Pub Date : 2025-02-25DOI: 10.1016/j.tre.2025.103972
Zhenjie Wang , Dezhi Zhang , Lóránt Tavasszy , Stefano Fazi
The continuous growth of international container trade calls for logistics networks that seamlessly connect cross-border, domestic, and local transport services. In the design of these networks with various hubs and modes of transport, the consideration of both economies of scale for multimodal transport and congestion is essential since they can significantly impact the location of the hubs and their size. Thereby, in this paper, we study these features within a multimodal hub location problem for international trade that considers a hierarchy in the network structure. We develop a mixed-integer linear programming formulation, minimizing infrastructural, operational, and congestion costs. A hybrid adaptive variable neighborhood search algorithm with tailored operators and speed-up strategies is proposed to solve large-scale instances. Numerical experiments are conducted for China’s New Western Land-Sea Corridor case and provide new managerial insights for designing hierarchical, multi-modal, cross-border logistics networks.
{"title":"The hierarchical multimodal hub location problem for cross-border logistics networks considering multiple capacity levels, congestion and economies of scale","authors":"Zhenjie Wang , Dezhi Zhang , Lóránt Tavasszy , Stefano Fazi","doi":"10.1016/j.tre.2025.103972","DOIUrl":"10.1016/j.tre.2025.103972","url":null,"abstract":"<div><div>The continuous growth of international container trade calls for logistics networks that seamlessly connect cross-border, domestic, and local transport services. In the design of these networks with various hubs and modes of transport, the consideration of both economies of scale for multimodal transport and congestion is essential since they can significantly impact the location of the hubs and their size. Thereby, in this paper, we study these features within a multimodal hub location problem for international trade that considers a hierarchy in the network structure. We develop a mixed-integer linear programming formulation, minimizing infrastructural, operational, and congestion costs. A hybrid adaptive variable neighborhood search algorithm with tailored operators and speed-up strategies is proposed to solve large-scale instances. Numerical experiments are conducted for China’s New Western Land-Sea Corridor case and provide new managerial insights for designing hierarchical, multi-modal, cross-border logistics networks.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 103972"},"PeriodicalIF":8.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-25DOI: 10.1016/j.tre.2025.104017
Nihal Berktas , Konstantinos G. Zografos
Transportation terminals play an important role in the functioning of the transportation system. Therefore, the efficient use of the capacity of transportation terminals is considered a major determinant of the performance of transportation networks. An important decision related to the efficient functioning of congested terminals relates to the optimum allocation of the available capacity to different operators (users). The capacity allocation problem in transportation terminals, such as airports, railroad stations, ports, involves the optimum apportion of the available capacity to different users, such as airlines, rail, and shipping companies, while satisfying operational, and regulatory constraints and requirements. Motivated by the similarities across capacity allocation problems in terminals of different transportation modes and the lack of a unifying framework, this study introduces a generic mixed integer linear programming (MILP) formulation and demonstrates its applicability through a detailed application of the proposed model for rail networks. The generic mathematical model is a generalization of models highly utilized in airport slot allocation. We explicitly present how the model applies to the train timetabling problem and conduct computational experiments using publicly available data. Our computational experiments show that the model consistently achieves optimal solutions across almost all tested cases, including instances where published solutions are suboptimal. The analysis of the results for a specific instance indicates that incorporating station capacity constraints yields the same set of scheduled requests but alters the deviations from the desired arrival and departure times. In contrast, increase in the flexibility of the requested times significantly affect the solution, leading to increase in the number of scheduled trains, deviations, and the overall length of the journey.
