Learning the optimal joint operation of the energy systems of Uruguay, Brazil, Paraguay and Argentina
Resumen:
In the continuous fight against Bellman's Curse of Dimensionality, this work presents the first steps towards learning the Optimal Operation Policy of the electricity generation system of Uruguay, Brazil, Paraguay and Argentina with the infrastructures projected for the year 2030. The Operation Policy under consideration involves 76 state variables: one associated to the surface temperature anomaly of the Pacific Ocean in the N34 area, and 75 related to the hydroelectric reservoirs. The proposed methodology includes the design and training of two alternate neural network architectures combined with modern techniques devised for variance reduction and exploration, which were key to the success achieved
| 2022 | |
| Proyecto ANII-FSE_1_2017_1_144926 - "Planificación de inversiones con energías variables, restricciones de red y gestión de demanda" (2018-2020) Fondo Sectorial de Energía ANII | |
|
Wind energy generation Training Sea surface Renewable energy sources Neural networks Hydroelectric power generation Reinforcement learning Approximate Stochastic Dynamic Programming Machine Learning Optimal operation of hydrothermal systems |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
|
https://ieeexplore.ieee.org/document/10037786
https://hdl.handle.net/20.500.12008/36685 |
|
| Acceso abierto | |
| Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
