More than 20 years ago, China's hydropower undertakings rapid development, hydropower installed capacity has been a breakthrough. With the continuous improvement of hydropower installed capacity, the optimal dispatching of hydropower system is facing great challenges. In this paper, the average daily processing prediction of artificial hydropower station based on machine learning is studied. In this paper, the prediction model based on BPNN neural network is discussed to predict the daily runoff of hydropower station, and the overall system architecture is designed from the aspects of logical structure, physical structure and technical structure. Through THE simulation analysis of the water level of the hydropower station in different time periods, it is verified that the model has good simulation accuracy in the process of water level deduction, which lays a foundation for the optimization of hydropower station operation in the future.

Fawaz Alassery. Average Daily Processing Prediction of Artificial Hydropower Station Based on Machine Learning. Machine Learning Theory and Practice (2020), Vol. 1, Issue 4: 36-44. https://doi.org/10.38007/ML.2020.010405.

[1] Myint A K, Latt K Z, Hla T T, et al. IoT-Based SCADA System Design and Generation Forecasting for Hydropower Station. International Journal of Electrical and Electronic Engineering & Telecommunications, 2020, 10(4): 251-260. https://doi.org/10.18178/ijeetc.10.4.251-260

[2] Alipour M H, Kibler K M, Alizadeh B. Flow alteration by diversion hydropower in tributaries to the Salween river: A comparative analysis of two streamflow prediction methodologies. International Journal of River Basin Management, 2020, 20(1): 33-43. https://doi.org/10.1080/15715124.2020.1760289

[3] Urgiles P, Sebastian M A, Claver J. Proposal and application of a methodology to improve the control and monitoring of complex hydroelectric power station construction projects. Applied Sciences, 2020, 10(21): 7913. https://doi.org/10.3390/app10217913

[4] Castillo-Botón C, Casillas-Pérez D, Casanova-Mateo C, et al. Analysis and prediction of dammed water level in a hydropower reservoir using machine learning and persistence-based techniques. Water, 2020, 12(6): 1528. https://doi.org/10.3390/w12061528

[5] Zaman M, Yuan S, Liu J, et al. Investigating hydrological responses and adaptive operation of a hydropower station under a climate change scenario. Polish Journal of Environmental Studies, 2018, 27(5): 2337-2348. https://doi.org/10.15244/pjoes/78678

[6] Barzola-Monteses J, Mite-León M, Espinoza-Andaluz M, et al. Time series analysis for predicting hydroelectric power production: The ecuador case. Sustainability, 2019, 11(23): 6539. https://doi.org/10.3390/su11236539

[7] Hassan M, Zaffar H, Mehmood I, et al. Development of streamflow prediction models for a weir using ANN and step-wise regression. Modeling Earth Systems and Environment, 2018, 4(3): 1021-1028. https://doi.org/10.1007/s40808-018-0500-7

[8] Khaniya B, Priyantha H G, Baduge N, et al. Impact of climate variability on hydropower generation: a case study from Sri Lanka. ISH Journal of Hydraulic Engineering, 2020, 26(3): 301-309. https://doi.org/10.1080/09715010.2018.1485516

[9] Arsenault R, Côté P. Analysis of the effects of biases in ensemble streamflow prediction (ESP) forecasts on electricity production in hydropower reservoir management. Hydrology and Earth System Sciences, 2019, 23(6): 2735-2750. https://doi.org/10.5194/hess-23-2735-2019

[10] Barzola-Monteses J, Gomez-Romero J, Espinoza-Andaluz M, et al. Hydropower production prediction using artificial neural networks: an Ecuadorian application case. Neural Computing and Applications, 2020, 34(16): 13253-13266. 

[11] Wesemann J, Herrnegger M, Schulz K. Hydrological modelling in the anthroposphere: predicting local runoff in a heavily modified high-alpine catchment. Journal of Mountain Science, 2018, 15(5): 921-938. https://doi.org/10.1007/s11629-017-4587-5

[12] Zolfaghari M, Golabi M R. Modeling and predicting the electricity production in hydropower using conjunction of wavelet transform long short-term memory and random forest models. Renewable Energy, 2020, 170: 1367-1381. 

[13] Álvarez X, Valero E, Torre-Rodríguez N, et al. Influence of small hydroelectric power stations on river water quality. Water, 2020, 12(2): 312. https://doi.org/10.3390/w12020312

[14] Nazirov J A, Davlatshoev S K, Kozlov D V. Geodetic monitoring of large-span underground facilities during construction of the Rogun hydroelectric power station. Power Technology and Engineering, 2018, 52(4): 400-404. https://doi.org/10.1007/s10749-018-0965-6

[15] Paluanov D, Abboskhujayev F. Analysis of the Results of Natural Studies of Hydraulic Turbines of Hydroelectric Power Stations. The American Journal of Engineering and Technology, 2020, 3(02): 42-46.

[16] Baniya M B, Asaeda T, KC S, et al. Hydraulic parameters for sediment Transport and prediction of suspended sediment for Kali Gandaki River basin, Himalaya, Nepal. Water, 2019, 11(6): 1229. https://doi.org/10.3390/w11061229

[17] Saw M M M, Ji-Qing L. Review on hydropower in Myanmar. Applied Water Science, 2019, 9(4): 1-7. https://doi.org/10.1007/s13201-019-0984-y

[18] Heddam S, Keshtegar B, Kisi O. Predicting total dissolved gas concentration on a daily scale using kriging interpolation, response surface method and artificial neural network: Case study of Columbia River Basin Dams, USA. Natural Resources Research, 2020, 29(3): 1801-1818. https://doi.org/10.1007/s11053-019-09524-2