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.
{"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":"https://doi.org/10.1016/j.tre.2024.103933","url":null,"abstract":"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.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"11 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-20","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}
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.
{"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":"https://doi.org/10.1016/j.tre.2024.103923","url":null,"abstract":"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.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"24 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-20","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}
Pub Date : 2024-12-20DOI: 10.1016/j.tre.2024.103897
Maryam Shaygan, Fatemeh Banani Ardecani, Mark Nejad
The importance of relieving central business district (CBD) congestion while fulfilling network user demand in the morning daily commute has prompted much attention to shared mobility. The deployment of ridesharing paired with autonomous vehicles is expected to bring about a paradigm shift in traffic network dynamics by eliminating the considerable reliance on solo-passenger vehicle usage. In this study, we propose and evaluate two strategies: (1) a CBD entrance permit and (2) temporal capacity allocation with tradable credit. To evaluate the effectiveness of the proposed strategies, we consider four travel modes, including Transit (T), Shared Autonomous Vehicle (SAV), Autonomous Vehicle (AV), and Conventional Vehicle (CV), and account for various factors, such as costs associated with walking, autonomous vehicle self-driving, ridesharing, travel time, and schedule delay. These strategies aim to encourage commuters to adopt sustainable transit or shared mobility options, taking into account different scenarios that consider the challenges and advantages of ridesharing alongside traditional transit systems. The findings indicate that implementing temporal capacity allocation for ridesharing with tradable credit is more advantageous compared to the CBD entrance permit, particularly when the disparity in the fixed additional cost of using SAVs and AVs is minimal. However, both strategies rely on accurately estimating the extra cost incurred by commuters when opting for ridesharing services. Besides, introducing tradable award schemes for ridesharing and transit can improve the efficiency of the system. This study highlights the importance of using new methods and strategies in regulating the travel behavior of commuters with the emergence of autonomous vehicles and shared mobility options to determine solutions for optimizing the system cost. The findings of this study provide valuable insights for transportation planners and policymakers to develop effective strategies for reducing traffic congestion in CBDs.
{"title":"Optimizing mixed traffic environments with shared and private autonomous vehicles: An equilibrium analysis of entrance permit and tradable credit strategies","authors":"Maryam Shaygan, Fatemeh Banani Ardecani, Mark Nejad","doi":"10.1016/j.tre.2024.103897","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103897","url":null,"abstract":"The importance of relieving central business district (CBD) congestion while fulfilling network user demand in the morning daily commute has prompted much attention to shared mobility. The deployment of ridesharing paired with autonomous vehicles is expected to bring about a paradigm shift in traffic network dynamics by eliminating the considerable reliance on solo-passenger vehicle usage. In this study, we propose and evaluate two strategies: (1) a CBD entrance permit and (2) temporal capacity allocation with tradable credit. To evaluate the effectiveness of the proposed strategies, we consider four travel modes, including Transit (T), Shared Autonomous Vehicle (SAV), Autonomous Vehicle (AV), and Conventional Vehicle (CV), and account for various factors, such as costs associated with walking, autonomous vehicle self-driving, ridesharing, travel time, and schedule delay. These strategies aim to encourage commuters to adopt sustainable transit or shared mobility options, taking into account different scenarios that consider the challenges and advantages of ridesharing alongside traditional transit systems. The findings indicate that implementing temporal capacity allocation for ridesharing with tradable credit is more advantageous compared to the CBD entrance permit, particularly when the disparity in the fixed additional cost of using SAVs and AVs is minimal. However, both strategies rely on accurately estimating the extra cost incurred by commuters when opting for ridesharing services. Besides, introducing tradable award schemes for ridesharing and transit can improve the efficiency of the system. This study highlights the importance of using new methods and strategies in regulating the travel behavior of commuters with the emergence of autonomous vehicles and shared mobility options to determine solutions for optimizing the system cost. The findings of this study provide valuable insights for transportation planners and policymakers to develop effective strategies for reducing traffic congestion in CBDs.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"26 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867654","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}
The cloud supported system can effectively optimize vehicle platooning operation due to its centralized control mode in the cloud, but due to its wireless transmission characteristics and the complexity of the mixed traffic environment, the controlled traffic units will inevitably suffer from time delays and outside disturbances, which can lead to serious safety issues. To address the problem of platooning stable operation under stochastic road slope and bi-directional time-varying delay, a novel delay-resistant cloud supported control model is proposed in this paper. First, the mixed vehicle platoon system under the vehicle–road-cloud integrated architecture is established, considering the influence of driving intentions’ uncertainty of human-driven vehicles (HDVs), random variations of road slope, and bi-direction time-varying delay. Second, an exponential mean-square stable delay-dependent controller is designed to stabilize the cloud supported platoon system subject on the basis of robust H∞ approach and Lyapunov-Krasovskii theorem. In addition, the inner-vehicle stability of time-delay mixed platoon system is analyzed using the enhanced free weighting matrix (EFWM) approach along with the improved cone complementarity linearization (ICCL) algorithm. Third, a L2 string stability criterion is defined to inhibit the increasement of perturbances as they propagate along the platoon. Finally, real traffic data as well as different driving conditions are adopted to verify the control performance of the presented method. Compared to traditional vehicle platoon control method, the presented controller can achieve better disturbance suppression and tracking performance under stochastic interferences and bi-direction time-varying delay, the distance error between adjacent vehicles is less than 0.44 m at low and medium speeds.
