Dergiler / Endüstri Mühendisliği / 2026 / Cilt: 37 Sayı: 2

TEDARİK ZİNCİRİNDE DEPO TASARIMI: SİMÜLASYON TABANLI VEKİL MODEL YAKLAŞIMI

WAREHOUSE DESIGN IN THE SUPPLY CHAIN: A SIMULATION-BASED SURROGATE MODEL APPROACH

Mehmet Özkan(YALOVA ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, ENDÜSTRİ MÜHENDİSLİĞİ BÖLÜMÜ)0000-0002-8583-4447
Sayfa
347–380
Yayın Tarihi
2026-08-28
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Bulgular, XGBoost algoritmasının daha tutarlı tahmin performansı sunduğunu ve vekil model yaklaşımının simülasyonun hesaplama maliyetini önemli ölçüde azalttığını göstermektedir.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Artan sipariş çeşitliliği ve hızlı teslimat beklentileri, depo tasarım kararlarının tedarik zinciri performansı üzerindeki etkisini daha kritik hale getirmiştir.
📊
Temel Bulgular & Veri:Bu çalışmada depo tasarım parametrelerinin sipariş toplama performansı üzerindeki etkisi, ayrık olay simülasyonu ve makine öğrenmesi tabanlı vekil model yaklaşımı ile incelenmiştir.
💡
Sonuç & Katkı:Bulgular, XGBoost algoritmasının daha tutarlı tahmin performansı sunduğunu ve vekil model yaklaşımının simülasyonun hesaplama maliyetini önemli ölçüde azalttığını göstermektedir.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:(1) Ürün · Süreç ve Tesis tasarımı · (2) Lojistik ve Tedarik Zinciri Yönetimi

Özet

Artan sipariş çeşitliliği ve hızlı teslimat beklentileri, depo tasarım kararlarının tedarik zinciri performansı üzerindeki etkisini daha kritik hale getirmiştir. Bu çalışmada depo tasarım parametrelerinin sipariş toplama performansı üzerindeki etkisi, ayrık olay simülasyonu ve makine öğrenmesi tabanlı vekil model yaklaşımı ile incelenmiştir. Çalışma kapsamında paralel koridorlu depo yapısını temsil eden ayrık olay simülasyonu modeli Python programlama dili kullanılarak SimPy kütüphanesi ile modellenmiştir. Veri işleme ve analiz süreçlerinde NumPy ve Pandas kütüphanelerinden yararlanılmış, makine öğrenmesi modellerinin oluşturulmasında scikit-learn ve XGBoost altyapısı kullanılmıştır. Tüm modelleme ve deneysel çalışmalar tekrarlanabilirliği sağlamak amacıyla Google Colaboratory ortamında gerçekleştirilmiştir. Simülasyon modeli aracılığıyla oluşturulan 300 gözlemden elde edilen veri seti kullanılarak Random Forest ve XGBoost algoritmaları ile vekil modeller eğitilmiş ve tasarım uzayının hızlı analizine olanak sağlamak amacıyla 10.000 sentetik veri üretilmiştir. Model performansları ortalama mutlak hata ve belirleme katsayısı (R²) metrikleri ile değerlendirilmiştir. Bulgular, XGBoost algoritmasının daha tutarlı tahmin performansı sunduğunu ve vekil model yaklaşımının simülasyonun hesaplama maliyetini önemli ölçüde azalttığını göstermektedir. Sonuçlar, depo tasarımında fiziksel yerleşim kararları ile iş gücü kapasitesi ve talep yoğunluğu arasındaki dengenin tedarik zinciri performansı açısından belirleyici olduğunu ortaya koymaktadır.

Abstract

Increasing order variety and expectations for fast delivery have made the impact of warehouse design decisions on supply chain performance even more critical. This study examines the effect of warehouse design parameters on order picking performance using discrete event simulation and a machine learning-based surrogate model approach. Within the scope of the study, a discrete event simulation model representing a parallel aisle warehouse structure was modeled using the SimPy library in the Python programming language. The NumPy and Pandas libraries were used in data processing and analysis, while the scikit-learn and XGBoost frameworks were used to build machine learning models. All modeling and experimental work was performed in the Google Colaboratory environment to ensure repeatability. Surrogate models were trained using Random Forest and XGBoost algorithms watt a dataset obtained from 300 observations generated through the simulation model, and 10,000 synthetic data sets were generated to enable rapid analysis of the design space. Model performances were evaluated using the mean absolute error and coefficient of determination (R²) metrics. The findings show that the XGBoost algorithm offers more consistent prediction performance and that the proxy model approach significantly reduces the computational cost of the simulation. The results indicate that in warehouse design, the balance between physical layout decisions and labor capacity and demand intensity affects supply chain performance.

