VALIDATION DES TRACES HISTORIQUES DE VÉHICULES DANS UNE SOLUTION D'OPTIMISATION D'ITINÉRAIRE ADAPTATIVE
DOI :
https://doi.org/10.59277/RRST-EE.2025.1.22Mots-clés :
Optimisation d'itinéraire, Classification par apprentissage automatique, Algorithme adaptatif, Pistes historiquesRésumé
Cet article détaille le développement d'une solution robuste d'optimisation d'itinéraires adaptée aux flottes de véhicules commerciaux, en mettant l'accent sur les besoins spécifiques des petites et moyennes entreprises (PME). Notre plateforme innovante intègre plusieurs composants, dont un service d'ingestion de données GPS en temps réel, une couche d'intégration pour une connectivité transparente avec les applications clients existantes, un moteur d'optimisation d'itinéraires sophistiqué et des interfaces conviviales pour les plateformes web et mobiles. L'une des principales caractéristiques de notre approche est l'intégration de techniques d'apprentissage automatique (ML) pour valider les données historiques d'itinéraires. Ce processus atténue l'impact des aléas routiers connus, entraînant une réduction moyenne de 19,6 % de la distance parcourue et de 14,2 % de la durée d'itinéraire lors de la comparaison des différences entre les itinéraires planifiés et exécutés. L'ajustement de l'itinéraire optimal nécessite des tracés historiques fiables, nécessitant ainsi leur validation automatique avec une intervention humaine minimale. Dans cet article, nous décrivons la mise en œuvre de plusieurs modèles de classification par apprentissage automatique sur des trajets historiques et comparons les résultats afin de sélectionner le modèle le plus adapté.
Références
(1) Y. Fan, Q. Zhang, S. Quan, A new approach to solve the vehicle routing problem: The perspective of the genetic algorithm combined with adaptive large neighborhood search, 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI), Kunming, China, pp. 331–337 (2021).
(2) Q. Ni, Y. Tang, A bibliometric visualized analysis and classification of vehicle routing problem research, Sustainability, 15, 7394 (2023).
(3) J.E. Bell, P. McMullen, Ant colony optimization techniques for the vehicle routing problem, Adv. Eng. Informatics, 18, pp. 41–48 (2004).
(4) M. Alweshah, M. Almiani, N. Almansour, S. Khalaileh, H. Aldabbas, A. Alshareef, Vehicle routing problems based on Harris Hawks optimization, Journal of Big Data, 9, pp. 1–18 (2021).
(5) B. Chen, C. Li, S. Zeng, S. Yang, M. Mavrovouniotis, An adaptive evolutionary algorithm for bi-level multi-objective VRPs with real-time traffic conditions, IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA, pp. 1–8 (2021).
(6) P. Mukherjee, A. Ramanathan, S. Dey, Efficient vehicle routing problem: a machine learning and evolutionary computation approach, Proceedings of the Companion Conference on Genetic and Evolutionary Computation, New York, NY, USA, pp. 3–4 (2023).
(7) M. Novelan, S. Efendi, P. Sihombing, H. Mawengkang, Vehicle routing problem optimization with machine learning in imbalanced classification vehicle route data, Eastern-European Journal of Enterprise Technologies, 5, 3 (125), pp. 49–56 (2023).
(8) ***https://iroute.eu/
(9) D. Pisinger, S. Røpke, A general heuristic for vehicle routing problems, Comput. Oper. Res., 34, pp. 2403–2435 (2007).
(10) R. Bai, X. Chen, Z. Chen, T. Cui, S. Gong, W. He, X. Jiang, H. Jin, J. Jin, G. Kendall, J. Li, Z. Lu, J. Ren, P. Weng, N. Xue, H. Zhang, Analytics and machine learning in vehicle routing research, International Journal of Production Research, 61, 1, pp. 4– 30 (2021).
(11) J. Patrick, Q. Jin, S. Melvyn, Routing optimization under uncertainty, Operations Research, Institute for Operations Research and the Management Sciences, 64, 1, pp. 186–200 (2016).
(12) F. Anghelache, C.V. Marian, D.A. Mitrea, N. Goga, A. Vasilateanu, V. Radulescu, D. Musat, D. Scurtu, iRoute - an adaptive route planning solution for commercial vehicle fleets, Applied Sciences, 13, 20, 11517 (2023).
(13) D. Baptista, D. Leite, E. Facca, M. Putti, C. De Bacco, Network extraction by routing optimization, Sci. Rep., 10, 20806 (2020).
(14) C.A. Iordache, C.V. Marian, Project management expert system with advanced document management for public institutions, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg, 69, 2, pp. 219–224 (2024).
(15) M. Song, J. Li, L. Li, W. Yong, P. Duan, Application of ant colony algorithms to solve the vehicle routing problem, Intelligent Computing Theories and Application (ICIC), Wuhan, China, pp. 831–840 (2018).