{"title":"Generic model for capacity allocation on transportation terminals","authors":"Nihal Berktas , Konstantinos G. Zografos","doi":"10.1016/j.tre.2025.104017","DOIUrl":"10.1016/j.tre.2025.104017","url":null,"abstract":"<div><div>Transportation terminals play an important role in the functioning of the transportation system. Therefore, the efficient use of the capacity of transportation terminals is considered a major determinant of the performance of transportation networks. An important decision related to the efficient functioning of congested terminals relates to the optimum allocation of the available capacity to different operators (users). The capacity allocation problem in transportation terminals, such as airports, railroad stations, ports, involves the optimum apportion of the available capacity to different users, such as airlines, rail, and shipping companies, while satisfying operational, and regulatory constraints and requirements. Motivated by the similarities across capacity allocation problems in terminals of different transportation modes and the lack of a unifying framework, this study introduces a generic mixed integer linear programming (MILP) formulation and demonstrates its applicability through a detailed application of the proposed model for rail networks. The generic mathematical model is a generalization of models highly utilized in airport slot allocation. We explicitly present how the model applies to the train timetabling problem and conduct computational experiments using publicly available data. Our computational experiments show that the model consistently achieves optimal solutions across almost all tested cases, including instances where published solutions are suboptimal. The analysis of the results for a specific instance indicates that incorporating station capacity constraints yields the same set of scheduled requests but alters the deviations from the desired arrival and departure times. In contrast, increase in the flexibility of the requested times significantly affect the solution, leading to increase in the number of scheduled trains, deviations, and the overall length of the journey.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104017"},"PeriodicalIF":8.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1016/j.tre.2025.104009
Yiqun Wang, Yaodong Ni
Continuously increasing carbon emissions pose new challenges to the civil aviation industry. Although new techniques to reduce emissions are being developed, the aviation industry still calls for research on advanced management practices. Airport slot allocation in air traffic flow management aims to reduce flight delays by rescheduling flights. This study extends previous research by proposing a low-carbon air traffic management model that considers flight carbon emissions during airport slot allocation. The model is formulated as a nonlinear integer programming. A flight-based variable neighborhood search algorithm is developed to solve the model. The algorithm is extended by operating flights in different slots within an airport network. Computational experiments on real-world data show that the algorithm can generate a near-optima solution within a short amount of time. A case study based on the solutions indicates that the model can effectively reduce carbon emissions by 26.3%, while simultaneously maintaining delays at a comparable level. These results provide insights into future practices for the civil aviation industry.
{"title":"Airport slot allocation with low-carbon consideration","authors":"Yiqun Wang, Yaodong Ni","doi":"10.1016/j.tre.2025.104009","DOIUrl":"10.1016/j.tre.2025.104009","url":null,"abstract":"<div><div>Continuously increasing carbon emissions pose new challenges to the civil aviation industry. Although new techniques to reduce emissions are being developed, the aviation industry still calls for research on advanced management practices. Airport slot allocation in air traffic flow management aims to reduce flight delays by rescheduling flights. This study extends previous research by proposing a <em>low-carbon air traffic management model</em> that considers flight carbon emissions during airport slot allocation. The model is formulated as a nonlinear integer programming. A <em>flight-based variable neighborhood search</em> algorithm is developed to solve the model. The algorithm is extended by operating flights in different slots within an airport network. Computational experiments on real-world data show that the algorithm can generate a near-optima solution within a short amount of time. A case study based on the solutions indicates that the model can effectively reduce carbon emissions by 26.3%, while simultaneously maintaining delays at a comparable level. These results provide insights into future practices for the civil aviation industry.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104009"},"PeriodicalIF":8.3,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-23DOI: 10.1016/j.tre.2025.104030
Xiang T.R. Kong , Rui Huang , Kai Kang , Suxiu Xu
Digital trading plays a crucial role in construction waste resource utilization. However, supply–demand imbalance and inefficient pricing exist under a prevalent negotiation-based trading approach and a fixed price mechanism, resulting in high transaction costs and rigid clearing prices. Furthermore, high ask prices restrict the transaction scale of recycled remanufacturing products of construction waste (RRPCW). These deficiencies severely hinder development of RRPCW digital trading market. Motivated by the successful implementation of group-buying in various industries, this article aims to propose a combinatorial group-buying double auction mechanism to deal with the challenges in RRPCW transactions. A combinatorial double auction is firstly established where buyers are allowed to bid on bundles of RRPCW to satisfy their full set of procurement requirements. To further scale up transactions, group-buying is incorporated into the auction, where sellers provide corresponding discounts to their matched buyers when thresholds are reached. Such an approach can effectively leverage buyers’ collective purchasing power and scale effect to lower the purchasing costs. The winner determination problem is solved with a bid density-based scheme, while buyers’ payments and sellers’ revenues are calculated by a critical value-based scheme. Theoretical analysis manifests that the designed mechanism can realize individual rationality, strong budget balance and incentive-compatibility of buyers. Five sensitivity analyses including buyers’ bid prices, threshold levels, discount degrees, seller supply heterogeneity, and buyer demand distribution on the mechanism’s overall performance are examined. Additionally, the results of comparative analysis among the proposed mechanism, its counterparts and the fixed price mechanism under different market conditions demonstrate the superiority of our new designed mechanism. Finally, managerial implications are summarized based on the stakeholders’ multi-dimension perspectives. Especially, we emphasized that the regulatory role of the platform is vital for the sustainable and healthy development in the construction waste trading industry.