🔖

Bu Makaleye Atıf Yap

Özkan, M. (2026). TEDARİK ZİNCİRİNDE DEPO TASARIMI: SİMÜLASYON TABANLI VEKİL MODEL YAKLAŞIMI. Endüstri Mühendisliği, Cilt: 37 Sayı: 2, 347–380. https://doi.org/10.46465/endustrimuhendisligi.1898918

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (60)

  1. Alanani, M. ve Elshaer, A. (2025). Machine learning-based surrogate model for layout optimization frameworks: A comparative study. In Proceedings of the Canadian Society for Civil Engineering Annual Conference 2024, 341–353, Cham. Doi: https://doi.org/10.1007/978-3-031-96763-4_27
  2. Andrea, F. ve Giulio, M. (2023). Review of relevant literature on modelling and simulation approaches for AS/RSs, 22nd IFAC World Congress, 3680-3685, Yokohama. Doi: https://doi.org/10.1016/j.ifacol.2023.10.1533
  3. Araújo, G. R., Gomes, R., Gomes, M. G., Guedes, M. C. ve Ferrão, P. (2023). Surrogate models for efficient multi-objective optimization of building performance, Energies, 16(10), 4030. Doi: https://doi.org/10.3390/en16104030
  4. Bagheri, H. (2022). A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data, Advances in Space Research, 69(9), 3333-3349. Doi: https://doi.org/10.1016/j.asr.2022.02.032
  5. Bahtiar, Z., Prabowo, R. ve Nugroho, H. (2026). Optimizing queue system performance through a comparative analysis of M/M/1 and M/M/s models using Monte Carlo forecasting, Journal of Applied Sciences, Management and Engineering Technology, 7(1), 67-78. Doi: https://doi.org/10.31284/j.jasmet.2026.v7i1.7942
  6. Baker, P. ve Canessa, M. (2009). Warehouse design: A structured approach. European Journal of Operational Research, 193(2), 425-436. Doi: https://doi.org/10.1016/j.ejor.2007.11.045
  7. Bleisinger, O., Malek, C. ve Holbach, S. (2022). Machine learning based simulation for design space exploration. Proceedings of the Design Society, 1521-1530, Doi: https://doi.org/10.1017/pds.2022.154
  8. Becerra-Fernandez, M., Romero, O. R., Trujillo-Diaz, J. ve Herrera, M. M. (2024). Assignment-simulation model for forklifts in a distribution center with aisle constraints. Simulation Modelling Practice and Theory, 133, 102902. Doi: https://doi.org/10.1016/j.simpat.2024.102902
  9. Bernhardsson, E. (2018). Waiting time, load factor and queueing theory: Why you need to cut your systems a bit of slack. Erişim adresi: https://erikbern.com/2018/03/27/waiting-time-load-factor-and-queueing-theory.html
  10. Bortolini, M., Faccio, M., Ferrari, E., Gamberi, M. ve Pilati, F. (2019). Design of diagonal cross-aisle warehouses with class-based storage assignment strategy. The International Journal of Advanced Manufacturing Technology, 100(9), 2521-2536. Doi: https://doi.org/10.1007/s00170-018-2833-9
  11. Bottani, E., Volpi, A. ve Montanari, R. (2019). Design and optimization of order picking systems: An integrated procedure and two case studies. Computers & Industrial Engineering, 137, 106035. Doi: https://doi.org/10.1016/j.cie.2019.106035
  12. Boysen, N. ve De Koster, R. (2025). 50 years of warehousing research—An operations research perspective. European Journal of Operational Research, 320(3), 449-464. Doi: https://doi.org/10.1016/j.ejor.2024.03.026
  13. Briggt, M. (2025). A hybrid AI-driven framework for synchronizing facility layout planning and supply chain execution systems. SSRN. Doi: https://doi.org/10.2139/ssrn.5255917
  14. Cai, L., Ren, L., Wang, Y., Xie, W., Zhu, G. ve Gao, H. (2021). Surrogate models based on machine learning methods for parameter estimation of left ventricular myocardium. Royal Society Open Science, 8(1), 201121. Doi: https://doi.org/10.1098/rsos.201121
  15. Casella, G., Volpi, A., Montanari, R., Tebaldi, L. ve Bottani, E. (2023). Trends in order picking: A 2007–2022 review of the literatüre. Production & Manufacturing Research, 11(1). Doi: https://doi.org/10.1080/21693277.2023.2191115
