kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2025-22-2-94-109kaz29-1991Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEМЕТОДЫ ОПТИМИЗАЦИИ, ОСНОВАННЫЕ НА КЛАСТЕРИЗАЦИИ НА ОСНОВЕ ДАННЫХ ГОРОДСКОЙ КУРЬЕРСКОЙ ЛОГИСТИКИCLUSTERING-BASED METHODS FOR DATA-DRIVEN OPTIMIZATION IN URBAN COURIER LOGISTICShttps://orcid.org/0009-0004-1537-7975ТалғатұлыЖ.TalgatulyZh.

 научный сотрудник 

 Астана 

 Researcher 

 Astana 

zforzesteam@gmail.comhttps://orcid.org/0000-0003-0355-5856АмиргалиевБ. Е.AmirgaliyevB. Ye.

 PhD, профессор 

 Астана 

 PhD, Professor 

 Astana 

beibut.amirgaliyev@astanait.edu.kzhttps://orcid.org/0000-0002-6343-5277ЕділханД.YedilkhanD.

 PhD, ассоц. профессор 

 Астана 

 PhD, Associate Professor 

 Astana 

d.yedilkhan@astanait.edu.kzhttps://orcid.org/0000-0002-2742-6779ТургинбековА.TurginbekovA.

 научный сотрудник 

 Астана 

 Researcher 

 Astana 

turginbekovalmaz@gmail.comhttps://orcid.org/0009-0001-3868-3594ГадаборшевХ. С.GadaborshevKh. S.

 MBA 

 Алматы 

 MBA 

Almaty 

khavazh@rmggroup.kzAstana IT UniversityКазахстанAstana IT UniversityKazakhstanAlmaty Management UniversityКазахстанAlmaty Management UniversityKazakhstan20250607202522294109Copyright © Талғатұлы Ж., Амиргалиев Б.Е., Еділхан Д., Тургинбеков А., Гадаборшев Х.С., 20252025Талғатұлы Ж., Амиргалиев Б.Е., Еділхан Д., Тургинбеков А., Гадаборшев Х.С.Talgatuly Z., Amirgaliyev B.Y., Yedilkhan D., Turginbekov A., Gadaborshev K.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/1991

В условиях стремительного развития городов и их инфраструктуры спрос к качественным городским доставкам возрастает с той же скоростью. Данная работа исследует возможности динамического распределения зон доставки для курьерских доставок на основе данных, предоставляемых курьерской компанией. Традиционные зоны доставки, создаваемые вручную, часто не обеспечивают релевантность картины по отношению к реальной ситуации в городе (погода, трафик, дороги и т.д.). В данном исследовании приводятся результаты того, как алгоритмы кластеризации K-Means и DBSCAN могут способствовать динамическому распределению зон доставок в виде кластеров. Сравнительный анализ включает в себя учет таких показателей, как значение Silhouette и вычислительная сложность Big-O Notation. Результаты показывают, что K-Means алгоритм создает структурированные и равномерные кластеры, в то время как DBSCAN показывает результаты в определении гибких кластеров с учетом плотности данных в регионе. Многоуровневый DBSCAN предоставляет возможность уменьшить концентрацию «шумов», тем самым увеличивая охват всех точек доставок. Полученные результаты отмечают преимущества использования алгоритмов кластеризации в создании динамических зон доставки для улучшения процессов распределения заказов между курьерами и уменьшением операционных расходов. В дальнейшие исследования следует включить получение данных в реальном времени для наблюдений за работой алгоритмов в динамической среде.

With the rapid development of cities and their infrastructure, the demand for high-quality urban deliveries is increasing at the same rate. This work explores the possibilities of dynamically allocating delivery zones for courier deliveries based on data provided by the courier company. Traditional manually created delivery zones often do not ensure that the picture is relevant to the real situation in the city (weather, traffic, roads, etc.). This study presents the results of how K-Means and DBSCAN clustering algorithms can contribute to the dynamic distribution of delivery zones in clusters. The comparative analysis includes consideration of such indicators as Silhouette value and computational complexity of Big-O Notation. The results show that the K-Means algorithm creates structured and uniform clusters, while DBSCAN shows results in defining flexible clusters based on the density of data in the region. Multi-level DBSCAN provides an opportunity to reduce the concentration of “noise”, thereby increasing the coverage of all delivery points. The results obtained highlight the advantages of using clustering algorithms in creating dynamic delivery zones to improve the distribution of orders between couriers and reduce operating costs. Further research should include obtaining continuous real-time data flow to monitor the operation of algorithms in a dynamic environment.