{"title":"Combinatorial Group-Buying double auction for recycled remanufacturing products of construction waste","authors":"Xiang T.R. Kong , Rui Huang , Kai Kang , Suxiu Xu","doi":"10.1016/j.tre.2025.104030","DOIUrl":"10.1016/j.tre.2025.104030","url":null,"abstract":"<div><div>Digital trading plays a crucial role in construction waste resource utilization. However, supply–demand imbalance and inefficient pricing exist under a prevalent negotiation-based trading approach and a fixed price mechanism, resulting in high transaction costs and rigid clearing prices. Furthermore, high ask prices restrict the transaction scale of recycled remanufacturing products of construction waste (RRPCW). These deficiencies severely hinder development of RRPCW digital trading market. Motivated by the successful implementation of group-buying in various industries, this article aims to propose a combinatorial group-buying double auction mechanism to deal with the challenges in RRPCW transactions. A combinatorial double auction is firstly established where buyers are allowed to bid on bundles of RRPCW to satisfy their full set of procurement requirements. To further scale up transactions, group-buying is incorporated into the auction, where sellers provide corresponding discounts to their matched buyers when thresholds are reached. Such an approach can effectively leverage buyers’ collective purchasing power and scale effect to lower the purchasing costs. The winner determination problem is solved with a bid density-based scheme, while buyers’ payments and sellers’ revenues are calculated by a critical value-based scheme. Theoretical analysis manifests that the designed mechanism can realize individual rationality, strong budget balance and incentive-compatibility of buyers. Five sensitivity analyses including buyers’ bid prices, threshold levels, discount degrees, seller supply heterogeneity, and buyer demand distribution on the mechanism’s overall performance are examined. Additionally, the results of comparative analysis among the proposed mechanism, its counterparts and the fixed price mechanism under different market conditions demonstrate the superiority of our new designed mechanism. Finally, managerial implications are summarized based on the stakeholders’ multi-dimension perspectives. Especially, we emphasized that the regulatory role of the platform is vital for the sustainable and healthy development in the construction waste trading industry.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104030"},"PeriodicalIF":8.3,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.tre.2025.104016
ManWo Ng , Yu-Chi Lee , Dung-Ying Lin
This paper contributes to the literature on the operations management of double stack trains by introducing a new, real-world research problem that arises when loading trains at marine container terminals with on-dock rail service. Specifically, in this research we model the reality that containers that need to be loaded on railcars can be unavailable at the time of loading, while optimizing the assignment of railcars to hubs and trains, and containers to railcars. To this end, we propose a two stage stochastic program that aims to minimize the number of well cars used when container availability is uncertain (first stage) while also maximizing their space utilization when taking corrective actions (second stage). For its solution, a tailored integer L-shaped solution method is presented. Algorithmic performance and managerial insights are highlighted in a series of numerical experiments. Findings include: 1) The proposed L-shaped method is superior compared to a state-of-the-art commercial solver (up to 5 times faster in our experiments). 2) It is beneficial for the rail manager to prioritize making available 40-foot containers versus 20-foot containers. 3) The higher the probability of container availability in the second stage, the more well cars should be made available in the first stage.
