Development of Medium-Term Water Inflow Forecasting Models for Planning Electricity Generation in Isolated Power Systems
Keywords:
medium-term forecasting, water inflow, isolated power system, ensemble models, small hydropower plant, electric power system
Abstract
Reliable operation of power systems with a significant share of hydropower plants (HPPs) in the energy mix depends in many respects on how accurately the water inflow is forecasted. Taken together, the water inflow prediction and optimal planning of production define energy security, ensure the possibility of protection from floods, and eliminate idle discharges at hydroelectric power plants. The solution of such problems is complicated by lack of reliable information about the water inflow, its being stochastic in nature, a variable electricity consumption pattern, and inaccurate prediction and planning models. Improvement of prediction accuracy is focused on determining the water inventory for planning prospective electricity generation at HPPs taking into account regulation in the medium term. Such regulation is necessary to meet the power system load in the load curve peak and semi-peak parts. The paper considers the problem of constructing a medium-term water inflow prediction model for planning electricity generation for a week ahead taking into account climate changes in isolated operating power systems taking as an example the electric power systems of the Gorno-Badakhshan autonomous oblast in Tajikistan. For taking into account constant climate changes, it is proposed to use an approach based on machine learning methods, which features a self-adaptation capability. Based on the results of accomplished experimental and industry-grade numerical analyses, the expediency of using a model based on an ensemble of regression decision trees has been shown.
References
1. Kishore T.S., et al. A Comprehensive Study on the Recent Progress and Trends in Development of Small Hydropower Projects. – Energies, 2021, vol. 14(10), 2882, DOI:10.3390/en14102882.
2. Bayazıt Y., et al. A Study on Transformation of Multi-Purpose Dams into Pumped Storage Hydroelectric Power Plants by Using GIS Model. – International Journal of Green Energy, 2021, vol. 18, iss. 3, pp. 308–318.
3. Mayeda A.M., Boyd A.D. Factors Influencing Public Perceptions of Hydropower Projects: A Systematic Literature Review. – Renewable and Sustainable Energy Reviews, 2020, vol. 21, DOI:10.1016/j.rser.2020.109713.
4. Jurasz J., Ciapała B. Solar–Hydro Hybrid Power Station as a Way to Smooth Power Output and Increase Water Retention. – Solar Energy, 2018, vol. 173, pp. 675–690, DOI:10.1016/j.solener.2018.07.087.
5. Chang, J., et.al. Efficiency Evaluation of Hydropower Station Operation: A Case Study of Longyangxia Station in the Yellow River, China. – Energy, 2017, vol. 35, 23–31, DOI:10. 1016/J.ENERGY. 2017:06.049.
6. Li F.-F., Qiu J. Multi-Objective Optimization for Integrated Hydro–Photovoltaic Power System. – Applied Energy, 2016, vol. 67, pp. 377–384, DOI:10.1016/j.apenergy.2015.09.018.
7. Albo-Salih H., Mays L. Testing of an Optimization-Simulation Model for Real-Time Flood Operation of River-Reservoir Systems. – Water, 2021, 13, 1207, DOI:10.3390/w13091207.
8. Vafakhahi M. Application of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Models to Short-Term Streamflow Forecasting. – Canadian Journal of Civil Engineering, 2012, vol. 39(4), pp. 402–414, DOI: 10.1139/l2012-011.
9. Li G., et al. Short-Term Power Generation Energy Forecasting Model for Small Hydropower Stations Using GA-SVM. – Mathematical Problems in Engineering, 2014, DOI:10.1155/2014/381387.
10. Li G., et al. Applying a Correlation Analysis Method to Long-Term Forecasting of Power Production at Small Hydropower Plants. – Water, 2015, vol. 7(9), pp. 4806–4820, DOI: 10.3390/w7094806.
11. Claesen M., De Moor B. Hyperparameter Search in Machine Learning, 2015 [Электрон. ресурс], URL: https://www.arxiv-vanity.com/papers/1502.02127 (дата обращения 12.07.2021).
12. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. – Journal of Machine Learning Research, 2012, vol. 13(1), pp. 281–305.
13. Overview of Hyperparameter Tuning. Google Cloud [Электрон. ресурс], URL: https://cloud.google.com/ai-platform/training/docs/hyperparameter-tuning-overview (дата обращения 12.07.2021).
14. Асанова С.М. и др. Разработка моделей среднесрочного прогнозирования электропотребления в изолированно работающих энергосистемах на основе ансамблевых методов машинного обучения. – Известия НТЦ Единой энергетической системы, 2021, № 1(84), c. 32–39.
15. Кокин С.Е., Сафаралиев М.Х., Султонов Ш.М. Особенности управления гидроэлектростанциями в энергосистеме Республики Таджикистан. – Известия НТЦ Единой энергетической системы, 2017, № 2, с. 109–118.
16. Hinton G.E. Connectionist Learning Procedures. – Artificial Intelligence, 1989, vol. 40(1), pp. 185–234, DOI:10.1016/0004-3702(89) 90049-0.
17. Drucker H. Improving Regressors Using Boosting Techniques, 1997 [Электрон. ресурс], URL: htpps://www.researchgate.net/publication/2424244_Improving_Regressors_Using_Boosting_Techniques (дата обращения 12.07.2021).
18. Breiman L. Random Forests, 2001 [Электрон. ресурс], URL: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf (дата обращения 12.07.2021).
19. Machine Learning in Python [Электрон. ресурс], URL: https://scikit-learn.org (дата обращения 12.07.2021).
20. Keras. Simple. Flexible. Powerful [Электрон. ресурс], URL: https://keras.io/ (дата обращения 12.07.2021).
21. Сафаралиев М.Х. и др. Адаптивные ансамблевые модели для среднесрочного прогнозирования выработки электроэнергии гидроэлектростанциями в изолированных энергосистемах с учётом изменений температуры. – Электротехнические системы и комплексы, 2022, № 1(54), с. 38–45.
---
Исследование выполнено при финансовой поддержке в рамках реализации программы развития НГТУ, научный проект № С22-15.
#
1. Kishore T.S., et al. A Comprehensive Study on the Recent Progress and Trends in Development of Small Hydropower Projects. – Energies, 2021, vol. 14(10), 2882, DOI:10.3390/en14102882.
2. Bayazıt Y., et al. A Study on Transformation of Multi-Purpose Dams into Pumped Storage Hydroelectric Power Plants by Using GIS Model. – International Journal of Green Energy, 2021, vol. 18, iss. 3, pp. 308–318.
3. Mayeda A.M., Boyd A.D. Factors Influencing Public Perceptions of Hydropower Projects: A Systematic Literature Review. – Renewable and Sustainable Energy Reviews, 2020, vol. 21, DOI:10.1016/j.rser.2020.109713.
4. Jurasz J., Ciapała B. Solar–Hydro Hybrid Power Station as a Way to Smooth Power Output and Increase Water Retention. – Solar Energy, 2018, vol. 173, pp. 675–690, DOI:10.1016/j.solener.2018.07.087.
5. Chang, J., et.al. Efficiency Evaluation of Hydropower Station Operation: A Case Study of Longyangxia Station in the Yellow River, China. – Energy, 2017, vol. 35, 23–31, DOI:10. 1016/J.ENERGY. 2017:06.049.
6. Li F.-F., Qiu J. Multi-Objective Optimization for Integrated Hydro–Photovoltaic Power System. – Applied Energy, 2016, vol. 67, pp. 377–384, DOI:10.1016/j.apenergy.2015.09.018.
7. Albo-Salih H., Mays L. Testing of an Optimization-Simulation Model for Real-Time Flood Operation of River-Reservoir Systems. – Water, 2021, 13, 1207, DOI:10.3390/w13091207.
8. Vafakhahi M. Application of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Models to Short-Term Streamflow Forecasting. – Canadian Journal of Civil Engineering, 2012, vol. 39(4), pp. 402–414, DOI: 10.1139/l2012-011.
