Simulating hydropower reservoir operations of the Yamula Dam with machine learning

Yıl 2023, Cilt: 12 Sayı: 4, 1426 - 1435, 15.10.2023

Mustafa Şahin Doğan

https://doi.org/10.28948/ngumuh.1314793

Öz

Large-scale reservoirs provide operational flexibility to water managers by storing water during times with higher surface water availability and releasing water when it is most needed. Most large-scale reservoirs serve for multipurpose demands, such as water supply for agricultural, urban and environmental users, hydropower, recreation, fisheries and transportation. Due to its low operating cost, hydropower generation is often maximized in energy systems with mixed hydro and thermal sources. Hydropower generation is also used to meet peak demand by advantage of operating in short notice. This study aims to simulate reservoir operations, including release schedule and hydropower operations of the Yamula Dam and hydropower plant using machine learning. Located on the Kızılırmak River, the Yamula Dam is a large-scale multipurpose reservoir with its 3476 million cubic meters of storage capacity. Turbine release decisions are learned with Random Forests algorithm using only reservoir inflow and upstream streamflow conditions. The developed model successfully predicts reservoir releases between 2006 and 2015, with a coefficient of determination value of 0.87. Model prediction results are provided, and then hydropower load, generation and revenue are calculated and results are presented. Based on simulation results, the Yamula Dam generates about 362.3 gigawatts hour of energy per year, with an annual average revenue of 14.1 million Dollars. With the developed model, reservoir operations under different upstream hydrological conditions can also be simulated.

Anahtar Kelimeler

reservoir operations, water management, hydropower, machine learning, random forests

Yamula Barajının hidroelektrik rezervuar işletiminin makine öğrenimi ile simülasyonu

Öz

Büyük depolama kapasiteli rezervuarlar yüzey suyunun fazlaca bulunduğu zamanlarda suyu depolayarak ve su ihtiyacının en yüksek olduğu zamanlarda bu depolanan suyu sisteme vererek suyu yönetenlere işletim esnekliği sağlar. Büyük kapasiteli rezervuarlar çoğunlukla tarımsal, kentsel ve çevresel su ihtiyaçlarının temini, hidroelektrik, rekreasyon, balıkçılık ve ulaşım gibi birden çok amaca hizmet ederler. Düşük işletim maliyetinden dolayı hidroelektrik üretimi, hidro ve termik karışık enerji sistemlerinde genellikle maksimize edilir. Hidroelektrik üretim kısa sürede işletime alınma avantajından dolayı pik saatlerdeki talebi karşılamak için de kullanılır. Bu çalışma Yamula Barajı ve hidroelektrik santralinin türbin akış zamanlaması ve hidroelektrik operasyonlarını içeren rezervuar işletimini makine öğrenimini kullanarak simüle etmeyi amaçlamaktadır. Kızılırmak Nehri üzerinde yer alan Yamula Barajı 3476 milyon metreküp depolama kapasitesiyle birden çok amaca hizmet eden büyük ölçekli bir barajdır. Rastgele Karar Ormanları algoritması ile sadece rezervuara giren akım ve memba akım koşullarına göre türbin akımı kararları öğrenilmiştir. Geliştirilen model 2006 ve 2015 yılları arasındaki türbin akımlarını, 0.87 korelasyon katsayısı ile, başarılı bir şekilde tahmin edebilmektedir. Model tahmini sonuçları gösterilmiş ve ayrıca hidroelektrik enerjisi üretimi ve getirisi hesaplanmış ve sonuçlar sunulmuştur. Simülasyon sonuçlarına göre Yamula barajı yılda yaklaşık 362.3 gigawatt saat enerji üretmekte ve 14.1 milyon dolar gelir sağlamaktadır. Geliştirilen model ile farklı memba hidrolojik durumlarına göre rezervuar işletim simülasyonları da yapılabilmektedir.

Anahtar Kelimeler

rezervuar işletimi, su yönetimi, hidroelektrik, makine öğrenimi, rastgele karar ormanları