{"title":"Optimizing the loading of double stack trains under uncertain container availability","authors":"ManWo Ng , Yu-Chi Lee , Dung-Ying Lin","doi":"10.1016/j.tre.2025.104016","DOIUrl":"10.1016/j.tre.2025.104016","url":null,"abstract":"<div><div>This paper contributes to the literature on the operations management of double stack trains by introducing a new, real-world research problem that arises when loading trains at marine container terminals with on-dock rail service. Specifically, in this research we model the reality that containers that need to be loaded on railcars can be unavailable at the time of loading, while optimizing the assignment of railcars to hubs and trains, and containers to railcars. To this end, we propose a two stage stochastic program that aims to minimize the number of well cars used when container availability is uncertain (first stage) while also maximizing their space utilization when taking corrective actions (second stage). For its solution, a tailored integer L-shaped solution method is presented. Algorithmic performance and managerial insights are highlighted in a series of numerical experiments. Findings include: 1) The proposed L-shaped method is superior compared to a state-of-the-art commercial solver (up to 5 times faster in our experiments). 2) It is beneficial for the rail manager to prioritize making available 40-foot containers versus 20-foot containers. 3) The higher the probability of container availability in the second stage, the more well cars should be made available in the first stage.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104016"},"PeriodicalIF":8.3,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.tre.2025.104032
Yong Wang , Yuanfan Wei , Yuanhan Wei , Lu Zhen , Shejun Deng
The growing demand for bulky goods has spurred logistics firms to explore how to effectively manage and optimize multidepot delivery networks that consider three-dimensional loading constraints. The ability to divide customer demands and adaptively adjust vehicle compartments has significantly enhanced delivery efficiency and vehicle resource utilization. This study develops a collaborative multidepot vehicle routing problem that accommodates split deliveries and three-dimensional loading constraints. It begins by formulating a multi-objective mathematical model that aims to minimize total operating costs (TOC) and the number of vehicles used (NV) while maximizing the average loading rate (ALR). A novel hybrid algorithm combining an improved k-nearest neighbor clustering algorithm with an adaptive non-dominated sorting genetic algorithm-III (ANSGA-III) is developed to find Pareto optimal solutions. The improved k-nearest neighbor clustering algorithm is applied for the reallocation of customers. The ANSGA-III incorporates elite alteration and adaptive information feedback mechanisms to enhance the solution quality and algorithm convergence. Strategies for split loads and vehicle compartment partition are integrated into the ANSGA-III, facilitating the improvement of vehicle resource configuration efficiency. The superiority of the proposed algorithm is verified by comparison with those of the CPLEX solver for small-scale problems and against multi-objective particle swarm optimization, multi-objective evolutionary algorithms, and multi-objective ant colony optimization for medium-to-large problems. Additionally, the proposed model and algorithm are applied to a real-world case study in Chongqing city, China, and the result comparison from the initial network to optimized network shows that the TOC and NV reduced by 43.57% and 32.14%, respectively, while the ALR is improved by 33.51%. Furthermore, this study discusses the optimized results under varying the vehicle compartment partition strategies, contributing to the superiority of proposed approach in improving vehicle resource utilization efficiency. This represents significant cost savings of $2,934 and a reduction of six vehicles, along with a notable 23.35%% improvement in ALR compared to the scenario without compartment division. We also discuss various scenarios involving the split load strategies and different loading capacity schemes, and the computational results demonstrate that the proposed approach improves vehicle loading rates and reduces logistics operating costs. Specifically, the result comparison between the network with and without split load strategies shows that the TOC and ALR in each depot are improved by $2,128, $905, $1,265, $796, and 40.47%, 34.67%, 21.98%, 36.91%, respectively. The findings offer essential insights for promoting a digitally-intelligent and resource-efficient urban logistics system.
