Time-Plan Optimization with Genetic Algorithm for Regain of Energy from Train Tracks

Yıl 2021, Cilt: 26 Sayı: 1, 187 - 202, 30.04.2021

Büşra Tural , Metin Turan , İbrahim Ethem Demirci

https://doi.org/10.17482/uumfd.687214

Öz

In this article, the research results for optimizing the maximum energy gain are shared by adapting the time plan of Metro Istanbul vehicles. Regenerative energy recovery is based on the principle that energy produced by the trains which make electromagnetic brake is transferred to the other trains that are ready to move. One of the ways to re-energize is to arrange the waiting times of the trains at the stations and to realize the time-plan optimization. Genetic algorithm was used to find station dwell times. Genetic algorithms are search and optimization methods that work similarly to the evolutionary process. This method is based on seeking the best solution according to the principle of survival of the best in multidimensional and complex space. At the end of each repetition, several of the best elite individuals were transferred to the next generation. For each repetition, the number of society individuals has been kept constant, while other individuals have been formed by crossing elite individuals or producing them randomly. Aggressive mutation was applied in cases where the change in station waiting times was not equal to zero. Result in of the simulation, around 26% better results compared to the reference study was obtained.

Anahtar Kelimeler

Regain of Energy, Subway Time-Table, Genetic Algorithm

TREN RAYLARINDAN ENERJİNİN GERİ KAZANIMI İÇİN GENETİK ALGORİTMA İLE ZAMAN-PLANI OPTİMİZASYONU

Öz

Bu makalede, Metro İstanbul araçlarından zaman planı uyarlanarak maksimum enerji kazanımının optimize edilmesine yönelik araştırma sonuçları paylaşılmıştır. Yeniden enerji kazanımı (rejeneratif enerji), elektromanyetik frenleme yapan trenlerin ürettiği enerjiyi hatta hareket etmeye hazır durumunda bulunan diğer trenlere aktarması prensibine dayanmaktadır. Yeniden enerji kazanımı elde etmenin en etkili yollarından birisi, trenlerin istasyonlarda bekleme sürelerinde düzenleme yaparak zaman-planı en iyileştirmesinin gerçekleştirilmesidir. Bu oldukça karışık ve elle yapılması mümkün olmayan bir NP problemi olduğundan bu çalışmada bekleme sürelerini bulmak için genetik algoritma kullanılmıştır. Genetik algoritmalar, evrimsel sürece benzer şekilde çalışan arama ve en iyileştirme yöntemidir. Bu yöntem çok boyutlu ve karmaşık uzayda en iyinin hayatta kalması ilkesine göre en iyi çözümü aramaya dayanır. Her tekrar sonunda en iyi birkaç elit birey bir sonraki nesle aktarılmıştır. Her tekrarda toplam birey sayısı sabit tutulmuş, diğer bireyler ise elit bireylerin çaprazlanması sonucu veya rastgele üretilmesiyle oluşturulmuştur. Agresif mutasyon işlemi, istasyon bekleme sürelerindeki değişimin sıfıra eşit olmadığı durumlarda uygulanmıştır. Yapılan simülasyon sonucunda, genetik algoritma ile elde edilen yeni bekleme süreleriyle trenlerin hızlanma ve frenleme anlarındaki örtüşme, referans çalışmaya göre %26 civarında daha iyi sonuçlar elde edilmiştir. Referans çalışmada %60 oranında olan trenlerin örtüşme anları bu çalışma ile %76 ‘ya kadar çıkartılmıştır.

