Integrating Machine Learning Into Vehicle Routing Problem: Methods and Applications

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 93087 - 93115

Published: Jan. 1, 2024

The vehicle routing problem (VRP) and its variants have been intensively studied by the operational research community. existing surveys majority of published articles tackle traditional solutions, including exact methods, heuristics, meta-heuristics. Recently, machine learning (ML)-based methods applied to a variety combinatorial optimization problems, specifically VRPs. strong trend using ML in VRPs gap literature motivated us review state-of-the-art. To provide clear understanding ML-VRP landscape, we categorize related studies based on their applications/constraints technical details. We mainly focus reinforcement (RL)-based approaches because importance literature, while also address non RL-based methods. cover both theoretical practical aspects clearly addressing trends, gap, limitations advantages ML-based discuss some potential future directions.

Language: Английский

---

Fulfilment of last-mile urban logistics for sustainable and inclusive smart cities: a case study conducted in Portugal

International Journal of Logistics Research and Applications, Journal Year: 2022, Volume and Issue: 27(6), P. 931 - 958

Published: Sept. 30, 2022

While industry tends towards mass personalisation and instant deliveries, the last mile of urban logistics is being challenged to decrease number vehicles in circulation distances they travel city centres. The COVID-19 pandemic helped expose inefficiency cities fulfilling citizens' real-time needs. Moreover, first aim this paper understand barriers which policymakers face providing a personalised response needs second ascertain how can proactively serve their communities. In line with these concerns, empirical evidence was collected through questionnaire Portuguese policymakers, results were discussed focus group experts. suggest lack tools enable visualisation study scenarios for implementing organising means delivery storage. although feel confident capacity manage mile, would struggle operate autonomously. Therefore, conceptualises an initial algorithm based on dynamic collaboration stakeholders sharing resources guarantee fulfilment necessities. Furthermore, future discussions shall emerge about relationships technical standards between provide necessary logistical management operations.

Language: Английский

---

An optimization model for routing—location of vehicles with time windows and cross-docking structures in a sustainable supply chain of perishable foods

Operations Management Research, Journal Year: 2023, Volume and Issue: 16(4), P. 1742 - 1765

Published: June 6, 2023

Language: Английский

---

Collaborative multidepot split delivery network design with three-dimensional loading constraints

Transportation Research Part E Logistics and Transportation Review, Journal Year: 2025, Volume and Issue: 196, P. 104032 - 104032

Published: Feb. 22, 2025

Language: Английский

---

Study on a Boat-Assisted Drone Inspection Scheme for the Modern Large-Scale Offshore Wind Farm

IEEE Systems Journal, Journal Year: 2023, Volume and Issue: 17(3), P. 4509 - 4520

Published: May 24, 2023

This study proposes a novel and comprehensive boat-assisted drone inspection scheme for offshore wind farms. Specifically, we develop unique wireless communication model, detailed turbine blade detection route planning the boat to formulate minimum energy consumption problem inspection. Then, demonstrate that this is combinatorial optimization mixed-integer nonlinear programming problem, which solve by decomposing into four subproblems. Moreover, an improved heuristic algorithm constructed optimum exploiting these The simulation results indicate proposed achieves optimal Furthermore, compared with existing methods, obtains lowest total provides higher performance unmanned aerial vehicle when utilized farm

Language: Английский

---

Collaborative Multidepot Vehicle Routing Problem with Dynamic Customer Demands and Time Windows

Sustainability, Journal Year: 2022, Volume and Issue: 14(11), P. 6709 - 6709

Published: May 31, 2022

Dynamic customer demands impose new challenges for vehicle routing optimization with time windows, in which appear dynamically within the working periods of depots. The delivery routes should be adjusted as soon possible when emerge. This study investigates a collaborative multidepot problem dynamic and windows (CMVRPDCDTW) by considering resource sharing demands. Resource across multiple service can maximize logistics utilization improve operating efficiency networks. A bi-objective model is constructed to optimize while minimizing total cost number vehicles. hybrid algorithm composed improved k-medoids clustering multiobjective particle swarm based on insertion strategy (IMOPSO-DIS) designed find near-optimal solutions proposed problem. assigns customers depots terms specific distances obtain units, whereas IMOPSO-DIS optimizes each unit updating external archive. elite learning are applied maintain diversity enhance search ability environment. experiment results 26 instances show that performance superior optimization, nondominated sorting genetic algorithm-II, evolutionary algorithm. case Chongqing City, China implemented, related analyzed. provides efficient strategies solve CMVRPDCDTW. reveal 32.5% reduction costs savings 29 vehicles after optimization. It also intelligence level distribution network, promote sustainable development urban transportation systems, has meaningful implications enterprises government provide theoretical decision supports economic social development.