{"title":"Collaborative multidepot split delivery network design with three-dimensional loading constraints","authors":"Yong Wang , Yuanfan Wei , Yuanhan Wei , Lu Zhen , Shejun Deng","doi":"10.1016/j.tre.2025.104032","DOIUrl":"10.1016/j.tre.2025.104032","url":null,"abstract":"<div><div>The growing demand for bulky goods has spurred logistics firms to explore how to effectively manage and optimize multidepot delivery networks that consider three-dimensional loading constraints. The ability to divide customer demands and adaptively adjust vehicle compartments has significantly enhanced delivery efficiency and vehicle resource utilization. This study develops a collaborative multidepot vehicle routing problem that accommodates split deliveries and three-dimensional loading constraints. It begins by formulating a multi-objective mathematical model that aims to minimize total operating costs (TOC) and the number of vehicles used (NV) while maximizing the average loading rate (ALR). A novel hybrid algorithm combining an improved <em>k</em>-nearest neighbor clustering algorithm with an adaptive non-dominated sorting genetic algorithm-III (ANSGA-III) is developed to find Pareto optimal solutions. The improved <em>k</em>-nearest neighbor clustering algorithm is applied for the reallocation of customers. The ANSGA-III incorporates elite alteration and adaptive information feedback mechanisms to enhance the solution quality and algorithm convergence. Strategies for split loads and vehicle compartment partition are integrated into the ANSGA-III, facilitating the improvement of vehicle resource configuration efficiency. The superiority of the proposed algorithm is verified by comparison with those of the CPLEX solver for small-scale problems and against multi-objective particle swarm optimization, multi-objective evolutionary algorithms, and multi-objective ant colony optimization for medium-to-large problems. Additionally, the proposed model and algorithm are applied to a real-world case study in Chongqing city, China, and the result comparison from the initial network to optimized network shows that the TOC and NV reduced by 43.57% and 32.14%, respectively, while the ALR is improved by 33.51%. Furthermore, this study discusses the optimized results under varying the vehicle compartment partition strategies, contributing to the superiority of proposed approach in improving vehicle resource utilization efficiency. This represents significant cost savings of $2,934 and a reduction of six vehicles, along with a notable 23.35%% improvement in ALR compared to the scenario without compartment division. We also discuss various scenarios involving the split load strategies and different loading capacity schemes, and the computational results demonstrate that the proposed approach improves vehicle loading rates and reduces logistics operating costs. Specifically, the result comparison between the network with and without split load strategies shows that the TOC and ALR in each depot are improved by $2,128, $905, $1,265, $796, and 40.47%, 34.67%, 21.98%, 36.91%, respectively. The findings offer essential insights for promoting a digitally-intelligent and resource-efficient urban logistics system.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104032"},"PeriodicalIF":8.3,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-19DOI: 10.1016/j.tre.2025.104006
Kaize Yu , Pengyu Yan , Yang Liu , Zhibin Chen , Xiang T.R. Kong
Effective management of battery degradation is crucial for electric vehicles (EVs) due to the high costs associated with replacing EV batteries. In practice, uninformed charging behaviors of EV drivers can accelerate battery wear without proper guidance. To address this challenge, this paper introduces a battery degradation mitigation-oriented charging and order-serving problem for EVs operating on the e-hailing platform. The objective is to maximize the lifespan profit for individual EVs, which encompasses order service revenue, charging expenses, and battery degradation costs. To achieve this goal, a Markov decision process model is developed to capture the dynamics of individual e-hailing EV operations, and a battery degradation cost estimation method is specifically proposed for the e-hailing scenario. Moreover, we propose a multi-agent reinforcement learning (MARL) framework with a centralized training and decentralized execution paradigm. The MARL approach integrates a reward-shaping approach and an enhanced multi-agent upper confidence bound approach to determine the optimal charging and order-serving strategy for EVs. We propose a novel order assignment method to reduce the imbalanced degradation costs across EVs during the learning process. Our simulation experiments validate that the proposed strategy can substantially prolong EV battery life while concurrently boosting driver profits. Furthermore, an explanation of the strategy is provided to ensure transparency and understanding of the decision-making process.
