Strategi Optimasi Antrian SPKLU dengan Algoritma Genetika untuk Mengurangi Waktu Tunggu dan Ketidakseimbangan Slot
DOI:
https://doi.org/10.46962/snte.25.067Keywords:
Kendaraan listrik, SPKLU, Genetic Algorithm, optimasi beban, sistem antrianAbstract
Pertumbuhan penggunaan kendaraan listrik (EV) memicu kebutuhan akan sistem manajemen Stasiun Pengisian Kendaraan Listrik Umum (SPKLU) yang efisien, khususnya dalam mengoptimalkan penjadwalan pengisian dan pemerataan beban antar stasiun. Penelitian ini mengusulkan penerapan Genetic Algorithm (GA) untuk mengoptimalkan penugasan EV ke SPKLU dengan mempertimbangkan jarak, perkiraan waktu tiba (Estimated Time of Arrival), kapasitas slot, dan durasi pengisian. Metode ini dibandingkan dengan pendekatan konvensional tanpa AI yang hanya mengandalkan jarak terdekat. Dataset yang digunakan bersifat sintetis, mencakup 30 EV dan 6 SPKLU dengan kapasitas slot bervariasi (5–7 slot). Simulasi dijalankan menggunakan pestimasi waktu ketibaan OpenRouteService untuk perhitungan jarak dan waktu tempuh aktual. Hasil menunjukkan bahwa GA mampu menurunkan rata-rata waktu tunggu EV sebesar 64,4% (dari 11,8 menit menjadi 4,2 menit), mempercepat total waktu penyelesaian dari 410 menit menjadi 320 menit, serta mengurangi variansi utilisasi slot antar SPKLU sebesar 67,86%. Temuan ini membuktikan bahwa GA tidak hanya meningkatkan efisiensi operasional, testimasi waktu ketibaanpi juga memeratakan beban infrastruktur pengisian. Penelitian ini memberikan kontribusi terhadap pengembangan strategi optimasi SPKLU berbasis AI dan membuka peluang untuk penerapan realtime dengan integrasi data lalu lintas dinamis.
References
. IEA, “Global EV Outlook 2023,” International Energy Agency, 2023.
. BloombergNEF, “Electric Vehicle Outlook 2023,” Bloomberg Finance L.P., 2023.
. Presiden Republik Indonesia, “Peraturan Presiden Republik Indonesia Nomor 55 Tahun 2019 Tentang Percepatan
Program Kendaraan Bermotor Listrik Berbasis Baterai,” 2019.
. X. Zhang, et al., “Charging Infrastructure Planning for Promoting Electric Vehicles: An Activity-Based Approach Using GPS Data,” Transportation Research Part C, vol. 52, pp. 255–276, 2015.
. H. Li, et al., “Optimal Deployment of Charging Stations for Electric Vehicles Considering Traffic and User Behavior,” Energy, vol. 150, pp. 735–744, 2018.
. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, 2018.
. D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.
. J. H. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
. IEA, “Global EV Outlook 2023,” International Energy Agency, 2023.
. BloombergNEF, “Electric Vehicle Outlook 2023,” Bloomberg Finance L.P., 2023.
. T. Gnann, et al., “Fast charging infrastructure for electric vehicles: Today’s situation and future needs,” Transp. Res. Part D, vol. 62, pp. 314–329, 2018.
. Z. Chen, et al., “Deployment of electric vehicle charging stations: A spatial-temporal planning approach,” Energy, vol. 195, 2020.
. X. Yang, et al., “Queueing Analysis and Optimization of EV Charging Stations,” IEEE Trans. ITS, vol. 22, no. 8, pp. 4985–4996, 2021.
. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, 2018.
. H. Zhao, et al., “Priority-based charging strategies for EVs,” Applied Energy, vol. 239, pp. 390–402, 2019.
. J. Wu, et al., “Load balancing strategy for EV charging stations,” IEEE Access, vol. 8, pp. 102743–102753, 2020.
. F. Wang, et al., “Multi-objective optimization for EV charging station placement,” IEEE Trans. Smart Grid, 2020.
. D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.
. J. H. Holland, Adaptation in Natural and Artificial Systems, Univ. of Michigan Press, 1975.
. S. Tan, et al., “VRP with time windows based on GA,” Procedia Computer Science, 2022.
. M. Gen, R. Cheng, and L. Lin, “Multi-objective GA for production scheduling,” Springer, 2021.
. Y. Sun, et al., “GA for distribution network reconfiguration,” IEEE Trans. Power Systems, 2019.
. Y. Liu, et al., “Real-time EV charging scheduling using GA,” IEEE Access, 2019.
. Z. Chen, et al., “ML + GA for smart charging of EVs,” Applied Energy, 2020.
. OpenRouteService, “API Documentation,” Heidelberg Institute for Geoinformation Technology, 2023.
. M. Zilske, et al., “Using OpenStreetMap and ORS for accessibility analyses,” J. Transport Geography, vol. 73, pp. 72–80, 2018.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Seminar Nasional Teknik Elektro
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