{"title":"A delay-resistant cloud supported control model for Optimizing vehicle platooning operation","authors":"Ying Liu, Qing Xu, Guangwei Wang, Yi Liu, Mengchi Cai, Chaoyi Chen, Jianqiang Wang, Guodong Yin","doi":"10.1016/j.tre.2024.103928","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103928","url":null,"abstract":"The cloud supported system can effectively optimize vehicle platooning operation due to its centralized control mode in the cloud, but due to its wireless transmission characteristics and the complexity of the mixed traffic environment, the controlled traffic units will inevitably suffer from time delays and outside disturbances, which can lead to serious safety issues. To address the problem of platooning stable operation under stochastic road slope and bi-directional time-varying delay, a novel delay-resistant cloud supported control model is proposed in this paper. First, the mixed vehicle platoon system under the vehicle–road-cloud integrated architecture is established, considering the influence of driving intentions’ uncertainty of human-driven vehicles (HDVs), random variations of road slope, and bi-direction time-varying delay. Second, an exponential mean-square stable delay-dependent controller is designed to stabilize the cloud supported platoon system subject on the basis of robust <ce:italic>H<ce:inf loc=\"post\">∞</ce:inf></ce:italic> approach and Lyapunov-Krasovskii theorem. In addition, the inner-vehicle stability of time-delay mixed platoon system is analyzed using the enhanced free weighting matrix (EFWM) approach along with the improved cone complementarity linearization (ICCL) algorithm. Third, a <mml:math altimg=\"si1.svg\"><mml:msub><mml:mtext mathvariant=\"script\">L</mml:mtext><mml:mn>2</mml:mn></mml:msub></mml:math> string stability criterion is defined to inhibit the increasement of perturbances as they propagate along the platoon. Finally, real traffic data as well as different driving conditions are adopted to verify the control performance of the presented method. Compared to traditional vehicle platoon control method, the presented controller can achieve better disturbance suppression and tracking performance under stochastic interferences and bi-direction time-varying delay, the distance error between adjacent vehicles is less than 0.44 m at low and medium speeds.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"268 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867656","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 : 2024-12-18DOI: 10.1016/j.tre.2024.103887
Minghui Xie, Siyu Lin, Sen Wei, Xinying Zhang, Yao Wang, Yuanqing Wang
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.
{"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":"https://doi.org/10.1016/j.tre.2024.103887","url":null,"abstract":"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.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"26 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-18","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}
Pub Date : 2024-12-16DOI: 10.1016/j.tre.2024.103902
Fran Setiawan, Tolga Bektaş, Çağatay Iris
Hub location is a planning problem that involves choosing, from a set of nodes, a subset to designate as hub facilities, linking the hubs to the remaining nodes using a hub-and-spoke structure, and routing of flows on the resulting network. This paper presents theoretical and computational comparisons of the fundamental compact formulations of the p-hub location problem (p-HLP) for three allocation strategies, namely single, multiple and r-allocation. Our theoretical results show that path-based formulations offer the strongest linear programming relaxation. The computational experiments, run on three prominent datasets using a state-of-the-art commercial solver indicate that, flow-based formulations generally solve the largest number of instances to optimality and require the shortest solution time, especially for large-scale instances.