Language: Английский

---

A two-stage hybrid ant colony algorithm for multi-depot half-open time-dependent electric vehicle routing problem

Complex & Intelligent Systems, Journal Year: 2023, Volume and Issue: 10(2), P. 2107 - 2128

Published: Oct. 26, 2023

Abstract This article presents a detailed investigation into the Multi-Depot Half-Open Time-Dependent Electric Vehicle Routing Problem (MDHOTDEVRP) within domain of urban distribution, prompted by growing urgency to mitigate environmental repercussions logistics transportation. The study first surmounts uncertainty in (EV) range arising from dynamic nature traffic networks establishing flexible energy consumption estimation strategy. Subsequently, Mixed-Integer Programming (MIP) model is formulated, aiming minimize total distribution costs associated with EV dispatch, vehicle travel, customer service, and charging operations. Given unique attributes intrinsic model, Two-Stage Hybrid Ant Colony Algorithm (TSHACA) developed as an effective solution approach. algorithm leverages enhanced K-means clustering assign customers EVs stage employs Improved (IACA) for optimizing each cluster second stage. Extensive simulations conducted on various test scenarios corroborate economic benefits derived MDHOTDEVRP demonstrate superior performance proposed algorithm. outcomes highlight TSHACA’s capability efficiently allocate different depots, optimize routes, reduce carbon emissions, logistic expenditures. Consequently, this contributes significantly advancement sustainable transportation, offering valuable insights practitioners policy-makers.

Language: Английский

---

Research on a Joint Distribution Vehicle Routing Problem Considering Simultaneous Pick-Up and Delivery under the Background of Carbon Trading

Sustainability, Journal Year: 2024, Volume and Issue: 16(4), P. 1698 - 1698

Published: Feb. 19, 2024

In order to explore the positive impact of joint distribution model on reduction in logistics costs small-scale enterprises, considering demand enterprises for simultaneous pick-up and delivery, as well cost carbon emissions, this study considers vehicle routing problem delivery under a model. First all, an independent including fixed transportation, variable time penalty, emissions are established; second, by adding self-adaption cross-mutation probability destruction repair mechanism large-scale neighborhood search algorithm, genetic algorithm is improved adapt solution paper, effectiveness verified analyzed. It found that more advantageous than original solving problems both models designed paper. Finally, used solve two models, results compared can reduce total 6.61% 5.73%. Additionally, trading further explored. The prove effectively costs, improve profits, promote sustainable development condition distribution.

Language: Английский

---

An Adaptive Nutcracker Optimization Approach for Distribution of Fresh Agricultural Products with Dynamic Demands

Agriculture, Journal Year: 2023, Volume and Issue: 13(7), P. 1430 - 1430

Published: July 19, 2023

In the operational, strategic and tactical decision-making problems of agri-food supply chain, perishable nature commodities can represent a particular complexity problem. It is, therefore, appropriate to consider decision support tools that take into account characteristics products, needs requirements producers, sellers consumers. This paper presents green vehicle routing model for fresh agricultural product distribution designs an adaptive hybrid nutcracker optimization algorithm (AH-NOA) based on k-means clustering solve process, AH-NOA uses CW increase population diversity adds genetic operators local search enhance global ability optimization. Finally, experimental data show proposed approaches effectively avoid optima, promote reduce total costs carbon emission costs.

Language: Английский

---

Spatiotemporal distance embedded hybrid ant colony algorithm for a kind of vehicle routing problem with constraints

Frontiers of Information Technology & Electronic Engineering, Journal Year: 2023, Volume and Issue: 24(7), P. 1062 - 1079

Published: July 1, 2023

Language: Английский

---