Water Inflow Forecasting using the Echo State Network: a Brazilian Case Study

A type of recurrent neural network has been proposed by H. Jaeger. This model, called Echo State Network (ESN), possesses a highly interconnected and recurrent topology of nonlinear processing elements, which constitutes a "reservoir of rich dynamics" and contains information about the history of input or/and output patterns. The interesting property of ESN is that only the memoryless readout is trained, whereas the recurrent topology has fixed connection weights. This reduces the complexity of recurrent neural network training to simple linear regression while preserving a recurrent topology. In this paper, the ESN is used to forecast hydropower plant reservoir water inflow, which is a fundamental information to the hydrothermal power system operation planning. A database of average monthly water inflows of Furnas plant, one of the Brazilian hydropower plants, was used as source of training and test data. The performance of the ESN is compared with SONARX network, RBF network and ANFIS model. The results show that the Echo State Network provides pretty good results for one-step ahead water inflow forecasting, providing a valuable information for the system operator.

[1]  Teresa Bernarda Ludermir,et al.  River flow forecasting for reservoir management through neural networks , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[2]  Secundino Soares,et al.  Learning algorithms for a class of neurofuzzy network and application , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Jose D. Salas,et al.  Estimation of ARMA Models with seasonal parameters , 1982 .

[6]  Amir F. Atiya,et al.  A comparison between neural-network forecasting techniques-case study: river flow forecasting , 1999, IEEE Trans. Neural Networks.

[7]  Elias S. Manolakos,et al.  Using recurrent neural networks for adaptive communication channel equalization , 1994, IEEE Trans. Neural Networks.

[8]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[9]  K. Warwick,et al.  Dynamic recurrent neural network for system identification and control , 1995 .

[10]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[11]  A.F.R. Araujo,et al.  A self-organizing NARX network and its application to prediction of chaotic time series , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[12]  D. Rumelhart,et al.  Generalization by weight-elimination applied to currency exchange rate prediction , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[13]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[14]  Paulin Coulibaly,et al.  Real-time short-term natural water inflows forecasting using recurrent neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[15]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[16]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[17]  S. Soares,et al.  Comparison between Closed-Loop and Partial Open-Loop Feedback Control Policies in Long-Term Hydrothermal Scheduling , 2002, IEEE Power Engineering Review.

[18]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[19]  A. I. McLeod.  DIAGNOSTIC CHECKING OF PERIODIC AUTOREGRESSION MODELS WITH APPLICATION , 1994 .