{"title":"Battery degradation mitigation-oriented strategy for optimizing e-hailing electric vehicle operations","authors":"Kaize Yu , Pengyu Yan , Yang Liu , Zhibin Chen , Xiang T.R. Kong","doi":"10.1016/j.tre.2025.104006","DOIUrl":"10.1016/j.tre.2025.104006","url":null,"abstract":"<div><div>Effective management of battery degradation is crucial for electric vehicles (EVs) due to the high costs associated with replacing EV batteries. In practice, uninformed charging behaviors of EV drivers can accelerate battery wear without proper guidance. To address this challenge, this paper introduces a battery degradation mitigation-oriented charging and order-serving problem for EVs operating on the e-hailing platform. The objective is to maximize the lifespan profit for individual EVs, which encompasses order service revenue, charging expenses, and battery degradation costs. To achieve this goal, a Markov decision process model is developed to capture the dynamics of individual e-hailing EV operations, and a battery degradation cost estimation method is specifically proposed for the e-hailing scenario. Moreover, we propose a multi-agent reinforcement learning (MARL) framework with a centralized training and decentralized execution paradigm. The MARL approach integrates a reward-shaping approach and an enhanced multi-agent upper confidence bound approach to determine the optimal charging and order-serving strategy for EVs. We propose a novel order assignment method to reduce the imbalanced degradation costs across EVs during the learning process. Our simulation experiments validate that the proposed strategy can substantially prolong EV battery life while concurrently boosting driver profits. Furthermore, an explanation of the strategy is provided to ensure transparency and understanding of the decision-making process.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104006"},"PeriodicalIF":8.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-19DOI: 10.1016/j.tre.2025.104020
Weiqing Wang , Yuxi Chen , Liukai Wang , Yu Xiong
Predicting the credit risk for enterprises in Supply Chain Finance (SCF) often presents substantial challenges in supply chain management community. Considering the huge information asymmetry, we introduce the Bidirectional Encoder Representations from Transformers (BERT) technology in the fields of Deep Learning and Natural Language Processing (NLP) to extract textual insights from legal judgments related to enterprises in SCF business. By integrating legal judgments-extracted information with the financial and corporate attributes of these enterprises, we aim to enhance the prediction accuracy of credit risk. Our empirical results show that the amalgamation of multi-source information significantly reinforces the predictive accuracy of credit risk. Furthermore, we effectively identify critical predictive factors for credit risk, demonstrating the important role of legal judgment content in default prediction situations. Additionally, considering the issue of imbalanced data categories, we propose a novel imbalanced data processing technique called ACWGAN-GPSA to address the generation of unrealistic samples, thereby significantly improving the performance of credit risk prediction models for enterprises in SCF. The strategic insights obtained from our findings offer valuable guidance for both lenders and financial institutions.
{"title":"Developing the value of legal judgments of supply chain finance for credit risk prediction through novel ACWGAN-GPSA approach","authors":"Weiqing Wang , Yuxi Chen , Liukai Wang , Yu Xiong","doi":"10.1016/j.tre.2025.104020","DOIUrl":"10.1016/j.tre.2025.104020","url":null,"abstract":"<div><div>Predicting the credit risk for enterprises in Supply Chain Finance (SCF) often presents substantial challenges in supply chain management community. Considering the huge information asymmetry, we introduce the Bidirectional Encoder Representations from Transformers (BERT) technology in the fields of Deep Learning and Natural Language Processing (NLP) to extract textual insights from legal judgments related to enterprises in SCF business. By integrating legal judgments-extracted information with the financial and corporate attributes of these enterprises, we aim to enhance the prediction accuracy of credit risk. Our empirical results show that the amalgamation of multi-source information significantly reinforces the predictive accuracy of credit risk. Furthermore, we effectively identify critical predictive factors for credit risk, demonstrating the important role of legal judgment content in default prediction situations. Additionally, considering the issue of imbalanced data categories, we propose a novel imbalanced data processing technique called ACWGAN-GPSA to address the generation of unrealistic samples, thereby significantly improving the performance of credit risk prediction models for enterprises in SCF. The strategic insights obtained from our findings offer valuable guidance for both lenders and financial institutions.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104020"},"PeriodicalIF":8.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143436935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-17DOI: 10.1016/j.tre.2025.104021
Zhaoyang Lu , Tianyi Xing , Yanfeng Li
With the growing awareness of environmental protection and energy conservation, more and more cities choose to utilize electric buses (EBs) in their public transit systems. Due to the limitations of battery technology, many fully charged EBs are not enough to complete their daily tasks, which must be charged twice or more times per day. Besides, many cities encourage the off-peak electricity power consumption, and the charging cost of EBs during peak hours is often extremely high. From an economic viewpoint, it is thus one practical and urgent problem on how to decide the fleet size of EBs and organize their charging schedules for the bus companies. To solve this problem, this manuscript builds a mixed-integer programming (MIP) model via taking the scheduling and charging constraints of EBs into consideration. Also, one dynamic label setting-based branch and price (DLS-BP) algorithm is proposed accordingly, whose efficiency is further verified and compared with two heuristic algorithms via some numerical experiments.
