Titre :

Parallel Bayesian Optimization for Optimal Scheduling of Underground Pumped Hydro-Energy Storage Systems

Auteur(s) :

Gobert, Maxime [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Faculté polytechnique de Mons
Gmys, Jan [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Inria Lille - Nord Europe
Toubeau, Jean-François [Auteur]
Université de Mons / University of Mons [UMONS]
Melab, Nouredine [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Inria Lille - Nord Europe
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Tuyttens, Daniel [Auteur]
Université de Mons / University of Mons [UMONS]
Vallée, François [Auteur]
Université de Mons / University of Mons [UMONS]

Titre de la manifestation scientifique :

IPDPSw PDCO - Parallel / Distributed Combinatorics and Optimization

Ville :

Lyon (remote)

Pays :

France

Date de début de la manifestation scientifique :

2022-05-27

Titre de l’ouvrage :

IEEE Xplore

Date de publication :

2022-08-01

Mot(s)-clé(s) en anglais :

Bayesian Optimization
Gaussian Process
Batch-based Parallelism
Optimization
Electrical Engineering

Discipline(s) HAL :

Computer Science [cs]/Operations Research [math.OC]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]
Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

Underground Pumped Hydro-Energy Storage stations are sustainable options to enhance storage capacity and thus the flexibility of energy systems. Efficient management of such units requires high-performance optimization ...
Lire la suite >Underground Pumped Hydro-Energy Storage stations are sustainable options to enhance storage capacity and thus the flexibility of energy systems. Efficient management of such units requires high-performance optimization algorithms able to find solutions in a very restricted timing to comply with the responsive energy markets. In this context, parallel computing offers a valuable solution to ensure appropriate decisions that maximize the profit of the station operator, while guaranteeing the safety of the energy network. This study investigates the use of three existing algorithms in Parallel Bayesian Optimization, namely q-EGO, BSP-EGO and TuRBO. The three algorithms have different inherent behaviors in terms of parallel potential and, even though TuRBO scales better, q-EGO remains the best choice regarding the final outcomes for all investigated batch sizes and manages to get up to 5 times more profits than other approaches.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL