Yimeng Zhang , Xiangrong Tan , Mi Gan , Xiaobo Liu , Bilge Atasoy
{"title":"Operational synchromodal transport planning methodologies: Review and roadmap","authors":"Yimeng Zhang , Xiangrong Tan , Mi Gan , Xiaobo Liu , Bilge Atasoy","doi":"10.1016/j.tre.2024.103915","DOIUrl":"10.1016/j.tre.2024.103915","url":null,"abstract":"<div><div>This review aims to explore the potential for synchromodal transport planning at the operational level. Synchromodal transport planning involves the optimization of the movement of freights across multiple transport modes, with the objective of minimizing cost, improving efficiency, and promoting sustainability. Through this review, we provide a roadmap for methodological developments in the area of operational synchromodal transport planning research. The roadmap provides a comprehensive categorization of different fields and their trends. The fundamentals of synchromodal transport planning are evolved to more flexible planning approaches that take practical considerations and multiple objectives into account. Dynamic planning is evolving to become more adaptive and resilient to changing environments. Finally, collaborative planning will continue to integrate both vertical and horizontal collaboration with distributed optimization approaches. With dynamic and collaborative approaches considering preferences, the full potential of synchromodal transport planning can be unlocked towards efficient and sustainable freight transportation.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103915"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867659","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}
{"title":"Optimal pricing and collection decisions in a two-period closed-loop supply chain considering channel inconvenience","authors":"Bocan Shu , Jie Wei , Hui Cao","doi":"10.1016/j.tre.2024.103869","DOIUrl":"10.1016/j.tre.2024.103869","url":null,"abstract":"<div><div>Improving recovery efficiency is a key concern for collectors in a closed-loop supply chain (CLSC) with remanufacturing, as customers often consider the inconvenience of recycling channels when returning used products. This issue profoundly affects collectors’ capacity to recover materials. In a two-period CLSC with remanufacturing, including a manufacturer and a retailer, we develop game-theoretical models in the centralized and decentralized scenarios and compare the optimal solutions, consumer surplus, social welfare and environmental impact of different models through analytical and numerical analysis. Our aim is to examine firms’ dynamic pricing strategies and collection investment decisions by considering customers’ perception of channel inconvenience. There are four main findings. Firstly, in the centralized model and the retailer collection model, the decision-maker lowers the retail price in the first period. However, in the competitive collection model, the manufacturer and the retailer raise the wholesale and retail prices in the first period, respectively. Secondly, in the retailer collection model, as the recycling revenue increases, the manufacturer, although not involved in collecting, the profit also increases due to the free-rider behavior. Thirdly, in the competitive collection model, when the remanufacturing cost savings is relatively high, the collection investment of the manufacturer is much larger than that of the retailer, resulting in the retailer failing to collect any product and giving up collecting. Finally, the collection competition improves the total collection rate and environmental performance but reduces the profit of the manufacturer and the retailer, as well as the consumer surplus and social welfare. Therefore, we design a two-part tariff contract to coordinate the decentralized model and effectively improve the performance of the supply chain.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103869"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788861","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}
Tao Tang , Simin Chai , Wei Wu , Jiateng Yin , Andrea D’Ariano
{"title":"A multi-task deep reinforcement learning approach to real-time railway train rescheduling","authors":"Tao Tang , Simin Chai , Wei Wu , Jiateng Yin , Andrea D’Ariano","doi":"10.1016/j.tre.2024.103900","DOIUrl":"10.1016/j.tre.2024.103900","url":null,"abstract":"<div><div>In high-speed railway systems, unexpected disruptions can result in delays of trains, significantly affecting the quality of service for passengers. Train Timetable Rescheduling (TTR) is a crucial task in the daily operation of high-speed railways to maintain punctuality and efficiency in the face of such unforeseen disruptions. Most existing studies on TTR are based on integer programming (IP) techniques and are required to solve IP models repetitively in case of disruptions, which however may be very time-consuming and greatly limit their usefulness in practice. Our study first proposes a multi-task deep reinforcement learning (MDRL) approach for TTR. Our MDRL is constructed and trained offline with a large number of historical disruptive events, enabling to generate TTR decisions in real-time for different disruption cases. Specifically, we transform the TTR problem into a Markov decision process considering the retiming and rerouting of trains. Then, we construct the MDRL framework with the definition of state, action, transition, reward, and value function approximations with neural networks for each agent (i.e., rail train), by considering the information of different disruption events as tasks. To overcome the low training efficiency and huge memory usage in the training of MDRL, given a large number of disruptive events in the historical data, we develop a new and high-efficient training method based on a Quadratic assignment programming (QAP) model and a Frank-Wolfe-based algorithm. Our QAP model optimizes only a small number but most “representative” tasks from the historical data, while the Frank-Wolfe-based algorithm approximates the nonlinear terms in the value function of MDRL and updates the model parameters among different training tasks concurrently. Finally, based on the real-world data from the Beijing–Zhangjiakou high-speed railway systems, we evaluate the performance of our MDRL approach by benchmarking it against state-of-the-art approaches in the literature. Our computational results demonstrate that an offline-trained MDRL is able to generate near-optimal TTR solutions in real-time against different disruption scenarios, and it evidently outperforms state-of-art models regarding solution quality and computational time.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103900"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816530","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}
Minghui Xie , Siyu Lin , Sen Wei , Xinying Zhang , Yao Wang , Yuanqing Wang
{"title":"Online configuration of reservable parking spaces: An agent-based deep reinforcement learning approach","authors":"Minghui Xie , Siyu Lin , Sen Wei , Xinying Zhang , Yao Wang , Yuanqing Wang","doi":"10.1016/j.tre.2024.103887","DOIUrl":"10.1016/j.tre.2024.103887","url":null,"abstract":"<div><div>Unevenly distributed parking demand frequently leads to the overconsumption of popular parking lots, resulting in increased regional travel costs and traffic congestion. Configuring reservable parking spaces in parking lots based on online reservation systems is a prevalent solution to alleviate these issues. However, existing static configuration methods are inadequate for addressing time-varying parking demand, presenting significant challenges in determining the optimal number of reservable parking spaces across different parking lots over time. Thus, to address these challenges and reduce the total travel time in popular reservation-enabled management areas, this paper proposes a dynamic configuration model for reservable parking spaces utilizing agent-based deep reinforcement learning. The model can dynamically schedule the ratio of reservable parking spaces in an environment where reserved users and non-reserved users coexist, thereby influencing parking users’ choice behavior and balancing demand distribution. Experimental results on a real-world simulator show that, compared to baseline methods, the proposed model can effectively configure reservable parking spaces online. It conservatively reduces the total travel time by 21.4% and alleviates parking cruising and waiting in the management area. This approach is prospective for smart parking management.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103887"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867657","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}
Xiaoyue Liu , Jingze Li , Mathieu Dahan , Benoit Montreuil
{"title":"Dynamic hub capacity planning in hyperconnected relay transportation networks under uncertainty","authors":"Xiaoyue Liu , Jingze Li , Mathieu Dahan , Benoit Montreuil","doi":"10.1016/j.tre.2024.103940","DOIUrl":"10.1016/j.tre.2024.103940","url":null,"abstract":"<div><div>In this article, we consider a truck carrier aiming to set contracts with multiple hub providers to reserve hub capacities in a hyperconnected relay transportation network. This network enables long-haul freight shipments to be transported by multiple short-haul drivers commuting between fixed-base hubs, promoting a driver-friendly approach. We introduce the dynamic stochastic hub capacity-routing problem (DS-HCRP), which is a two-stage stochastic program to determine hub contracted capacities for each planning period that minimizes hub and subsequent transportation costs given demand and travel time uncertainty. To overcome the difficulty in solving this NP-hard problem, we propose a combinatorial Benders decomposition (CBD) algorithm based on a tailored implementation of branch-and-Benders-cut. In addition, we design a heuristic initial cut pool generation method to restrict the search space within the CBD algorithm. Experimental results from a case study in the automotive delivery sector demonstrate that our algorithm outperforms other commonly used approaches in terms of solution quality and convergence speed. Furthermore, the results show that the proposed model offers potential savings of up to 22.96% in hub costs and 8.47% in total costs compared to its static deterministic counterpart by effectively mitigating the impact of demand fluctuations and network disruptions, thus highlighting the advantages of dynamic and stochastic integration in capacity planning.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103940"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142887898","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}