  16. Chiadamrong, N. ve Piyathanavong, V. (2017). Optimal design of supply chain network under uncertainty environment using hybrid analytical and simulation modeling approach. Journal of Industrial Engineering International, 13(4), 465-478. Doi: https://doi.org/10.1007/s40092-017-0201-2
  17. De Carvalho Paula, M., Carvalho, M. S. ve Silva, E. (2025). Improving warehouse operations: Leveraging simulation for efficient layout design and process improvement in a picking by line operation. Procedia Computer Science, International Conference on Industry Sciences and Computer Science Innovation (iSCSi’24), 481-489. Doi: https://doi.org/10.1016/j.procs.2025.07.058
  18. De Koster, R., Le-Duc, T. ve Roodbergen, K. J. (2007). Design and control of warehouse order picking: A literature review. European Journal of Operational Research, 182(2), 481-501. Doi: https://doi.org/10.1016/j.ejor.2006.07.009
  19. Derhami, S., Smith, J. S. ve Gue, K. R. (2020). A simulation-based optimization approach to design optimal layouts for block stacking warehouses, International Journal of Production Economics, 223, 107525. Doi: https://doi.org/10.1016/j.ijpe.2019.107525
  20. Derpich, I., Sepúlveda, J. M., Barraza, R. ve Castro, F. (2022). Warehouse optimization: Energy efficient layout and design. Mathematics, 10(10), 1705. Doi: https://doi.org/10.3390/math10101705
  21. Díaz, J., Rodriguez, H., Fajardo-Calderín, J., Angulo, I., Onieva, E. (2021). Optimization of warehouse layout for the minimization of operation times. In: Sanjurjo González, H., Pastor López, I., García Bringas, P., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. Lecture Notes in Computer Science, Cham. Doi: https://doi.org/10.1007/978-3-030-86271-8_54
  22. Efe, A. R. ve Mangan, S. D. (2024). Tasarım alanı keşfinde üç farklı vekil modelin etkinlik düzeyinin irdelenmesi. 4. Ulusal Yapı Fiziği ve Çevre Kontrolü Kongresi Bildiriler Kitabı, 196-204, İstanbul. Erişim adresi: https://www.researchgate.net/publication/383048628
  23. Farhadi Moghadam, M., Khalili-Damghani, K., Ghezavati, V. ve Rashidi Komijan, A. (2025). A bi-level optimization method for ıntegrated warehouse design, storage location assignment, and order picking. Social Science Research Network. Doi: https://doi.org/10.2139/ssrn.5365180
  24. Garzón, A., Kapelan, Z., Langeveld, J. ve Taormina, R. (2022). Machine learning-based surrogate modeling for Urban Water Networks: Review and future research directions. Water Resources Research, 58, e2021WR031808. Doi: https://doi.org/10.1029/2021WR031808
  25. Giannikas, V., Lu, W., Robertson, B. ve McFarlane, D. (2017). An interventionist strategy for warehouse order picking: Evidence from two case studies. International Journal of Production Economics, 189, 63-76. Doi: https://doi.org/10.1016/j.ijpe.2017.04.002
  26. Gu, J., Goetschalckx, M. ve McGinnis, L. F. (2007). Research on warehouse operation: A comprehensive review. European Journal of Operational Research, 177(1), 1-21. Doi: https://doi.org/10.1016/j.ejor.2006.02.025
  27. Gürses, D. (2025). Structural design of the electric vehicle components using Runge-Kutta optimization algorithm. Cukurova University Journal of the Faculty of Engineering, 40(3), 699–705. Doi: https://doi.org/10.21605/cukurovaumfd.1770296
  28. Kanchi, P. (2025). Computational modeling of AI-driven project systems: Integrating SAP S/4HANA CPM, PS, and warehouse management in symbotic’s ıntelligent automation framework. International Journal of Computational and Experimental Science and Engineering, 11(4). Doi: https://doi.org/10.22399/ijcesen.4800
  29. Karim, S. M. R., Hossain, Md. S., Akter, K., Sarker, D., Kabir, Md. M. ve Assad, M. (2025). Impact of dataset size on machine learning regression accuracy in solar power prediction. Energy Engineering, 122(8). Doi: https://doi.org/10.32604/ee.2025.066867
