To address the problems of large fluctuations in order demand, low distribution efficiency, and high carbon emissions in urban last-mile distribution, a low-carbon path optimization model responsive to dynamic demand changes was constructed to achieve the dual optimization of distribution costs and carbon emissions. The dynamic demand of urban last-mile distribution was analyzed, and orders were classified into initial orders and real-time new orders. A dynamic path optimization model was established with the objective of minimizing the total distribution cost. A rolling horizon optimization framework was designed to decompose the dynamic problem, which was solved by an improved large neighborhood search genetic algorithm. Furthermore, a simulation verification was conducted combined with the practical business parameters of last-mile distribution enterprises in Xiamen. The results indicate that the improved genetic algorithm reduces the distribution cost by 8.59%, decreases carbon emissions by 13.25%, and significantly improves the solution efficiency; the rolling horizon framework increases the response rate of new orders from 68.5% to 98.2%; carbon emission monetization reduces carbon emissions by 9.45% while only increasing the cost by 3.31%. This research can provide a reference for urban last-mile distribution enterprises to respond to dynamic order demands and promote low-carbon transformation.
ZHOUXiancheng, ZHOUKaijun, WANGLi,et al. Review of Green Vehicle Routing Model and Its Algorithm in Logistics Distribution[J]. Systems Engineering—Theory & Practice,2021,41(1):213-230.
[3]
MOHAMMADIM, RAHMANIFARG, HAJIAGHAEI-KESHTELIM,et al. A Dynamic Approach for the Multi-Compartment Vehicle Routing Problem in Waste Management[J]. Renewable and Sustainable Energy Reviews,2023,184:113526.
[4]
BELHAIZAS, LAPORTEG. A Data-Driven Heuristic for the Dynamic Vehicle Routing Problem with Multiple Soft Time Windows[J]. Computers & Operations Research,2026,187:107341.
LIYanfeng, LIUXuelin. Optimization of Dynamic Heterogeneous Order Delivery in Crowdsourcing Scenarios[J]. Industrial Engineering Journal,2025,28(5):123-130,168.
[9]
JIANGT H, CHANGY C. Machine Learning-Enhanced Last-Mile Delivery Optimization:Integrating Deep Reinforcement Learning with Queueing Theory for Dynamic Vehicle Routing[J]. Applied Sciences,2025,15(21):11320.
[10]
HUANGJ Y, XUM. Dynamic Vehicle Dispatching for Shared-and-Autonomous-Mobility Services with Adaptive Request Assignment[J]. Transportation Research Part E:Logistics and Transportation Review,2026,210:104802.
[11]
CHEND W, IMDAHLC, LAID,et al. A Reinforcement Learning Approach for the Dynamic Vehicle Routing and Scheduling Problem with Stochastic Request Times and Time-Dependent,Stochastic Travel Times[J]. Transportation Research Part C:Emerging Technologies,2026,182:105387.
[12]
LIUY W, TANGY G, HUAC C. A Hybrid Metaheuristic Algorithm for Dynamic Heterogeneous Vehicle Routing Problem with Stochastic Demand Considering Environmental Aspects[J]. International Journal of Electrical Power & Energy Systems,2025,172:111135.
[13]
BRUGLIERIM, ÇATAYB, KESKINM,et al. The Mixed-Fleet Vehicle Routing Problem with Low Emission Zones[J]. Transportation Research Part E:Logistics and Transportation Review,2025,201:104230.
DENGHongxing, ZHOUJie, HUYi. Optimization Model of the Cold Chain Logistics Distribution Path of Fresh Agricultural Products Considering Carbon Emission[J]. Journal of Chongqing Institute of Technology,2023,37(4):289-297.
[16]
ZUOD F, ZHUD L, ZHUN N. Low-Carbon Cold Chain Distribution Facility Location and Multi-Temperature Time-Dependent Routing Optimization Based on Bi-Level Programming[J]. Engineering Research Express,2026,8(2):025227.
WANGN, HUD W, XUJ,et al. Time-Dependent Vehicle Routing of Urban Cold-Chain Logistics Based on Customer Value and Satisfaction[J].China Journal of Highway and Transport,2021,34(09):297-308.
SUHang, LIHaijun. Route Optimization on Low-Carbon Multimodal Transport of Refrigerated Containers under Uncertain Demand[J]. Railway Transport and Economy,2025,47(1):61-69.
HARMSEG. Heuristic and Metaheuristic Approaches to the Multi-Period Vehicle Routing Problem with Time Windows and Rolling Planning Horizon[D]. Stellenbosch:Stellenbosch University,2025.
TUBinbin, LIMeilan, WANGFei.Optimization of Cold Chain Logistics Paths for Fresh Produce Considering Carbon Emissions[J].Journal of Shenyang University (Natural Science),2025,37(6):496-504.
MAJinchao, GAOZihan, SHANGLin, et al. Calculation Model for Generalized Carbon Emission Costs of Typical Logistics Enterprises[J]. Railway Transport and Economy,2025,47(10):95-104.