Kaynakça

• M. S. Dogan, Hydropower generation in the era of renewables and climate change. Ph.D. Thesis, University of California, Davis, California, USA, 2019.
• K. Madani, M. Guégan and C. B. Uvo, Climate change impacts on high-elevation hydroelectricity in California. Journal of Hydrology, 510,153-163, 2014. https://doi.org/10.1016/j.jhydrol.2013.12.001.
• A. F. Hamlet, D. Huppert and D. P. Lettenmaier, Economic value of long-lead streamflow forecasts for Columbia River hydropower. Journal of Water Resources Planning and Management, 128 (2), 91-101, 2002. https://doi.org/10.1061/(ASCE)0733-9496(2002)128:2(91).
• B. Chatterjee, R. E. Howitt and R. J. Sexton, The optimal joint provision of water for irrigation and hydropower. Journal of Environmental Economics and Management, 36 (3), 295-313, 1998. https://doi.org/10.1006/jeem.1998.1047.
• P. Côté and R. Leconte, Comparison of stochastic optimization algorithms for hydropower reservoir operation with ensemble streamflow prediction. Journal of Water Resources Planning and Management, 142 (2), 04015046, 2016. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000575.
• J. Li, Y. Zhang, C. Ji, A. Wang and J. R. Lund, Large-scale hydropower system optimization using dynamic programming and object-oriented programming: the case of the Northeast China Power Grid. Water Science & Technology, 68 (11), 2458, 2013. https://doi.org/10.2166/wst.2013.528.
• T. Yang, X. Gao, S. Sorooshian and X. Li, Simulating California reservoir operation using the classification and regression‐tree algorithm combined with a shuffled cross‐validation scheme. Water Resources Research, 52 (3), 1626-1651, 2016. https://doi.org/10.1002/2015WR017394.
• W. Zhang, H. Wang, Y. Lin, J. Jin, W. Liu and X. An, Reservoir inflow predicting model based on machine learning algorithm via multi-model fusion: A case study of Jinshuitan river basin. IET Cyber-systems Robotics, 3 (3), 265-277. 2021. https://doi.org/10.1049/csy2.12015.
• Y. Liu, H. Qin, Z. Zhang, L. Yao, Y. Wang, J. Li, G. Liu and J. Zhou, Deriving reservoir operation rule based on Bayesian deep learning method considering multiple uncertainties. Journal of Hydrology, 579, 124207, 2019. https://doi.org/10.1016/j.jhydrol.2019.124207.
• A. J. Draper, A. Munévar, S. K. Arora, E. Reyes, N. L. Parker, F. I. Chung and L. E. Peterson, CalSim: Generalized model for reservoir system analysis. Journal of Water Resources Planning and Management, 130 (6), 480-489, 2004. https://doi.org/10.1061/(ASCE)0733-9496(2004)130:6(480).
• R. Oliveira and D. P. Loucks, Operating rules for multireservoir systems. Water Resources Research, 33 (4), 839-852, 1997. https://doi.org/10.1029/96WR03745.
• J. R. Lund and J. Guzman, Derived Operating Rules for Reservoirs in Series or in Parallel. Journal of Water Resources Planning and Management, 125 (3), 143-153, 1999. https://doi.org/10.1061/(ASCE)0733-9496(1999)125:3(143).
• T. Nelson, R. Hui, J. R. Lund and J. Medellín-Azuara, Reservoir operating rule optimization for California’s Sacramento Valley. San Francisco Estuary and Watershed Sciences, 14 (1), 2016. https://doi.org/10.15447/sfews.2016v14iss1art6.
• H. Chu, J. Wei, W. Wu, Y. Jiang, Q. Chu and X. Meng, A classification-based deep belief networks model framework for daily streamflow forecasting. Journal of Hydrology, 595, 125967, 2021. https://doi.org/10.1016/j.jhydrol.2021.125967.
• L. E. Besaw, D. M. Rizzo, P. R. Bierman and W. R. Hackett, Advances in ungauged streamflow prediction using artificial neural networks. Journal of Hydrology, 386 (1-4), 27-37, 2010. https://doi.org/10.1016/j.jhydrol.2010.02.037.
• N. Noori and L. Kalin, Coupling SWAT and ANN models for enhanced daily streamflow prediction. Journal of Hydrology, 533, 141-151, 2016. https://doi.org/10.1016/j.jhydrol.2015.11.050.
• T. R. Petty and P. Dhingra, Streamflow hydrology estimate using machine learning (SHEM). Journal of the American Water Resources Association, 54 (1), 55-68, 2018. https://doi.org/10.1111/1752-1688.12555.
• R. M. Adnan, Z. Liang, S. Trajkovic, M. Zounemat-Kermani, B. Li and O. Kisi, Daily streamflow prediction using optimally pruned extreme learning machine. Journal of Hydrology, 577, 123981, 2019. https://doi.org/10.1016/j.jhydrol.2019.123981.
