Predictive Control Approach for Long-Term Hydropower Scheduling Using Annual Inflow Forecasting Model

Abstract This paper proposes an annual inflow forecasting model in an open-loop feedback control operational policy for long-term hydropower scheduling. A deterministic optimization model precisely represents hydropower generation by taking into consideration water head as a nonlinear function of storage, discharge and spillage. The inflow is made available by a forecasting model based on a fuzzy inference system that captures the nonlinear correlation of consecutive inflows on an annual basis, with disaggregation of the results on a monthly basis. The performance of the proposed approach is evaluated by simulation for a multi-reservoir system, based on historical inflow records and compared to the same approach on monthly basis. The results show that the proposed approach leads to an operational performance closer to that of the perfect foresight solution, providing lower spillages and higher average hydropower efficiency and generation.

[1]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[2]  Sushmita Mitra,et al.  Neuro-fuzzy rule generation: survey in soft computing framework , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  Juan B. Valdés,et al.  Aggregation‐Disaggregation Approach to multireservoir operation , 1992 .

[4]  Laureano F. Escudero,et al.  Hydropower generation management under uncertainty via scenario analysis and parallel computation , 1995 .

[5]  John W. Labadie,et al.  Optimal Operation of Multireservoir Systems: State-of-the-Art Review , 2004 .

[6]  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.

[7]  Peter K. Kitanidis,et al.  Limitations of Deterministic Optimization Applied to Reservoir Operations , 1999 .

[8]  Dimitri P. Solomatine,et al.  Modular learning models in forecasting natural phenomena , 2006, Neural Networks.

[9]  Larry Lapide,et al.  Top-Down & Bottom-Up Forecasting in S&op , 2006 .

[10]  S. Chiu,et al.  A cluster estimation method with extension to fuzzy model identification , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[11]  N. Nabona.  Multicommodity network flow model for long-term hydro-generation optimization , 1993 .

[12]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  Jakob Rosing,et al.  Composite Representation of a Multireservoir Hydroelectric Power System , 1970 .

[14]  M. V. F. Pereira,et al.  Multi-stage stochastic optimization applied to energy planning , 1991, Math. Program..

[15]  Secundino Soares,et al.  A second order network flow algorithm for hydrothermal scheduling , 1995 .

[16]  Ron S. Dembo,et al.  Scenario optimization , 1991, Ann. Oper. Res..

[17]  A. Turgeon.  Optimal operation of multireservoir power systems with stochastic inflows , 1980 .

[18]  B. F. Sule,et al.  Stochastic dynamic programming models for reservoir operation optimization , 1984 .