(16) L. Zhuge, L. Tong, H. Wu, Y. Chen, X. Zhou, Finding robust and consistent space-time delivery paths for multi-day vehicle routing problem, IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, pp. 1355–1360 (2019).
(17) H. Zhang, W. Yang, An enhanced adaptive large neighborhood search algorithm for the capacitated vehicle routing problem, 13th International Conference on Machine Learning and Computing, Association for Computing Machinery, New York, NY, USA, pp. 79–85 (2021).
(18) B. Chen, C. Li, S. Zeng, S. Yang, M. Mavrovouniotis, An adaptive evolutionary algorithm for bi-level multi-objective VRPs with real-time traffic conditions, IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA, pp. 1–8 (2021).
(19) X. Ji, J. Pan, S. Chu, P. Hu, Q. Chai, P. Zhang, Adaptive cat swarm optimization algorithm and its applications in vehicle routing problems, Mathematical Problems in Engineering, 2020, 1291526 (2020).
(20) L. Wang, C. Song, Y. Sun, C. Lu, Q. Chen, A neural multi-objective capacitated vehicle routing optimization algorithm based on preference adjustment, Electronics, 12, 19, 4167 (2023).
(21) B. Păvăloiu, P. Cristea, Training spiking neurons with isolated spikes coding, UPB Sci. Bull. C: Electr. Eng. Comput. Sci., 69, 3, pp. 93–104 (2007).
(22) S.A. Samya, V. Nagarajan, A. Appathurai, S. Suniram, Software cost effort and time estimation using dragonfly whale lion optimized deep neural network, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg, 69, 4, pp. 431–436 (2024).
(23) J. Cao, Z. Fang, G. Qu, H. Sun, D. Zhang, An accurate traffic classification model based on support vector machines, International Journal of Network Management, 27, 1 (2017).
(24) B.I. Ciubotaru, G.V. Sasu, N. Goga, A. Vasilățeanu, I. Marin, M. Goga, R. Popovici, G. Datta, Prototype results of an Internet of Things system using wearables and artificial intelligence for the detection of frailty in elderly people, Applied Sciences, 13, 15, 8702 (2023).
(25) S. Bajpai, A. Chauhan, Evolution of machine learning techniques for optimizing delay tolerant routing, 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India, pp. 294–299 (2022).
(26) V. Jain, J. Prakash, D. Saini, J. Jiao, R. Ramjee, M. Varma, Renee: End-to-end training of extreme classification models, Proceedings of Machine Learning and Systems, 5 (2023).
(27) Z. Mammeri, Reinforcement learning based routing in networks: review and classification of approaches, IEEE Access, 7, pp. 55916–55950 (2019).
(28) M. Lima, Information theory inspired optimization algorithm for efficient service orchestration in distributed systems, Plos One, 16, 1, e0242285 (2021).
(29) S. Kaewman, R. Akararungruangkul, Heuristics algorithms for a heterogeneous fleets VRP with excessive demand for the vehicle at the pickup points, and the longest traveling time constraint: a case study in Prasitsuksa Songkloe, Ubonratchathani Thailand, Logistics, 2, 3, 15 (2018).
(30) C.A. Cazan, C.V. Marian, Automation improvement for GIS-based applications deployment in fast-growing high scalability data-rooms, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg, 69, 3, pp. 347–352 (2024).
(31) F.Anghelache, D.A. Mitrea, N. Goga, A. Vasilateanu, V. Radulescu, D. Scurtu, D. Musat, B. Pavaloiu, A quantitative research for determining the user requirements for an innovative route planning system targeted for the commercial vehicle fleets, In Proceedings of the 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Pitesti, Romania, pp. 1–4 (2021).
(32) F. Anghelache, D.A. Mitrea, N. Goga, A. Vasilateanu, V. Radulescu, D. Scurtu, D. Musat, Adaptive route planning algorithm based on historical executions for commercial vehicle fleets, In Proceedings of the IEEE International Conference on Blockchain, Smart Healthcare and Emerging Technologies (SmartBlock4Health), Bucharest, Romania, pp. 1–6 (2022).
(33) A. Glavan, V. Croitoru, Incremental learning for edge network intrusion detection, Rev. Roum. Sci. Techn. – Électrotechn. et Énerg, 68, 3, pp. 301–306 (2023).
(34) B.I. Ciubotaru, G.V. Sasu, N. Goga, A. Vasilățeanu, I. Marin, I.B. Păvăloiu, C.T.I. Gligore, Frailty Insights detection system (FIDS)—a comprehensive and intuitive dashboard using artificial intelligence and web technologies, Appl. Sci., 14, 7180 (2024).
Téléchargements
Publiée
Numéro
Rubrique
Licence
(c) Copyright REVUE ROUMAINE DES SCIENCES TECHNIQUES — SÉRIE ÉLECTROTECHNIQUE ET ÉNERGÉTIQUE 2025
Ce travail est disponible sous licence Creative Commons Attribution - Pas d'Utilisation Commerciale - Pas de Modification 4.0 International.