9. Li G., et al. Short-Term Power Generation Energy Forecasting Model for Small Hydropower Stations Using GA-SVM. – Mathematical Problems in Engineering, 2014, DOI:10.1155/2014/381387.
10. Li G., et al. Applying a Correlation Analysis Method to Long-Term Forecasting of Power Production at Small Hydropower Plants. – Water, 2015, vol. 7(9), pp. 4806–4820, DOI: 10.3390/w7094806.
11. Claesen M., De Moor B. Hyperparameter Search in Machine Learning, 2015 [Electron. resource], URL: https://www.arxiv-vanity.com/papers/1502.02127 (Date of appeal 12.07.2021).
12. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. – Journal of Machine Learning Research, 2012, vol. 13(1), pp. 281–305.
13. Overview of Hyperparameter Tuning. Google Cloud [Electron. resource], URL: https://cloud.google.com/ai-platform/training/docs/hyperparameter-tuning-overview (Date of appeal 12.07.2021).
14. Asanova S.M., et al. Izvestiya NTTs Yedinoy energeticheskoy sistemy – in Russ. (Proceedings of the Scientific and Technical Center of the Unified Energy System), 2021, No. 1(84), pp. 32–39.
15. Kokin S.E., Safaraliev M.Kh., Sultonov Sh.М. Izvestiya NTTs Yedinoy energeticheskoy sistemy – in Russ. (Proceedings of the Scientific and Technical Center of the Unified Energy System), 2017, No. 2, pp. 109–118.
16. Hinton G.E. Connectionist Learning Procedures. – Artificial Intelligence, 1989, vol. 40(1), pp. 185–234, DOI:10.1016/0004-3702 (89)90049-0.
17. Drucker H. Improving Regressors Using Boosting Techniques, 1997 [Electron. resource], URL: htpps://www.researchgate.net/publica-tion/2424244_Improving_Regressors_Using_Boosting_Techniques (Date of appeal 12.07.2021).
18. Breiman L. Random Forests, 2001 [Electron. resource], URL: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf (Date of appeal 12.07.2021).
19. Machine Learning in Python [Electron. resource], URL: https://scikit-learn.org (Date of appeal 12.07.2021).
20. Keras. Simple. Flexible. Powerful [Electron. resource], URL: https://keras.io/ (Date of appeal 12.07.2021).
21. Safaraliev M.Kh., et. al. Electroteknicheskie systemy i kompleksy – in Russ. (Electrotechnical Systems and Complexes), 2022, No. 1(54), pp. 38–45.
---
The research was carried out with financial support within the framework of the NSTU development program, scientific project No. C22-15.
2. Bayazıt Y., et al. A Study on Transformation of Multi-Purpose Dams into Pumped Storage Hydroelectric Power Plants by Using GIS Model. – International Journal of Green Energy, 2021, vol. 18, iss. 3, pp. 308–318.
3. Mayeda A.M., Boyd A.D. Factors Influencing Public Perceptions of Hydropower Projects: A Systematic Literature Review. – Renewable and Sustainable Energy Reviews, 2020, vol. 21, DOI:10.1016/j.rser.2020.109713.
4. Jurasz J., Ciapała B. Solar–Hydro Hybrid Power Station as a Way to Smooth Power Output and Increase Water Retention. – Solar Energy, 2018, vol. 173, pp. 675–690, DOI:10.1016/j.solener.2018.07.087.
5. Chang, J., et.al. Efficiency Evaluation of Hydropower Station Operation: A Case Study of Longyangxia Station in the Yellow River, China. – Energy, 2017, vol. 35, 23–31, DOI:10. 1016/J.ENERGY. 2017:06.049.
6. Li F.-F., Qiu J. Multi-Objective Optimization for Integrated Hydro–Photovoltaic Power System. – Applied Energy, 2016, vol. 67, pp. 377–384, DOI:10.1016/j.apenergy.2015.09.018.