• Y. Li, Z. Liang, Y. Hu, B. Li, B. Xu and D. Wang, A multi-model integration method for monthly streamflow prediction: Modified stacking ensemble strategy. Journal of Hydroinformatics, 22 (2), 310-326, 2020. https://doi.org/10.2166/hydro.2019.066.
• A. Kumar, R. Ramsankaran, L. Brocca and F. Muñoz-Arriola, A simple machine learning approach to model real-time streamflow using satellite inputs: Demonstration in a data scarce catchment. Journal of Hydrology, 595, 2021. https://doi.org/10.1016/j.jhydrol.2021.126046.
• Y. Lin, D. Wang, G. Wang, J. Qiu, K. Long, Y. Du, H. Xie, Z. Wei, W. Shangguan and Y. Dai, A hybrid deep learning algorithm and its application to streamflow prediction. Journal of Hydrology. 601, 1-10, 2021. https://doi.org/10.1016/j.jhydrol.2021.126636.
• W. Xu, J. Chen, X. J. Zhang, L. Xiong and H. Chen, A framework of integrating heterogeneous data sources for monthly streamflow prediction using a state-of-the-art deep learning model. Journal of Hydrology, 614, 128599, 2022. https://doi.org/10.1016/j.jhydrol.2022.128599.
• M. S. Dogan, Estimating streamflow of the Kızılırmak River, Turkey with single- and multi-station datasets using Random Forests. Water Science & Technology, 87 (11), 2742-2755 2023. https://doi.org/10.2166/wst.2023.171.
• T. Yang, A. A. Asanjan, E. Welles, X. Gao, S. Sorooshian and X. Liu, Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information. Water Resources Research, 53 (4), 2786-2812, 2017. https://doi.org/10.1002/2017WR020482.
• D. Zhang, J. Lin, Q. Peng, D. Wang, T. Yang, S. Sorooshian, X. Liu and J. Zhuang, Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm. Journal of Hydrology, 565, 720-736, 2018. https://doi.org/10.1016/j.jhydrol.2018.08.050.
• Z. C. Herbert, Z. Asghar and C. Oroza, Long-term reservoir inflow forecasts: Enhanced water supply and inflow volume accuracy using deep learning. Journal of Hydrology, 601, 126676, 2021. https://doi.org/10.1016/j.jhydrol.2021.126676.
• A. Khalil, M. McKee, M. Kemblowski and T. Asefa, Sparse Bayesian learning machine for real-time management of reservoir releases. Water Resources Research, 41 (11), 1-15, 2005. https://doi.org/10.1029/2004WR003891.
• S. Gangrade, D. Lu, S. C. Kao and S. L. Painter, Machine learning assisted reservoir operation model for long-term water management simulation. Journal of the American Water Resources Association, 58 (6), 1592-1603, 2022. https://doi.org/10.1111/1752-1688.13060.
• G. Qie, Z. Zhang, E. Getahun and E. A. Mamer, Comparison of machine learning models performance on simulating reservoir outflow: A case study of two reservoirs in Illinois, U.S.A. Journal of the American Water Resources Association, 59, 554-570, 2022. https://doi.org/10.1111/1752-1688.13040.
• J. D. Herman and M. Giuliani, Policy tree optimization for threshold-based water resources management over multiple timescales. Environmental Modelling & Software, 99, 39-51, 2018. https://doi.org/10.1016/j.envsoft.2017.09.016.
• G. Özdoğan-Sarıkoç, M. Sarıkoç, M. Celik and F. Dadaser-Celik, Reservoir volume forecasting using artificial intelligence-based models: Artificial Neural Networks, Support Vector Regression, and Long Short-Term Memory. Journal of Hydrology, 616, 2023. https://doi.org/10.1016/j.jhydrol.2022.128766.
• Ayan Enerji, Yamula Hidro Elektrik Santrali. https://www.ayen.com.tr/yamula-hidro-elektrik-santrali, Accessed 3 April 2023.
• DSİ, Akım gözlem yıllıkları. https://www.dsi.gov.tr/Sayfa/Detay/744, Accessed 10 February 2023.
• L. Breiman, Random forests. Machine Learning, 45 (1), 5-32, 2001. https://doi.org/10.1023/A:1010933404324.
• L. Breiman, J. H. Friedman, R. A. Olshen and C. J. Stone, Classification and regression trees. Taylor and Francis, New York, 1984.
• MGM, 2010 yılı iklim değerlendirmesi. https://www.mgm.gov.tr/FILES/iklim/2010-yili-iklim-degerlendirmesi.pdf, Accessed 1 June 2023.
• Enerji Atlası, Yamula Barajı ve HES yıllık elektrik üretimi. https://www.enerjiatlasi.com/hidroelektrik/yamula-baraji.html, Accessed 3 April 2023.
• EPİAŞ, 2020 yılı elektrik piyasası özet bilgiler raporu. https://www.epias.com.tr/wp-content/uploads/2021/01/EPIAS_2020_Yillik_Bulten_vson.pdf, Accessed 10 March 2023.