Regression-Supported Optimal Location Of Electric Vehicle Charging Stations on The IEEE-33 Bus Distribution System

Öz

In this study, the technical impacts of electric vehicle charging stations on distribution systems were analyzed, and optimal placement combinations were determined. Load flow analyses were conducted on the IEEE-33 bus test system under various charging scenarios, and a multi-criteria fitness function was developed based on minimum voltage (Vmin), maximum line loading (Lmax), total reactive power (Qtotal), and active power loss (Ploss) parameters. Using simulation data, a regression model was trained to estimate fitness scores for different combinations. The combination with the highest score was selected as the optimal placement and evaluated in terms of system performance. As a result of scenario analyzes, it was observed that loading on the bars significantly affected system performance; in particular, it was determined that loading at the system's weak points had negative impacts on voltage drop and losses. In this context, Scenarios 2, 3, and 5 were identified as the most successful layouts, yielding more balanced results in terms of system voltage profile and losses.

Anahtar Kelimeler

• Charging station
• distribution system
• optimization
• fitness
• regression.

IEEE-33 Bara Dağıtım Sistemi Üzerinde Elektrikli Araç Şarj İstasyonlarının Regresyon Destekli Konumlandırılması

Öz

Bu çalışmada, elektrikli araç şarj istasyonlarının dağıtım sistemleri üzerindeki teknik etkileri incelenmiş ve optimum yerleşim kombinasyonlarının belirlenmesi amaçlanmıştır. IEEE-33 baralı test sistemi üzerinde tanımlanan senaryolar için yük akışı analizleri gerçekleştirilmiş; minimum gerilim(Vmin), maksimum hat yüklenmesi (Lmax), toplam reaktif güç(Qtop) ve aktif güç kaybı(Pkayıp) parametreleri üzerinden çok kriterli bir fitness fonksiyonu oluşturulmuştur. Simülasyon verileri kullanılarak regresyon modeli eğitilmiş ve farklı kombinasyonlar için tahmini fitness skorları hesaplanmıştır. En yüksek skora sahip kombinasyon optimum yerleşim olarak seçilmiş ve sistem performansı açısından değerlendirilmiştir. Senaryo analizleri sonucunda, baralara yapılan yüklemenin sistem performansını ciddi biçimde etkilediği görülmüş; özellikle sistemin zayıf noktalarında yapılan yüklemelerin gerilim düşümü ve kayıplar üzerinde olumsuz etkiler oluşturduğu tespit edilmiştir. Bu kapsamda Senaryo 2, 3 ve 5 en başarılı yerleşimler olarak belirlenmiş; sistem gerilim profili ve kayıplar açısından daha dengeli sonuçlar elde edilmiştir.

Anahtar Kelimeler

• Şarj istasyonu
• dağıtım sistemi
• optimizasyon
• fitness
• regresyon.

Kaynakça

1. [1] M. Jamei, M. Zeynal, A. Dey, A. Maroufmashat ve M. Fowler, “Review on placement of EV charging station using optimization methods,” Renewable and Sustainable Energy Reviews, Vol. 157, pp.112034, 2022.
2. [2] M. R. Hossain, S. M. Muyeen ve A. Al-Durra, “Minimization of power losses and improvement of voltage profile using optimal placement of EV charging stations,” Sustainable Cities and Society, Vol. 65, pp: 102610, 2021.
3. [3] International Energy Agency (IEA), Global EV Outlook 2022, [Çevrimiçi]. Erişim adresi: https://www.iea.org/reports/global-ev-outlook-2022 [Erişim tarihi: 27 Mayıs 2025].
4. [4] D. Singh, V. Singh ve A. Verma, “Optimal placement of EV charging station in distribution network using multi-objective optimization,” IEEE Transactions on Industrial Informatics, Vol. 17, No. 5, pp. 3050–3058, 2021.
5. [5] A. Y. Saber ve G. K. Venayagamoorthy, “Plug-in vehicles and renewable energy sources for cost and emission reductions,” IEEE Transactions on Industrial Electronics, Vol. 58, No. 4, pp. 1229–1238, 2011.
6. [6] R. C. Bansal, “Optimization methods for electric vehicle charging station placement: A review,” Electric Power Systems Research, Vol. 190, pp. 106666, 2021.
7. [7] J. J. Escalera, G. Jiménez-Estévez, A. Vargas and J. Troncoso, “Electric Vehicle Infrastructure: An Overview,” Renewable and Sustainable Energy Reviews, Vol. 135, pp. 110120, 2020.
8. [8] Z. Darabi ve M. Ferdowsi, “Aggregated impact of plug-in hybrid electric vehicles on electricity demand profile,” IEEE Transactions on Sustainable Energy, Vol. 2, No. 4, pp. 501–508, 2011.