{"title":"The two-echelon truck-unmanned ground vehicle routing problem with time-dependent travel times","authors":"Yuanhan Wei , Yong Wang , Xiangpei Hu","doi":"10.1016/j.tre.2024.103954","DOIUrl":"10.1016/j.tre.2024.103954","url":null,"abstract":"<div><div>With the rapid expansion of e-commerce and the resulting surge in parcel delivery demands, the integration of trucks and unmanned ground vehicles (UGVs) in last-mile package delivery provides a more efficient and sustainable venue for a logistics system. However, coordinating trucks and UGVs in the context of fluctuating traffic conditions, especially with varying travel times, continues to be a significant challenge. This study addresses this issue by proposing and solving a two-echelon truck-UGV routing problem with time-dependent travel times. The first echelon encompasses transporting goods from the warehouse to satellites using trucks, considering time-dependent travel times. The second echelon involves distributing goods from satellites to customers using UGVs. Initially, a continuous-time time-dependent travel model is proposed based on the fluid queueing model to estimate vehicle travel times under varying traffic conditions. We then develop a multiobjective mixed integer linear programming model that aims to minimize total operating costs and the number of UGVs used. Subsequently, a novel hybrid algorithm combining an improved three dimension <em>k</em>-nearest neighbor clustering algorithm with an improved multiobjective adaptive large neighborhood search method is developed to solve the model. This algorithm incorporates the adaptive score adjustment and Pareto solution selection strategies to enhance algorithm convergence and evaluate solution quality. The acceptance criterion for new solutions is redesigned based on multiobjective function values to explore the search space more thoroughly. Additionally, the algorithm’s computational performance is verified by comparing it with the CPLEX solver for small-scale problems and with multiobjective ant colony optimization, multiobjective evolutionary algorithms, multiobjective particle swarm optimization, multiobjective monarch butterfly optimization, and multiobjective harmony search algorithms for medium-to-large problems. The results demonstrate the superior convergence, uniformity, and spread of the proposed algorithm. Furthermore, a real-world case study employing traffic information of Dalian city, China, supports that the proposed method enhances the efficiency of delivery. Four different time-dependent travel times model are proposed to analyze the outperformance of the time-dependent travel model in this study. Finally, the sensitivity analysis considers different road congestion states and UGV capacities, aiming to reduce transportation costs, and overcome high coordination and congestion costs in the network. This study offers robust methodologies for theoretically and practically addressing the two-echelon truck-UGV routing problem with time-dependent travel times, providing essential insights for promoting development, enhancing smart city integration, and boosting operational efficiency.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103954"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142939698","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}
{"title":"Selection of R&D techniques: The influence of spillover effects and government subsidies","authors":"Kehong Chen , Yiming Fan","doi":"10.1016/j.tre.2024.103879","DOIUrl":"10.1016/j.tre.2024.103879","url":null,"abstract":"<div><div>This study examines the research and development (R&D) investment strategies of two competing logistics firms under the influence of spillover effects and government subsidies. Firms must decide whether to invest in similar or distinct R&D techniques, or to forgo R&D entirely. Spillover effects occur only when firms adopt different R&D techniques, including cases where one firm chooses not to invest in R&D while the other does. Our findings show that high spillover effects discourage firms from investing in R&D, while low spillover effects induce firms to choose the same R&D techniques. However, social welfare cannot be maximized under the equilibrium state established by free competition among firms. Subsequently, we investigate the impact of government subsidies on firms’ operational decisions, finding that firms choose different R&D techniques when spillover effects are low and R&D costs are high. Notably, government subsidies can partially rectify the misalignment between the Nash equilibrium and maximization of social welfare. This implies that, under certain conditions, government intervention can achieve a dual optimization of firm profits and social welfare. This is crucial for supply chain management, as it ensures both logistics efficiency and competitive pricing, ultimately benefiting the entire supply chain system.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103879"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788852","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}
Song Xu , Xiangyue Ou , Kannan Govindan , Mingzhou Chen , Wenting Yang
