Batch Learning SDDP for Long-Term Hydrothermal Planning

Daniel Ávila, Anthony Papavasiliou and Nils Löhndorf
Additional contact information
Daniel Ávila: Université catholique de Louvain, LIDAM/CORE, Belgium
Anthony Papavasiliou: Université catholique de Louvain, LIDAM/CORE, Belgium
Nils Löhndorf: University of Luxembourg

No 3221, LIDAM Reprints CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE)

Abstract: We consider the stochastic dual dynamic programming (SDDP) algorithm - a widely employed algorithm applied to multistage stochastic programming - and propose a variant using experience replay - a batch learning technique from reinforcement learning. To connect SDDP with reinforcement learning, we cast SDDP as a Q-learning algorithm and describe its application in both risk-neutral and risk-averse settings. We demonstrate the superiority of the algorithm over conventional SDDP by benchmarking it against PSR's SDDP software using a large-scale instance of the long-term planning problem of inter-connected hydropower plants in Colombia. We find that SDDP with batch learning is able to produce tighter optimality gaps in a shorter amount of time than conventional SDDP. We also find that batch learning improves the parallel efficiency of SDDP backward passes.

Keywords: Dynamic programming; parallel algorithms; stochastic optimal control; hydroelectric-thermal power generation; SDDP (search for similar items in EconPapers)
Pages: 14
Date: 2023-02-20
Note: In: IEEE Transactions on Power Systems, 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cor:louvrp:3221

Access Statistics for this paper

More papers in LIDAM Reprints CORE from Université catholique de Louvain, Center for Operations Research and Econometrics (CORE) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Alain GILLIS ().