7. Albo-Salih H., Mays L. Testing of an Optimization-Simulation Model for Real-Time Flood Operation of River-Reservoir Systems. – Water, 2021, 13, 1207, DOI:10.3390/w13091207.
8. Vafakhahi M. Application of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Models to Short-Term Streamflow Forecasting. – Canadian Journal of Civil Engineering, 2012, vol. 39(4), pp. 402–414, DOI: 10.1139/l2012-011.
9. Li G., et al. Short-Term Power Generation Energy Forecasting Model for Small Hydropower Stations Using GA-SVM. – Mathematical Problems in Engineering, 2014, DOI:10.1155/2014/381387.
10. Li G., et al. Applying a Correlation Analysis Method to Long-Term Forecasting of Power Production at Small Hydropower Plants. – Water, 2015, vol. 7(9), pp. 4806–4820, DOI: 10.3390/w7094806.
11. Claesen M., De Moor B. Hyperparameter Search in Machine Learning, 2015 [Электрон. ресурс], URL: https://www.arxiv-vanity.com/papers/1502.02127 (дата обращения 12.07.2021).
12. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. – Journal of Machine Learning Research, 2012, vol. 13(1), pp. 281–305.
13. Overview of Hyperparameter Tuning. Google Cloud [Электрон. ресурс], URL: https://cloud.google.com/ai-platform/training/docs/hyperparameter-tuning-overview (дата обращения 12.07.2021).
14. Асанова С.М. и др. Разработка моделей среднесрочного прогнозирования электропотребления в изолированно работающих энергосистемах на основе ансамблевых методов машинного обучения. – Известия НТЦ Единой энергетической системы, 2021, № 1(84), c. 32–39.
15. Кокин С.Е., Сафаралиев М.Х., Султонов Ш.М. Особенности управления гидроэлектростанциями в энергосистеме Республики Таджикистан. – Известия НТЦ Единой энергетической системы, 2017, № 2, с. 109–118.
16. Hinton G.E. Connectionist Learning Procedures. – Artificial Intelligence, 1989, vol. 40(1), pp. 185–234, DOI:10.1016/0004-3702(89) 90049-0.
17. Drucker H. Improving Regressors Using Boosting Techniques, 1997 [Электрон. ресурс], URL: htpps://www.researchgate.net/publication/2424244_Improving_Regressors_Using_Boosting_Techniques (дата обращения 12.07.2021).
18. Breiman L. Random Forests, 2001 [Электрон. ресурс], URL: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf (дата обращения 12.07.2021).
19. Machine Learning in Python [Электрон. ресурс], URL: https://scikit-learn.org (дата обращения 12.07.2021).
20. Keras. Simple. Flexible. Powerful [Электрон. ресурс], URL: https://keras.io/ (дата обращения 12.07.2021).
21. Сафаралиев М.Х. и др. Адаптивные ансамблевые модели для среднесрочного прогнозирования выработки электроэнергии гидроэлектростанциями в изолированных энергосистемах с учётом изменений температуры. – Электротехнические системы и комплексы, 2022, № 1(54), с. 38–45.
---
Исследование выполнено при финансовой поддержке в рамках реализации программы развития НГТУ, научный проект № С22-15.
#
1. Kishore T.S., et al. A Comprehensive Study on the Recent Progress and Trends in Development of Small Hydropower Projects. – Energies, 2021, vol. 14(10), 2882, DOI:10.3390/en14102882.
2. Bayazıt Y., et al. A Study on Transformation of Multi-Purpose Dams into Pumped Storage Hydroelectric Power Plants by Using GIS Model. – International Journal of Green Energy, 2021, vol. 18, iss. 3, pp. 308–318.
3. Mayeda A.M., Boyd A.D. Factors Influencing Public Perceptions of Hydropower Projects: A Systematic Literature Review. – Renewable and Sustainable Energy Reviews, 2020, vol. 21, DOI:10.1016/j.rser.2020.109713.
