Multistep-ahead Streamflow and Reservoir Level Prediction Using ANNs for Production Planning in Hydroelectric Stations

In this work, a methodology to estimate the reservoir level in a hydroelectric dam, based on the predicted streamflow and desired active power, is presented. The streamflow is predicted using two multistep-ahead prediction methods: Close-Loop Prediction (CLP) and Open-Loop Prediction (OLP). Streamflow predictors and dam model are based on Artificial Neural Networks (ANNs). Further analysis of historical streamflow data demonstrated the presence of three climatic seasons and allowed to set the better configuration of ANNs topology and horizons. The prediction system was tested in a hydroelectric power plant in Ecuador. In particular, a comparison between the results obtained from the different combinations of streamflow predictors and dam model was performed concerning success percentage of prediction. Finally, dam model revealed a good accuracy for reservoir level predictions when combined with the most promising streamflow predictors implemented with CLP method for the summer season.

[1]  M. R. A. Calado,et al.  Optimal Hydro-Wind Power Generation for Day-Ahead Pool Market , 2015, IEEE Latin America Transactions.

[2]  Fernanda Strozzi,et al.  Forecasting high waters at Venice Lagoon using chaotic time series analysis and nonlinear neural networks , 2000 .

[3]  Arka Ghosh,et al.  Hybrid Optimized Back propagation Learning Algorithm For Multi-layer Perceptron , 2012, ArXiv.

[4]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[5]  Shilpi Rani,et al.  Predicting Reservoir Water Level UsingArtificial Neural Network , 2014 .

[6]  A. Quichimbo,et al.  Predicción de caudales en la cabecera de la cuenca del Paute mediante el modelo DBM , 2016 .

[7]  Muhammad Adil Ansari,et al.  Nonlinear System Identification Using Neural Network , 2012 .

[8]  Aw Salami,et al.  Modelling of Hydropower Reservoir Variables for Energy Generation: Neural Network Approach , 2013 .

[9]  Ac Igboanugo,et al.  Predicting Water Levels at Kainji Dam Using Artificial Neural Networks , 2013 .

[10]  Garrido Bullón,et al.  Identificación, estimación y control de sistemas no-lineales mediante RGO , 2000 .

[11]  J. Veintimilla,et al.  Redes Neuronales Artificiales (RNA) aplicadas en la prediccion de caudales para intervalos de tiempo horarios , 2014 .

[12]  José Roberto Camacho,et al.  A Contribution to the Study of the Estimate Hydroelectric Potential for Small Hydropower Plant , 2016 .

[13]  J. D. Velásquez,et al.  Streamflow Prediction using a Forecast Combining System , 2015, IEEE Latin America Transactions.

[14]  Victor Hinojosa,et al.  PRONÓSTICO DE CAUDALES DE MEDIANO Y CORTO PLAZO UTILIZANDO RAZONAMIENTO INDUCTIVO FUZZY Y ALGORITMOS EVOLUTIVOS – APLICACIÓN PARA LAS CENTRALES DE EMBALSE Y CENTRALES DE PASADA , 2008 .