  30. Lamperti, F., Roventini, A. ve Sani, A. (2017). Agent-based model calibration using machine learning surrogates. Doi: https://doi.org/10.48550/arXiv.1703.10639
  31. Li, F., Tao, J., Wang, Q., Guo, W., Wang, X., Wang, B., Su, H., Cheng, Z., Yan, B. ve Chen, G. (2025). Simulation and optimization of cold chain logistics system towards lower carbon emission: A state-of-the-art review. Carbon Research, 4(1), 22. Doi: https://doi.org/10.1007/s44246-024-00191-4
  32. Liang, J., Li, Z., Pan, L., Khailah, E. Y., Sun, L. ve Lu, W. (2023). Research on surrogate model of dam numerical simulation with multiple outputs based on adaptive sampling. Scientific Reports, 13, 11955. Doi: https://doi.org/10.1038/s41598-023-38590-z
  33. Mahouti, M., Komek, M. S. ve Yılmaz, S. (2024). Yapay zekâ kullanılarak tren tekerleklerinin yorulma özelliklerinin vekil modellenmesi. Mühendislik Bilimleri ve Tasarım Dergisi, 12(2), 277-284. Doi: https://doi.org/10.21923/jesd.1434972
  34. Moin Uddin Mojumder ve Md. Nuruzzaman. (2025). AI-driven optimization of warehouse layout and material handling: a quantitative study on efficiency and space utilization. Review of Applied Science and Technology, 4(02), 233-273. Doi: https://doi.org/10.63125/bgxb1z53
  35. Negahban, A. ve Smith, J. S. (2014). Simulation for manufacturing system design and operation: Literature review and analysis. Journal of Manufacturing Systems, 33(2), 241-261. Doi: https://doi.org/10.1016/j.jmsy.2013.12.007
  36. Nguyen, T.-U., Suk, H., Liang, C.-P., Ho, Y.-C. ve Chen, J.-S. (2025). Using machine learning to develop a surrogate model for simulating multispecies contaminant transport in groundwater. Hydrology, 12(7). Doi: https://doi.org/10.3390/hydrology12070185
  37. Petersen, C. G. ve Aase, G. (2004). A Comparison of picking, storage, and routing policies in manual order picking. International Journal of Production Economics, 92(1), 11-19. Doi: https://doi.org/10.1016/j.ijpe.2003.09.006
  38. Poloczek, R. (2026). Using simulation modelling to support decision-making in warehouse internal logistics. Production Engineering Archives, 32(2), 164-171. Doi: https://doi.org/10.30657/pea.2026.32.14
  39. Queipo, N. V., Haftka, R. T., Shyy, W., Goel, T., Vaidyanathan, R. ve Kevin Tucker, P. (2005). Surrogate-based analysis and optimization. Progress in Aerospace Sciences, 41(1), 1-28. https://doi.org/10.1016/j.paerosci.2005.02.001
  40. Razavi, S., Tolson, B. A. ve Burn, D. H. (2012). Review of surrogate modeling in water resources. Water Resources Research, 48(7). Doi: https://doi.org/10.1029/2011WR011527
  41. Rouwenhorst, B., Reuter, B., Stockrahm, V., van Houtum, G. J., Mantel, R. J. ve Zijm, W. H. M. (2000). Warehouse design and control: Framework and literature review. European Journal of Operational Research, 122(3), 515-533. Doi: https://doi.org/10.1016/S0377-2217(99)00020-X
  42. Saderova, J., Rosova, A., Behunova, A., Behun, M., Sofranko, M. ve Khouri, S. (2022). Case study: The simulation modelling of selected activity in a warehouse operation. Wireless Networks, 28(1), 431-440. Doi: https://doi.org/10.1007/s11276-021-02574-6
  43. Saraçoğlu, H. ve Söğüt, O. S. (2017). Metan yakıtlı sıkıştırmalı ateşlemeli motorlarda piston geometrisi ve yanma süreci parametrelerinin motor performansına etkilerinin Kriging yöntemiyle incelenmesi. Journal of ETA Maritime Science, 5(4), 314–321. Doi: https://doi.org/10.5505/jems.2017.52824
  44. Saves, P., Palar, P. S., Robani, M. D., Verstaevel, N., Garouani, M., Aligon, J., Gaudou, B., Shimoyama, K. ve Morlier, J. (2025). Surrogate modeling and explainable artificial ıntelligence for complex systems: A workflow for automated simulation exploration. Doi: https://doi.org/10.48550/arXiv.2510.16742
