1. Optimal scenario tree reduction for stochastic streamflows in power generation planning problems.
- Author
-
de Oliveira, WelingtonLuis, Sagastizábal, Claudia, Penna, DéboraDias Jardim, Maceira, MariaElvira Piñeiro, and Damázio, JorgeMachado
- Subjects
- *
ELECTRIC power production , *MACHINE learning , *MATHEMATICAL optimization , *SUPPORT vector machines , *DATA mining - Abstract
The mid-term operation planning of hydro-thermal power systems needs a large number of synthetic sequences to represent accurately stochastic streamflows. These sequences are generated by a periodic autoregressive model. If the number of synthetic sequences is too big, the optimization planning problem may be too difficult to solve. To select a small set of sequences representing the stochastic process well enough, this work employs two variants of the Scenario Optimal Reduction technique. The first variant applies such a technique at the last stage of a tree defined a priori for the whole planning horizon while the second variant combines a stage-wise reduction, preserving the periodic autoregressive structure, with resampling. Both approaches are assessed numerically on hydrological sequences generated for real configurations of the Brazilian power system. [ABSTRACT FROM AUTHOR]
- Published
- 2010
- Full Text
- View/download PDF