Pause
Lecture
Moteur de recherche d'offres d'emploi CEA

Uncertainty Quantification and Machine Learning in multi-vector energy systems. H/F


Détail de l'offre

Informations générales

Entité de rattachement

Le Commissariat à l'énergie atomique et aux énergies alternatives (CEA) est un organisme public de recherche.

Acteur majeur de la recherche, du développement et de l'innovation, le CEA intervient dans le cadre de ses quatre missions :
. la défense et la sécurité
. l'énergie nucléaire (fission et fusion)
. la recherche technologique pour l'industrie
. la recherche fondamentale (sciences de la matière et sciences de la vie).

Avec ses 16000 salariés -techniciens, ingénieurs, chercheurs, et personnel en soutien à la recherche- le CEA participe à de nombreux projets de collaboration aux côtés de ses partenaires académiques et industriels.  

Référence

2022-22214  

Description de l'unité

In the context of energy transition, multi-vector energy systems and networks (smart grids, heat and cold networks, industrial production systems) must balance the energy sources and demands in function of time. Modeling and simulation play a crucial role in the process of sizing and controlling these systems and their multiple components [1, 2].
The energy systems models are computationally intensive, and limit the capability to analyze the systems e.g. through sensitivity analysis. In multi-vector energy systems modeling as in many other domains, surrogate models help reduce the models computation time [3, 4]. However, the surrogate models generate bias; thus they deteriorate the validity of results.

Description du poste

Domaine

Mécanique et thermique

Contrat

Post-doctorat

Intitulé de l'offre

Uncertainty Quantification and Machine Learning in multi-vector energy systems. H/F

Sujet de stage

In the frame of the impact analysis of using surrogate models for simulation and optimization of energy systems, your project will focus on quantification of uncertainty in surrogate models, including neural networks, with characteristics adapted to time series processing. In particular, you may study the use of Bayesian neural networks to process time series.

Durée du contrat (en mois)

24

Description de l'offre

In a team composed of about twenty experts (energy systems modeling, operations research, machine learning, programming), you will work in the frame of a project on modeling and optimization of energy networks common to several CEA divisions.

 Your tasks:

· Conduct a bibliographic review focused on the types of surrogate models adapted to the processing of time series in the frame of energy systems analysis, and the associated uncertainty quantification methods.

· Conceive and run a proof of concept study for surrogate models uncertainty quantification in energy systems analysis on a test case.

· Publish the results in scientific journals and contribute to cooperation with French and International academics.

The laboratory is located in Le Bourget du Lac and in Grenoble. Travels to Saclay (Paris area) are expected. The position is based in Le Bourget du Lac.

 

 

Profil du candidat

You have a PhD in applied mathematics and have skills in scientific programming. You are interested in energy. You are familiar with at least one of the following topics, and would like to learn more about the others:

·       Machine learning

·       Uncertainty quantification

·       Energy systems

You are fluent in English. You bring creativity, enjoy teamwork and can undertake research projects autonomously.

Localisation du poste

Site

Autre

Localisation du poste

France, Auvergne-Rhône-Alpes, Savoie (73)

Ville

Le Bourget du Lac

Critères candidat

Langues

Anglais (Courant)

Demandeur

Disponibilité du poste

01/09/2022