Stand-alone renewable power system scheduling for a green data center using integer linear programming - Université de Technologie de Belfort-Montbeliard Accéder directement au contenu
Article Dans Une Revue Journal of Scheduling Année : 2021

Stand-alone renewable power system scheduling for a green data center using integer linear programming

Résumé

In light of the rapid growth of data centers around the world and their huge energy consumption, several researchers have focused on the task scheduling and resource allocation problem in order to minimize the energy consumed by the data center. Other initiatives focus on the implementation of green energy sources in order to minimize the consumption of fossil fuels and their emission of CO2. As part of the ANR DATAZERO project (Pierson et al. in IEEE Access 7, 2019. https://doi.org/10.1109/ACCESS.2019.2930368), several research teams have engaged in efforts at defining the main concepts of a full green data center, powered only by renewable energy. Achieving this goal necessitates a focus on the efficient management of an autonomous hybrid power system consisting of solar panels, wind turbines, batteries, and fuel cell systems. The purpose of this work is not to show that a stand-alone data center is economically viable, but rather is feasible. This paper proposes a set of models based on mixed integer linear programs capable of managing the energy commitment to address data center power demand. The approach takes the season and weather forecasts into account at the time of optimization.
Fichier principal
Vignette du fichier
8c249b30-7c3f-40eb-8db5-7ff26bd7bf2e-author.pdf (798.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03455029 , version 1 (29-11-2021)

Identifiants

Citer

Marwa Haddad, Jean-Marc Nicod, Marie-Cécile Péra, Christophe Varnier. Stand-alone renewable power system scheduling for a green data center using integer linear programming. Journal of Scheduling, 2021, 24 (5), pp.523 - 541. ⟨10.1007/s10951-021-00700-y⟩. ⟨hal-03455029⟩
30 Consultations
258 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More