логистикаалгоритмы кластеризацииоптимизация курьерской доставкиумные городазоны доставкимашинное обучениеurban logisticsclustering algorithmscourier optimizationsmart citydelivery zonesmachine learningThis research has been funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant No.BR24992852 “Intelligent models and methods of Smart City digital ecosystem for sustainable development and This research has been funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant No.BR24992852 “Intelligent models and methods of Smart City digital ecosystem for sustainable development and the citizens’ quality of life improvement”).the citizens’ quality of life improvement”).This research has been funded by the Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan (Grant No.BR24992852 “Intelligent models and methods of Smart City digital ecosystem for sustainable development and the citizens’ quality of life improvement”).ReferencesKinelski G. Smart-city trends in the environment of sustainability as support for decarbonization processes // Polityka Energetyczna. – 2022. – Vol. 25. – No. 2.Kinelski G. Smart-city trends in the environment of sustainability as support for decarbonization processes // Polityka Energetyczna. – 2022. – Vol. 25. – No. 2.Janjevic M., Winkenbach M. Characterizing urban last-mile distribution strategies in mature and emerging e-commerce markets // Transportation Research Part A: Policy and Practice. – 2020. – Vol. 133. – P. 164–196.Janjevic M., Winkenbach M. Characterizing urban last-mile distribution strategies in mature and emerging e-commerce markets // Transportation Research Part A: Policy and Practice. – 2020. – Vol. 133. – P. 164–196.Russo F., Comi A. Urban courier delivery in a smart city: the user learning process of travel costs enhanced by emerging technologies // Sustainability. – 2023. – Vol. 15. – No. 23. – P. 16253.Russo F., Comi A. Urban courier delivery in a smart city: the user learning process of travel costs enhanced by emerging technologies // Sustainability. – 2023. – Vol. 15. – No. 23. – P. 16253.Monferdini L., Bottani E. Examining the Response to COVID-19 in Logistics and Supply Chain Processes: Insights from a State-of-the-Art Literature Review and Case Study Analysis // Applied Sciences. – 2024. – Vol. 14. – No. 12. – P. 5317.Monferdini L., Bottani E. Examining the Response to COVID-19 in Logistics and Supply Chain Processes: Insights from a State-of-the-Art Literature Review and Case Study Analysis // Applied Sciences. – 2024. – Vol. 14. – No. 12. – P. 5317.Li Z., Gu W., Meng Q. The impact of COVID-19 on logistics and coping strategies: a literature review // Regional Science Policy & Practice. – 2023. – Vol. 15. – No. 8. – P. 1768–1795.Li Z., Gu W., Meng Q. The impact of COVID-19 on logistics and coping strategies: a literature review // Regional Science Policy & Practice. – 2023. – Vol. 15. – No. 8. – P. 1768–1795.Yang J. et al. Optimization of real-time traffic network assignment based on IoT data using DBN and clustering model in smart city // Future Generation Computer Systems. – 2020. – Vol. 108. – P. 976–986.Yang J. et al. Optimization of real-time traffic network assignment based on IoT data using DBN and clustering model in smart city // Future Generation Computer Systems. – 2020. – Vol. 108. – P. 976–986.Rahman M. A. et al. Logistics Hub Location Optimization: A K-Means and P-Median Model Hybrid Approach Using Road Network Distances // arXiv preprint arXiv:2308.11038. – 2023.Rahman M. A. et al. Logistics Hub Location Optimization: A K-Means and P-Median Model Hybrid Approach Using Road Network Distances // arXiv preprint arXiv:2308.11038. – 2023.Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.Barreto S. et al. Using clustering analysis in a capacitated location-routing problem //European journal of operational research. – 2007. – Vol. 179. – No. 3. – P. 968–977.Barreto S. et al. Using clustering analysis in a capacitated location-routing problem //European journal of operational research. – 2007. – Vol. 179. – No. 3. – P. 968–977.Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.Mandal M.P., Archetti C. A Decomposition Approach to Last Mile Delivery Using Public Transportation Systems // arXiv preprint arXiv:2306.04219. – 2023.Hess A., Spinler S., Winkenbach M. Real-time demand forecasting for an urban delivery platform // Transportation Research Part E: Logistics and Transportation Review. – 2021. – Vol. 145. – P. 102147.Hess A., Spinler S., Winkenbach M. Real-time demand forecasting for an urban delivery platform // Transportation Research Part E: Logistics and Transportation Review. – 2021. – Vol. 145. – P. 102147.Sawik B. Optimizing Last-Mile Delivery: A Multi-Criteria Approach with Automated Smart Lockers, Capillary Distribution and Crowdshipping // Logistics. – 2024. – Vol. 8. – No. 2. – P. 52.Sawik B. Optimizing Last-Mile Delivery: A Multi-Criteria Approach with Automated Smart Lockers, Capillary Distribution and Crowdshipping // Logistics. – 2024. – Vol. 8. – No. 2. – P. 52.Google Sites. K-means clustering algorithm. URL: https://sites.google.com/site/dataclusteringalgorithms/k-means-clustering-algorithm (дата обращения: 31.01.2025).Google Sites. K-means clustering algorithm. URL: https://sites.google.com/site/dataclusteringalgorithms/k-means-clustering-algorithm (Retrieved January 31, 2025).DataCamp. DBSCAN clustering algorithm URL: https://www.datacamp.com/tutorial/dbscanclustering-algorithm (дата обращения: 31.01.2025).DataCamp. DBSCAN clustering algorithm URL: https://www.datacamp.com/tutorial/dbscanclustering-algorithm (Retrieved January 31, 2025).KDnuggets. DBSCAN clustering algorithm in machine learningю – 2020, апрель. URL: https://www.kdnuggets.com/2020/04/dbscan-clustering-algorithm-machine-learning.html (дата обращения: 31.01.2025).KDnuggets. DBSCAN clustering algorithm in machine learningю – 2020, апрель. URL: https://www.kdnuggets.com/2020/04/dbscan-clustering-algorithm-machine-learning.html (Retrieved January 31, 2025).Shahapure K.R., Nicholas C. Cluster quality analysis using silhouette score // 2020 IEEE 7th international conference on data science and advanced analytics (DSAA). – IEEE, 2020. – С. 747–748.Shahapure K.R., Nicholas C. Cluster quality analysis using silhouette score // 2020 IEEE 7th international conference on data science and advanced analytics (DSAA). – IEEE, 2020. – С. 747–748.Ogbuabor G., Ugwoke F. N. Clustering algorithm for a healthcare dataset using silhouette score value // Int. J. Comput. Sci. Inf. Technol. – 2018. – Vol. 10. – No. 2. – P. 27–37.Ogbuabor G., Ugwoke F. N. Clustering algorithm for a healthcare dataset using silhouette score value // Int. J. Comput. Sci. Inf. Technol. – 2018. – Vol. 10. – No. 2. – P. 27–37.Analytics Vidhya. K-means: Getting the optimal number of clusters. – 2021, май. URL: https://www.analyticsvidhya.com/blog/2021/05/k-mean-getting-the-optimal-number-of-clusters/ (дата обращения: 31.01.2025).Analytics Vidhya. K-means: Getting the optimal number of clusters. – 2021, май. URL: https://www.analyticsvidhya.com/blog/2021/05/k-mean-getting-the-optimal-number-of-clusters/ (Retrieved January 31, 2025).GeeksforGeeks. Elbow method for optimal value of k in K-means. URL: https://www.geeksforgeeks.org/elbow-method-for-optimal-value-of-k-in-kmeans/ (дата обращения: 31.01.2025).GeeksforGeeks. Elbow method for optimal value of k in K-means. URL: https://www.geeksforgeeks.org/elbow-method-for-optimal-value-of-k-in-kmeans/ (Retrieved January 31, 2025).GeeksforGeeks. DBSCAN clustering in ML: Density-based clustering. URL: https://www.geeksforgeeks.org/dbscan-clustering-in-ml-density-based-clustering/ (дата обращения: 31.01.2025).GeeksforGeeks. DBSCAN clustering in ML: Density-based clustering. URL: https://www.geeksforgeeks.org/dbscan-clustering-in-ml-density-based-clustering/ (Retrieved January 31, 2025).Srilekha S., Priyadharshini P., Adhilakshmi M. Comparative evaluation of K-Means, hierarchical clustering, and DBSCAN in blood donor segmentation // International Journal for Multidisciplinary Research. – 2024. – Vol. 6. – No. 4. – P. 1–5. https://doi.org/10.36948/ijfmr.2024.v06i04.26755.Srilekha S., Priyadharshini P., Adhilakshmi M. Comparative evaluation of K-Means, hierarchical clustering, and DBSCAN in blood donor segmentation // International Journal for Multidisciplinary Research. – 2024. – Vol. 6. – No. 4. – P. 1–5. https://doi.org/10.36948/ijfmr.2024.v06i04.26755.

The authors declare that there are no conflicts of interest present.