-based revenue management model is built with embedding the nested control strategy inside.Meanwhile,some practical factors such as cancellation and no-show are considered.The experimental computation results show TSDA is effective.展开更多
基金supported in part by the National Natural Science Foundation of China(Nos.62167003,52302421)in part by the Diversified Investment Fund of Tianjin,China(No.23JCQNJC00210)。
文摘Airports around the world commonly face challenges in managing airport slot allocation.Effective management of limited slot resources by civil aviation authority often requires redistributing requested slots among airlines.The allocation process must operate within the prescribed capacity limits of the airport while adhering to established priorities and regulations.Additionally,ensuring market fairness is a key objective,as the value of airport slots plays a significant role in the adjustment process.This transforms the traditional time-shift-based problem into a complex multi-objective optimization problem.Addressing such complications is of significant importance to airlines,airports,and passengers alike.Due to the complexity of fairness metrics,traditional integer programming models encounter difficulties in finding effective solutions.This study proposes a neighborhood search strategy to tackle the single airport slot allocation,making it adaptable to both static and rolling capacity scenarios.Two Genetic Algorithms(GAs)are introduced,corresponding to time adjustment and sequence adjustment strategies,respectively.The GA based on the time adjustment strategy demonstrates high robustness,while the sequence adjustment strategy builds upon this GA to develop a simple heuristic algorithm that offers rapid convergence.Case studies conducted at seven airports in China confirm that all three algorithms yield high-quality adjustment solutions suitable for the majority of applications.Further,Pareto analysis reveals that these algorithms effectively balance the adjustment shifts and fairness metrics,demonstrating high practical value and broad applicability.
文摘Siting low-altitude takeoff and landing platforms(vertiports)is a fundamental challenge for developing urban air mobility(UAM).This study formulates this issue as a variant of the capacitated facility location problem,incorporating flight range and service capacity constraints,and proposes SPID,a deep reinforcement learning(DRL)-based solution framework that models the problem as a Markov decision process.To handle dynamic coverage,the designed DRL framework-based SPID uses a multi-head attention mechanism to capture spatiotemporal patterns,followed by integrating dynamic and static information into a unified input state vector.Afterward,a gated recurrent unit(GRU)is used to generate the query vector,thereby enhancing sequential decision-making.The action network within the DRL network is regulated by a loss function that integrates service distance costs with unmet demand penalties,enabling end-to-end optimization.Subsequent experimental results demonstrate that SPID significantly enhances solution efficiency and robustness compared with traditional methods under flight and capacity constraints.Especially,across the social performance metrics emphasized in this study,SPID outperforms the suboptimal solutions produced by traditional clustering and graph neural network(GNN)-based methods by up to approximately 29%.This improvement comes with an increase in distance-based cost that is kept within 10%.Overall,we demonstrate an efficient,scalable approach for vertiport siting,supporting rapid decisionmaking in large-scale UAM scenarios.
基金This workwas supported by Shanghai Philosophy and Social Science Planning Project[Grant number 2020EGL014].
文摘The dynamic joint pricing and seat inventory control is more practical but complicated in both formulation and solving.This paper presents a three-stage decision approach(TSDA)to attack this problem.In the first stage,the relationship between dynamic prices and their pre-sale periods is built.The game process between passengers and the airline based on maximisation of both passenger utility and airline’s network revenue is applied.Passenger’s booking and cancellation processes are simulated according to respective distributions.In the second stage,the seat allocation model for different itineraries is built based on presented unified prices.It greatly decreases computation complexity since prices,itinerary legs and pre-sale time periods are excluded from combination.In the third stage,itinerary-based revenue management model is built with embedding the nested control strategy inside.Meanwhile,some practical factors such as cancellation and no-show are considered.The experimental computation results show TSDA is effective.