  45. Schleyer, M. ve Gue, K. (2012). Throughput time distribution analysis for a one-block warehouse. Transportation Research Part E: Logistics and Transportation Review, 48(3), 652-666. Doi: https://doi.org/10.1016/j.tre.2011.10.010
  46. Senel Solmaz, A. (2026). A machine learning-based early design energy prediction framework for school buildings across multiple climatic regions of Türkiye. Buildings, 16, 779. Doi: https://doi.org/10.3390/buildings16040779
  47. Sevin, A., Yaman, G. ve Atilgan, D. (2025). Analysis of Queue models in simulation applications. Sakarya University Journal of Computer and Information Sciences, 8(1), 123-135. Doi: https://doi.org/10.35377/saucis.1610018
  48. Shahroudnejad, A., Mousavi, P., Perepelytsia, O., Sahir, Staszak, D., Taylor, M. E. ve Bawel, B. (2024). A novel framework for automated warehouse layout generation. Frontiers in artificial intelligence, 7, 1465186. Doi: https://doi.org/10.3389/frai.2024.1465186
  49. Shi, R., Long, T., Ye, N., Wu, Y., Wei, Z. ve Liu, Z. (2021). Metamodel-based multidisciplinary design optimization methods for aerospace system. Astrodynamics, 5(3), 185-215. Doi: https://doi.org/10.1007/s42064-021-0109-x
  50. Shirzadi, N., Lau, D. ve Stylianou, M. (2025). Surrogate modeling for building design: Energy and cost prediction compared to simulation-based methods. Buildings, 15(13), 2361. Doi: https://doi.org/10.3390/buildings15132361
  51. Soares, G. M., Vieira, A. A. C., Zeiträg, Y. ve Figueira, J. R. (2026). A machine learning framework for surrogate modeling and benchmarking in dynamic job shop scheduling. Decision Analytics Journal, 18, 100669. Doi: https://doi.org/10.1016/j.dajour.2025.100669
  52. Šturek, D. ve Lazarova-Molnar, S. (2025). Surrogate modeling: Review and opportunities for expert knowledge ıntegration. Procedia Computer Science, The 16th International Conference on Ambient Systems, Networks and Technologies Networks (ANT)/ the 8th International Conference on Emerging Data and Industry 4.0, 826-833. Doi: https://doi.org/10.1016/j.procs.2025.03.106
  53. Westermann, P. ve Evins, R. (2019). Surrogate modelling for sustainable building design – A review. Energy and Buildings, 198, 170-186. Doi: https://doi.org/10.1016/j.enbuild.2019.05.057
  54. Wu, Y. (2022). Warehouse layout optimization based on EIQ Model. International Core Journal of Engineering, 8(1), 153–159. Doi: https://doi.org/10.6919/ICJE.202201_8(1).0022
  55. Xie, W., Nelson, B. L. ve Barton, R. R. (2014). A Bayesian framework for quantifying uncertainty in stochastic simulation. Operations Research. Doi: https://doi.org/10.1287/opre.2014.1316
  56. Zeng, Y., Li, W. ve Li, C. (2024). A dynamic simulation framework based on hybrid modeling paradigm for parallel scheduling systems in warehouses. simulation modelling, Practice and Theory, 133, 102921. DOi: https://doi.org/10.1016/j.simpat.2024.102921
  57. Zhang, G., Nishi, T., Turner, S. D. O., Oga, K. ve Li, X. (2017). An integrated strategy for a production planning and warehouse layout problem: Modeling and solution approaches. Omega, 68, 85-94. Doi: https://doi.org/10.1016/j.omega.2016.06.005
  58. Zorn, M., Catunda, N., Claus, L., Kobylinska, N., Frey, M. ve Wortmann, T. (2022). Replacing energy simulations with surrogate models for design space exploration. Bauphysik, 44, 311-316. Doi: https://doi.org/10.1002/bapi.202200034
  59. Moin Uddin Mojumder ve Md. Nuruzzaman. (2025). AI-driven optimization of warehouse layout and material handling: a quantitative study on efficiency and space utilization. Review of Applied Science and Technology, 4(02), 233-273. Doi: https://doi.org/10.63125/bgxb1z53
  60. Sevin, A., Yaman, G. ve Atilgan, D. (2025). Analysis of Queue models in simulation applications. Sakarya University Journal of Computer and Information Sciences, 8(1), 123-135. Doi: https://doi.org/10.35377/saucis.1610018