{"title":"An adaptive genetic hyper-heuristic algorithm for a two-echelon vehicle routing problem with dual-customer satisfaction in community group-buying","authors":"Song Xu , Xiangyue Ou , Kannan Govindan , Mingzhou Chen , Wenting Yang","doi":"10.1016/j.tre.2024.103874","DOIUrl":"10.1016/j.tre.2024.103874","url":null,"abstract":"<div><div>This study focuses on a novel variant of the classical two-echelon vehicle routing problem (2E-VRP), termed the two-echelon vehicle routing problem with dual-customer satisfaction (2E-VRP-DS) (i.e. time windows satisfaction and freshness satisfaction) in community group-buying. It is important to obtain better solutions for the 2E-VRP-DS with long-distance distribution in the first echelon and last-mile delivery in the second echelon. Therefore, a new mathematical model is established for the 2E-VRP-DS that incorporates objectives: minimising the total distribution costs, and maximum dual-customer satisfaction (time windows satisfaction, and product freshness satisfaction). To solve the mathematical model, an efficient adaptive genetic hyper-heuristic algorithm (AGA-HH) was proposed, complemented by a k-means clustering approach to generate initial solutions. The adaptive genetic algorithm is considered to be a high-level heuristic, and ten local search operators were considered as low-level heuristics to expand the search region of the solution and achieve robust optimal results. Three sets of experiments were conducted, and the results demonstrated the superiority of AGA-HH in solving the 2E-VRP-DS, showing improvements in distribution costs reduction, time windows compliance, and product freshness preservation. Moreover, sensitivity analyses were carried out to show the influence of the number of DCs and the tolerance range of product freshness, discovering some managerial insights for companies. Future work should consider and investigate VRPs in other new business modes.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103874"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Unlocking Real-Time Decision-Making in Warehouses: A machine learning-based forecasting and alerting system for cycle time prediction","authors":"Davide Aloini , Elisabetta Benevento , Riccardo Dulmin , Emanuele Guerrazzi , Valeria Mininno","doi":"10.1016/j.tre.2024.103933","DOIUrl":"10.1016/j.tre.2024.103933","url":null,"abstract":"<div><div>In highly automated warehouses characterized by unpredictable demand, timely decision-making is critical to maintaining operational efficiency. This study proposes a forecasting and alerting system for real-time warehouse management. The system utilizes a Machine Learning (ML)-based predictive model to forecast picking order tardiness using Warehouse Management System data, complemented by a real-time alerting mechanism to support operators in in making informed short-term decisions. A case study conducted in a Shuttle-Based Storage and Retrieval Systems (SBS/RS) of a tire distribution company validates the system’s effectiveness. Particularly, several ML techniques were tested to find the best forecasting model, leveraging a set of predictors tailored to the characteristics of the warehouse. Simulation with real data demonstrates significant reductions of peak cycle times and in total cycle time.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103933"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867653","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}
Yuyan Wang , Junhong Gao , T.C.E. Cheng , Mingzhou Jin , Xiaohang Yue , Huajie Wang
{"title":"Is it necessary for the supply chain to implement artificial intelligence-driven sales services at both the front-end and back-end stages?","authors":"Yuyan Wang , Junhong Gao , T.C.E. Cheng , Mingzhou Jin , Xiaohang Yue , Huajie Wang","doi":"10.1016/j.tre.2024.103923","DOIUrl":"10.1016/j.tre.2024.103923","url":null,"abstract":"<div><div>This paper explores the application of artificial intelligence (AI) in supply chain management, focusing on its impact on service models at both the front and back ends of the supply chain (SC). We employ a Stackelberg game model to construct an SC system consisting of a single manufacturer and a single retailer, aiming to assess the impact of AI on SC performance and explore strategic selection considerations within this framework. Our findings are as follows: (1) AI implementation generally leads to lower product pricing, but its effect on market demand follows a nonlinear pattern. In particular, when the manufacturer integrates AI, the simultaneous use of AI by the retailer will not change the wholesale price but will lead to a decrease in the retail price and market demand. (2) In situations where the back-end cost efficiency is sufficiently high, the optimal choice for both the manufacturer and retailer might be to refrain from adopting AI. Conversely, adopting AI is preferable when the back-end cost efficiency is sufficiently low. Furthermore, when the back-end cost efficiency is moderate, the manufacturer benefits from adopting AI, but the retailer’s profit suffers. (3) Regardless of whether the manufacturer adopts AI, the retailer’s most prudent option is not to implement AI.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"194 ","pages":"Article 103923"},"PeriodicalIF":8.3,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867655","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}