4. Jurasz J., Ciapała B. Solar–Hydro Hybrid Power Station as a Way to Smooth Power Output and Increase Water Retention. – Solar Energy, 2018, vol. 173, pp. 675–690, DOI:10.1016/j.solener.2018.07.087.
5. Chang, J., et.al. Efficiency Evaluation of Hydropower Station Operation: A Case Study of Longyangxia Station in the Yellow River, China. – Energy, 2017, vol. 35, 23–31, DOI:10. 1016/J.ENERGY. 2017:06.049.
6. Li F.-F., Qiu J. Multi-Objective Optimization for Integrated Hydro–Photovoltaic Power System. – Applied Energy, 2016, vol. 67, pp. 377–384, DOI:10.1016/j.apenergy.2015.09.018.
7. Albo-Salih H., Mays L. Testing of an Optimization-Simulation Model for Real-Time Flood Operation of River-Reservoir Systems. – Water, 2021, 13, 1207, DOI:10.3390/w13091207.
8. Vafakhahi M. Application of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Models to Short-Term Streamflow Forecasting. – Canadian Journal of Civil Engineering, 2012, vol. 39(4), pp. 402–414, DOI: 10.1139/l2012-011.
9. Li G., et al. Short-Term Power Generation Energy Forecasting Model for Small Hydropower Stations Using GA-SVM. – Mathematical Problems in Engineering, 2014, DOI:10.1155/2014/381387.
10. Li G., et al. Applying a Correlation Analysis Method to Long-Term Forecasting of Power Production at Small Hydropower Plants. – Water, 2015, vol. 7(9), pp. 4806–4820, DOI: 10.3390/w7094806.
11. Claesen M., De Moor B. Hyperparameter Search in Machine Learning, 2015 [Electron. resource], URL: https://www.arxiv-vanity.com/papers/1502.02127 (Date of appeal 12.07.2021).
12. Bergstra J., Bengio Y. Random Search for Hyper-Parameter Optimization. – Journal of Machine Learning Research, 2012, vol. 13(1), pp. 281–305.
13. Overview of Hyperparameter Tuning. Google Cloud [Electron. resource], URL: https://cloud.google.com/ai-platform/training/docs/hyperparameter-tuning-overview (Date of appeal 12.07.2021).
14. Asanova S.M., et al. Izvestiya NTTs Yedinoy energeticheskoy sistemy – in Russ. (Proceedings of the Scientific and Technical Center of the Unified Energy System), 2021, No. 1(84), pp. 32–39.
15. Kokin S.E., Safaraliev M.Kh., Sultonov Sh.М. Izvestiya NTTs Yedinoy energeticheskoy sistemy – in Russ. (Proceedings of the Scientific and Technical Center of the Unified Energy System), 2017, No. 2, pp. 109–118.
16. Hinton G.E. Connectionist Learning Procedures. – Artificial Intelligence, 1989, vol. 40(1), pp. 185–234, DOI:10.1016/0004-3702 (89)90049-0.
17. Drucker H. Improving Regressors Using Boosting Techniques, 1997 [Electron. resource], URL: htpps://www.researchgate.net/publica-tion/2424244_Improving_Regressors_Using_Boosting_Techniques (Date of appeal 12.07.2021).
18. Breiman L. Random Forests, 2001 [Electron. resource], URL: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf (Date of appeal 12.07.2021).
19. Machine Learning in Python [Electron. resource], URL: https://scikit-learn.org (Date of appeal 12.07.2021).
20. Keras. Simple. Flexible. Powerful [Electron. resource], URL: https://keras.io/ (Date of appeal 12.07.2021).
21. Safaraliev M.Kh., et. al. Electroteknicheskie systemy i kompleksy – in Russ. (Electrotechnical Systems and Complexes), 2022, No. 1(54), pp. 38–45.
---
The research was carried out with financial support within the framework of the NSTU development program, scientific project No. C22-15.
Published
2021-07-12
Issue
Section
Article