Anahtar Kelimeler

Yeniden Enerji Kazanımı, Metro Zaman Planı, Genetik Algoritma

Kaynakça

• Açıkbaş, S. (2008). Çok hatlı çok araçlı raylı sistemlerde enerji tasarrufuna yönelik sürüş kontrolü (Doctoral dissertation, Fen Bilimleri Enstitüsü).
• Açıkbaş, S. ve Alataş A., 2006: Rayli Sistemlerde Enerji Verimli Sürüş. In Türkiye 10. Enerji Kongresi, 29 Kasım
• Açıkbaş, S., & Söylemez, M. T. (2004). Energy loss comparison between 750 VDC and 1500 VDC power supply systems using rail power simulation. Computers in Railways IX, 951-960. doi: 10.2495/CR040951
• Adinolfi, A., Lamedica, R., Modesto, C., Prudenzi, A., & Vimercati, S. (1998). Experimental assessment of energy saving due to trains regenerative braking in an electrified subway line. IEEE Transactions on Power Delivery, 13(4), 1536-1542. doi: 10.1109/61.714859
• Albert, H., Levin, C., Vietrose, E., & Witte, G. (1995). Reducing energy consumption in underground systems.
• Albrecht, T. (2010). Reducing power peaks and energy consumption in rail transit systems by simultaneous train running time control. WIT Transactions on State-of-the-art in Science and Engineering, 39. doi:10.2495/978-1-84564-498-7/01
• Amit, I., & Goldfarb, D. (1971). The timetable problem for railways. Developments in Operations Research, 2(1), 379-387.
• Asnis, I. A., Dmitruk, A. V., & Osmolovskii, N. P. (1985). Solution of the problem of the energetically optimal control of the motion of a train by the maximum principle. USSR Computational Mathematics and Mathematical Physics, 25(6), 37-44. doi: 10.1016/0041-5553(85)90006-0
• Büşra. (2021). Time-Plan Optimization with Genetic Algorithm for Regain of Energy from Train Tracks [Data set]. Zenodo. doi: http://doi.org/10.5281/zenodo.4467528
• Chen, J. F., Lin, R. L., & Liu, Y. C. (2005). Optimization of an MRT train schedule: reducing maximum traction power by using genetic algorithms. IEEE Transactions on power systems, 20(3), 1366-1372. doi: 10.1109/TPWRS.2005.851939
• Cornic, D. (2010, October). Efficient recovery of braking energy through a reversible dc substation. In Electrical systems for aircraft, railway and ship propulsion (pp. 1-9). IEEE. doi: 10.1109/ESARS.2010.5665264
• Demirci, I. E., & Celikoglu, H. B. (2018, November). Timetable Optimization for Utilization of Regenerative Braking Energy: A Single Line Case over Istanbul Metro Network. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC) (pp. 2309-2314). IEEE. doi: 10.1109/ITSC.2018.8569553
• Ghoseiri, K., Szidarovszky, F., & Asgharpour, M. J. (2004). A multi-objective train scheduling model and solution. Transportation research part B: Methodological, 38(10), 927-952. doi :10.1016/j.trb.2004.02.004
• Goldberg, D. E. (1989). Genetic algorithms in search. Optimization, and MachineLearning.
• Gonzalez, E. L., & Fernandez, M. A. R. (2000). Genetic optimisation of a fuzzy distribution model. International Journal of Physical Distribution & Logistics Management. doi: 10.1108/09600030010346440
• González-Gil, A., Palacin, R., Batty, P., & Powell, J. P. (2014). A systems approach to reduce urban rail energy consumption. Energy Conversion and Management, 80, 509-524. doi: 10.1016/j.enconman.2014.01.060
• Gordon, S. P., & Lehrer, D. G. (1998, April). Coordinated train control and energy management control strategies. In Proceedings of the 1998 ASME/IEEE Joint Railroad Conference (pp. 165-176). IEEE. doi: 10.1109/RRCON.1998.668103
• Gunselmann, W. (2005, September). Technologies for increased energy efficiency in railway systems. In 2005 European Conference on Power Electronics and Applications (pp. 10-pp). IEEE. doi: 10.1109/EPE.2005.219712
• He, D., Yang, Y., Chen, Y., Deng, J., Shan, S., Liu, J., & Li, X. (2020). An integrated optimization model of metro energy consumption based on regenerative energy and passenger transfer. Applied Energy, 264, 114770. doi: 10.1016/j.apenergy.2020.114770