{"title":"The hub location problem with comparisons of compact formulations: A note","authors":"Fran Setiawan, Tolga Bektaş, Çağatay Iris","doi":"10.1016/j.tre.2024.103902","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103902","url":null,"abstract":"Hub location is a planning problem that involves choosing, from a set of nodes, a subset to designate as hub facilities, linking the hubs to the remaining nodes using a hub-and-spoke structure, and routing of flows on the resulting network. This paper presents theoretical and computational comparisons of the fundamental compact formulations of the <mml:math altimg=\"si1.svg\" display=\"inline\"><mml:mi>p</mml:mi></mml:math>-hub location problem (<mml:math altimg=\"si1.svg\" display=\"inline\"><mml:mi>p</mml:mi></mml:math>-HLP) for three allocation strategies, namely single, multiple and <mml:math altimg=\"si823.svg\" display=\"inline\"><mml:mi>r</mml:mi></mml:math>-allocation. Our theoretical results show that path-based formulations offer the strongest linear programming relaxation. The computational experiments, run on three prominent datasets using a state-of-the-art commercial solver indicate that, flow-based formulations generally solve the largest number of instances to optimality and require the shortest solution time, especially for large-scale instances.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"88 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867658","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 : 2024-12-14DOI: 10.1016/j.tre.2024.103915
Yimeng Zhang, Xiangrong Tan, Mi Gan, Xiaobo Liu, Bilge Atasoy
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.
{"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":"https://doi.org/10.1016/j.tre.2024.103915","url":null,"abstract":"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.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"24 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-14","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}
Pub Date : 2024-12-14DOI: 10.1016/j.tre.2024.103885
Ruo Jia, Kun Gao, Shaohua Cui, Jing Chen, Jelena Andric
Electrification of commercial vehicles for more sustainable logistic systems has been promoted in the past decades. This study proposes a deep reinforcement learning method for velocity optimization and battery degradation minimization during operation for battery-powered electric trucks (BETs), aiming to achieve a safe, efficient, and comfortable driving control policy for BETs. To obtain an optimal solution considering both calendar and cyclic battery degradation, Deep Deterministic Policy Gradient and Twin Delayed Deep Deterministic Policy Gradient (TD3) approaches are integrated within a simulation environment. To optimize overall BET velocity performance, a trade-off among safety, efficiency, comfort, and battery degradation is incorporated into the reward function of reinforcement learning using Mixture of Experts (MoE) model. The results indicate that the proposed TD3-MoE model achieves safe, efficient, and comfortable car-following control while optimizing total battery degradation. Specifically, the model achieves reductions in total battery capacity loss ranging from 2.4% to 8.3% at different states of charge (SoC) of battery compared to human-driven scenarios. Moreover, despite calendar battery degradation being inevitable, the cyclic battery degradation is effectively mitigated by 27.7% to 29.6% compared to the same SoCs in human-driving data. Furthermore, the TD3-MoE model achieves significant energy consumption reductions, ranging from 35.3% to 39.8% compared to real car-following trajectories.
{"title":"A multi-objective reinforcement learning-based velocity optimization approach for electric trucks considering battery degradation mitigation","authors":"Ruo Jia, Kun Gao, Shaohua Cui, Jing Chen, Jelena Andric","doi":"10.1016/j.tre.2024.103885","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103885","url":null,"abstract":"Electrification of commercial vehicles for more sustainable logistic systems has been promoted in the past decades. This study proposes a deep reinforcement learning method for velocity optimization and battery degradation minimization during operation for battery-powered electric trucks (BETs), aiming to achieve a safe, efficient, and comfortable driving control policy for BETs. To obtain an optimal solution considering both calendar and cyclic battery degradation, Deep Deterministic Policy Gradient and Twin Delayed Deep Deterministic Policy Gradient (TD3) approaches are integrated within a simulation environment. To optimize overall BET velocity performance, a trade-off among safety, efficiency, comfort, and battery degradation is incorporated into the reward function of reinforcement learning using Mixture of Experts (MoE) model. The results indicate that the proposed TD3-MoE model achieves safe, efficient, and comfortable car-following control while optimizing total battery degradation. Specifically, the model achieves reductions in total battery capacity loss ranging from 2.4% to 8.3% at different states of charge (SoC) of battery compared to human-driven scenarios. Moreover, despite calendar battery degradation being inevitable, the cyclic battery degradation is effectively mitigated by 27.7% to 29.6% compared to the same SoCs in human-driving data. Furthermore, the TD3-MoE model achieves significant energy consumption reductions, ranging from 35.3% to 39.8% compared to real car-following trajectories.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"28 10 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867661","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 : 2024-12-14DOI: 10.1016/j.tre.2024.103904
Joshua Marriott, Tolga Bektaş, Erik Ka Ho Leung, Andrew Lyons
This study explores a critically under-researched aspect of Supply Chain Management (SCM), e-commerce returns in the fashion sector. By combining a comprehensive literature review with empirical data from the UK’s second-largest pure-play fashion retailer, the research offers new insights into the scale and drivers of fashion e-commerce returns. Using a mixed-methods approach, the study uncovers detailed patterns in returned items and the reasons behind consumer return behaviours, revealing the operational complexities these returns impose on reverse logistics processes. In 2022 alone, fashion returns cost the UK industry an estimated £7 billion, while contributing to 750,000 tonnes of CO2 emissions from discarded apparel. A novel framework is proposed to address the challenges associated with high-volume returns, providing practical strategies for improving returns management efficiency. The findings contribute significantly to the SCM field by offering empirical evidence on the specifics of fashion returns, an area previously lacking robust data. This paper not only fills this gap but also provides actionable insights for both academic research and industry practice. By focusing on the management of returns within fashion e-commerce, the study contributes to the development of more sustainable and efficient supply chain strategies, advancing current knowledge within SCM research.