9. [9] X. Zhang, Y. Wang, X. Wu, M. Xiao ve H. Zhang, “Ultra-fast charging of electric vehicles: A review,” Journal of Power Sources, Vol. 435, pp. 226701, 2019.
10. [10] H. Hu, C. Zhu, H. Zhang, Y. Yang ve Z. Lu, “Wireless power transfer for electric vehicle applications,” IEEE Transactions on Industrial Electronics, Vol. 63, No. 10, pp. 6530–6545, 2016.
11. [11] International Electrotechnical Commission (IEC), IEC 61851-1 Ed.2: Electric Vehicle Conductive Charging System, Geneva, 2010.
12. [12] S. Rajper, T. Khokhar, M. M. Ahmed ve R. Mahfooz, “A review of electric vehicle charging standards and infrastructure,” Environmental Science and Pollution Research, Vol. 28, pp. 26713–26731, 2021.
13. [13] M. Dabbaghjamanesh, M. Shahabi ve A. Etemadi, “Review of fast charging station technologies for electric vehicles,” IEEE Transactions on Transportation Electrification, Vol. 7, No. 4, pp. 1096–1111, 2021.
14. [14] A. N. Hussain, M. M. Billah, A. Mahmud, “Impact of electric vehicles on power systems: A review,” Sustainable Cities and Society, Vol. 55, pp. 102022, 2020.
15. [15] P. Richardson, D. Flynn ve A. Keane, “Impact assessment of EV charging on distribution networks,” IEEE Transactions on Power Systems, Vol. 26, No. 1, pp. 76–84, 2011.
16. [16] J. Li, L. Wu ve Z. Zhou, “Optimal siting and sizing of electric vehicle charging stations considering urban traffic characteristics,” Journal of Cleaner Production, vol. 279, p. 123882, 2021.
17. [17] A. Maleki, S. Ghafouri, R. Kazemzadeh, “A comprehensive review on criteria for electric vehicle charging station placement,” Energy Reports, Vol. 8, pp. 3606–3624, 2022.
18. [18] T. Zhang, Y. Chen, X. Liu, “Multi-objective optimization for electric vehicle charging station siting using LSTM and DGGO,” Frontiers in Energy Research, Vol. 12, 2024.
19. [19] W. Wu, Q. Liu ve H. Wang, “Optimization of EV fast charging location based on war strategy optimization,” Scientific Reports, Vol. 14, pp: 72428, 2024.
20. [20] S. Lee, M. Kim ve J. Park, “Blockchain-Based Peer-to-Peer Energy Trading for Microgrid Applications,” IEEE Access, Vol. 11, pp. 39471–39483, 2023.
21. [21] A. T. Binh, J. Y. Lee, “AI-based prediction models for EV siting in urban networks,” Energy Reports, Vol. 9, pp. 4400–4415, 2023.
22. [22] N. G. Mohamed, S. Kumar, “GIS-based planning of EV charging stations: A spatial analysis approach,” Journal of Cleaner Transport, Vol. 5, pp: 101–110, 2022.
23. [23] R. K. Sharma, T. S. Bhatti, “Vehicle-to-grid systems in modern power networks: A stability perspective,” IEEE Transactions on Smart Grid, Vol. 13, No. 1, pp. 243–252, 2022.
24. [24] H. F. Kang, “Comparative study of EV infrastructure regulations in OECD countries,” Energy Policy, Vol. 168, pp. 113134, 2022.
25. [25] L. P. Martins, D. Silva, “Community engagement in electric mobility planning,” Renewable Energy Focus, Vol. 43, pp: 11–19, 2023.
26. [26] S. Patel, Y. Huang, “Short-term EV charging load forecasting using hybrid LSTM models,” Electric Power Systems Research, Vol. 208, pp: 107987, 2023.
27. [27] C. D. Nguyen, M. A. Rahman, “Energy efficiency considerations in EV charger location optimization,” Applied Energy, Vol. 306, pp. 117986, 2022.
28. [28] S. Choudhury, A. Aurnab, S. M. R. Abrar, S. Roy Ruhan, S. M. R. H. Rabbi, R. A. Khan, "Comparative analysis of machine learning techniques in optimal site selection," 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar, Bangladesh, pp. 1-6, 2023.
29. [29] M. Al-Sharif, L. Zhang, “Urban mobility data analytics for EV station planning,” Sustainable Cities and Society, Vol. 85, pp. 104030, 2023.