• Higgins, A., Kozan, E., & Ferreira, L. (1996). Optimal scheduling of trains on a single line track. Transportation research part B: Methodological, 30(2), 147-161. doi: 10.1016/0191-2615(95)00022-4
• Holland, J. H. (1992). Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press.
• Jong, J. C., & Chang, E. F. (2005). Models for estimating energy consumption of electric trains. Journal of the Eastern Asia Society for Transportation Studies, 6, 278-291. doi: 10.11175/easts.6.278
• Kampeerawat, W., & Koseki, T. (2017). A strategy for utilization of regenerative energy in urban railway system by application of smart train scheduling and wayside energy storage system. Energy Procedia, 138, 795-800. doi: 10.1016/j.egypro.2017.10.070
• Martin, P., 1999: Train performance and simulation. In Winter Simulation Conference. doi: 10.1109/WSC.1999.816799
• Murata, T., Ishibuchi, H., & Tanaka, H. (1996). Genetic algorithms for flowshop scheduling problems. Computers & Industrial Engineering, 30(4), 1061-1071. doi: 10.1016/0360-8352(96)00053-8
• Nasri, A., Moghadam, M. F., & Mokhtari, H. (2010, June). Timetable optimization for maximum usage of regenerative energy of braking in electrical railway systems. In SPEEDAM 2010 (pp. 1218-1221). IEEE. doi: 10.1109/SPEEDAM.2010.5542099
• Peña-Alcaraz, M., Fernández, A., Cucala, A. P., Ramos, A., & Pecharromán, R. R. (2012). Optimal underground timetable design based on power flow for maximizing the use of regenerative-braking energy. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 226(4), 397-408. doi: 10.1177/0954409711429411
• Ramos, A., Pena, M. T., Fernández, A., & Cucala, P. (2008). Mathematical programming approach to underground timetabling problem for maximizing time synchronization. Dirección y Organización, (35), 88-95.
• Syswerda, G. (1991). Scheduling optimization using genetic algorithms. Handbook of genetic algorithms.
• UITP, 2005: The Cost Of Energy And How To Reduce It, Lisbon.
• Wong, K. K., & Ho, T. K. (2004). Dynamic coast control of train movement with genetic algorithm. International journal of systems science, 35(13-14), 835-846. doi:10.1080/00207720412331203633
• Xu, X., Li, K., Li, X., (2016). A Multi‐Objective Subway Timetable Optimization Approach With Minimum Passenger Time And Energy Consumption. Journal of Advanced Transportation, 50(1), 69-95. doi: 10.1002/atr.1317
• Yang, A., Huang, J., Wang, B., & Chen, Y. (2019). Train scheduling for minimizing the total travel time with a skip-stop operation in urban rail transit. IEEE Access, 7, 81956-81968. doi: 10.1109/ACCESS.2019.2923231
• Yang, L., Li, K., & Gao, Z. (2008). Train timetable problem on a single-line railway with fuzzy passenger demand. IEEE Transactions on fuzzy systems, 17(3), 617-629. doi: 10.1109/TFUZZ.2008.924198
• Yang, X., Li, X., Gao, Z., Wang, H., & Tang, T. (2012). A cooperative scheduling model for timetable optimization in subway systems. IEEE Transactions on Intelligent Transportation Systems, 14(1), 438-447. doi: 10.1109/TITS.2012.2219620
• Yang, X., Ning, B., Li, X., & Tang, T. (2014). A two-objective timetable optimization model in subway systems. IEEE Transactions on Intelligent Transportation Systems, 15(5), 1913-1921. doi: 10.1109/TITS.2014.2303146
• Yeo, M. F., & Agyei, E. O. (1998). Optimising engineering problems using genetic algorithms. Engineering Computations. doi: 10.1108/02644409810202684
• Zou, B., Gong, L., Yu, N., & Chen, J. (2018). Intelligent scheduling method for energy saving operation of multi-train based on genetic algorithm and regenerative kinetic energy. The Journal of Engineering, 2018(16), 1550-1554. doi: 10.1049/joe.2018.8273