{"title":"The billion-pound question in fashion E-commerce: Investigating the anatomy of returns","authors":"Joshua Marriott, Tolga Bektaş, Erik Ka Ho Leung, Andrew Lyons","doi":"10.1016/j.tre.2024.103904","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103904","url":null,"abstract":"This study explores a critically under-researched aspect of Supply Chain Management (SCM), e-commerce returns in the fashion sector. By combining a comprehensive literature review with empirical data from the UK’s second-largest pure-play fashion retailer, the research offers new insights into the scale and drivers of fashion e-commerce returns. Using a mixed-methods approach, the study uncovers detailed patterns in returned items and the reasons behind consumer return behaviours, revealing the operational complexities these returns impose on reverse logistics processes. In 2022 alone, fashion returns cost the UK industry an estimated £7 billion, while contributing to 750,000 tonnes of CO<ce:inf loc=\"post\">2</ce:inf> emissions from discarded apparel. A novel framework is proposed to address the challenges associated with high-volume returns, providing practical strategies for improving returns management efficiency. The findings contribute significantly to the SCM field by offering empirical evidence on the specifics of fashion returns, an area previously lacking robust data. This paper not only fills this gap but also provides actionable insights for both academic research and industry practice. By focusing on the management of returns within fashion e-commerce, the study contributes to the development of more sustainable and efficient supply chain strategies, advancing current knowledge within SCM research.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"117 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867660","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 : 2024-12-13DOI: 10.1016/j.tre.2024.103880
Yadong Wang, Huming Zhang, Tingsong Wang, Jinping Liu
As the oversupply of shipping capacity and the competition within the shipping industry intensifies, liner alliances have emerged as the prevailing mode of cooperation. The members in a liner alliance often have different shipping resources, indicating that they have to coordinate the shipping resources with each other, in order to achieve smooth cooperation. During the coordination, the fairness of members cannot be ignored as it forms the foundation of cooperation stability. Meanwhile, the vessel fleet is often heterogeneous in practice, not homogeneous assumed in most of existing studies. Therefore, this research explores the joint optimization problem of heterogeneous vessel fleet co-management (including fleet co-deployment, vessel co-scheduling, vessel co-sequencing, slot co-chartering and slot co-allocation), taking into account profit-sharing agreement and weekly-dependent demand. In response to this problem, a mixed-integer nonlinear program is first formulated with the goal of maximizing the overall profit reached by the alliance. We then linearize this nonlinear program, and subsequently develop a solution method to identify the optimal solution for the linearized model. Various numerical tests are performed to examine the validity of the proposed model. Furthermore, several managerial insights that support the operation of liner alliance are delivered.
{"title":"Heterogeneous vessel fleet co-management for liner alliances under profit-sharing agreement and weekly-dependent demand","authors":"Yadong Wang, Huming Zhang, Tingsong Wang, Jinping Liu","doi":"10.1016/j.tre.2024.103880","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103880","url":null,"abstract":"As the oversupply of shipping capacity and the competition within the shipping industry intensifies, liner alliances have emerged as the prevailing mode of cooperation. The members in a liner alliance often have different shipping resources, indicating that they have to coordinate the shipping resources with each other, in order to achieve smooth cooperation. During the coordination, the fairness of members cannot be ignored as it forms the foundation of cooperation stability. Meanwhile, the vessel fleet is often heterogeneous in practice, not homogeneous assumed in most of existing studies. Therefore, this research explores the joint optimization problem of heterogeneous vessel fleet co-management (including fleet co-deployment, vessel co-scheduling, vessel co-sequencing, slot co-chartering and slot co-allocation), taking into account profit-sharing agreement and weekly-dependent demand. In response to this problem, a mixed-integer nonlinear program is first formulated with the goal of maximizing the overall profit reached by the alliance. We then linearize this nonlinear program, and subsequently develop a solution method to identify the optimal solution for the linearized model. Various numerical tests are performed to examine the validity of the proposed model. Furthermore, several managerial insights that support the operation of liner alliance are delivered.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"9 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816524","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：