{"title":"Optimization of electric bus vehicle scheduling and charging strategies under Time-of-Use electricity price","authors":"Zhaoyang Lu , Tianyi Xing , Yanfeng Li","doi":"10.1016/j.tre.2025.104021","DOIUrl":"10.1016/j.tre.2025.104021","url":null,"abstract":"<div><div>With the growing awareness of environmental protection and energy conservation, more and more cities choose to utilize electric buses (EBs) in their public transit systems. Due to the limitations of battery technology, many fully charged EBs are not enough to complete their daily tasks, which must be charged twice or more times per day. Besides, many cities encourage the off-peak electricity power consumption, and the charging cost of EBs during peak hours is often extremely high. From an economic viewpoint, it is thus one practical and urgent problem on how to decide the fleet size of EBs and organize their charging schedules for the bus companies. To solve this problem, this manuscript builds a mixed-integer programming (MIP) model via taking the scheduling and charging constraints of EBs into consideration. Also, one dynamic label setting-based branch and price (DLS-BP) algorithm is proposed accordingly, whose efficiency is further verified and compared with two heuristic algorithms via some numerical experiments.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104021"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-17DOI: 10.1016/j.tre.2025.104013
Lan Luo, Xiangyong Li, Yuxuan Zhao
A minor disruption can have a disastrous impact as it cascades through a supply chain. In addition, customer demand is uncertain and susceptible to disruption risks and supply chain management decisions, which in turn impacts how well supply chains function during disruptions. In this paper, we address these issues by studying a supply chain network design problem under disruptions and endogenous demand uncertainty. We first propose a two-stage stochastic-robust formulation where disruption risks are represented using a scenario-based approach and the demand is characterized by a box uncertainty set that depends on both facility-location decisions and disruptions. We then develop an adjusted column-and-constraint generation algorithm and conduct extensive evaluations to verify its effectiveness by comparing it with an affine decision rule method. Additionally, We perform out-of-sample tests to assess the effectiveness and robustness of our model compared to two stochastic programming models. Finally, we present managerial insights, examining how the key factors influence supply chain network performance under disruptions, providing practical guidance.
{"title":"A two-stage stochastic-robust model for supply chain network design problem under disruptions and endogenous demand uncertainty","authors":"Lan Luo, Xiangyong Li, Yuxuan Zhao","doi":"10.1016/j.tre.2025.104013","DOIUrl":"10.1016/j.tre.2025.104013","url":null,"abstract":"<div><div>A minor disruption can have a disastrous impact as it cascades through a supply chain. In addition, customer demand is uncertain and susceptible to disruption risks and supply chain management decisions, which in turn impacts how well supply chains function during disruptions. In this paper, we address these issues by studying a supply chain network design problem under disruptions and endogenous demand uncertainty. We first propose a two-stage stochastic-robust formulation where disruption risks are represented using a scenario-based approach and the demand is characterized by a box uncertainty set that depends on both facility-location decisions and disruptions. We then develop an adjusted column-and-constraint generation algorithm and conduct extensive evaluations to verify its effectiveness by comparing it with an affine decision rule method. Additionally, We perform out-of-sample tests to assess the effectiveness and robustness of our model compared to two stochastic programming models. Finally, we present managerial insights, examining how the key factors influence supply chain network performance under disruptions, providing practical guidance.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"196 ","pages":"Article 104013"},"PeriodicalIF":8.3,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号