Job offer

Mines Paris - PSL, Centre PERSEE & RTE; France; Sur place; EUR 35 000 - 55 000; Plein temps

Résumé du poste

An innovative research opportunity awaits in the realm of renewable energy forecasting. This project aims to harness advanced AI methodologies to enhance the predictability of renewable energy generation, crucial for modern power systems. Candidates will engage in developing adaptable, large-scale forecasting models, leveraging diverse datasets to improve accuracy and grid stability. Join a forward-thinking organization dedicated to pioneering research in energy technology, where your contributions can lead to significant advancements in the field. If you are passionate about tackling real-world challenges with cutting-edge technology, this PhD opportunity is perfect for you.

Qualifications

• Candidates must hold an Engineer or Master of Science degree.
• Strong analytical, synthesis, and communication skills are essential.

Responsabilités

• Develop AI-based forecasting models for renewable energy generation.
• Analyze data and improve predictability under various conditions.

Connaissances

Python

Analytical Skills

Data Science

Machine Learning

Communication Skills

Adaptability

Creativity

Formation

Engineer degree

Master of Science degree

Description du poste

Organisation/Company: Mines Paris - PSL, Centre PERSEE & RTE

Research Field: Engineering Technology & Energy Technology

Position: Recognised Researcher (R2), Leading Researcher (R4), First Stage Researcher (R1), Established Researcher (R3)

Country: France

Application Deadline: 9 Jun 2025 - 22:00 (UTC)

Type of Contract: Temporary

Job Status: Full-time

Offer Starting Date: 1 Oct 2025

Funding: Not funded through the EU Research Framework Programme

Research Infrastructure Staff Position: No

Offer Description

Title: "Advanced AI-based methods to exploit massive data for improved predictability of renewable energy generation."

Context and background:

Short-term energy forecasting for the next minutes to days ahead is crucial for the safe and economical operation of modern power systems and electricity markets, especially with high renewable energy sources (RES) penetration. This PhD project addresses RES forecasting at local, regional, and national levels, aiming to improve accuracy to reduce costs and enhance grid stability.

The project focuses on leveraging geographically distributed RES data, handling large and sometimes incomplete datasets, and ensuring forecast consistency across different scales. The French Transmission System Operator, RTE, relies on such forecasts for balancing and grid management, where even minor errors can lead to significant financial losses.

Scientific objectives:

The goal is to enhance RES production and net load predictability, especially under challenging conditions like extreme weather, data issues, and non-weather factors, using AI methodologies such as foundational models and deep learning. The project seeks to develop adaptable, large-scale, and multi-scale forecasting models.

Methodology and expected results:

The research will analyze current state-of-the-art techniques, develop AI-assisted filtering and classification tools, and incorporate additional data sources to improve forecasts. Benchmarking against existing models will identify areas for enhancement, leading to the development of resilient, accurate, and context-aware AI-based forecasting solutions.

Funding category: Cifre

PhD Title: Doctorat en Énergétique et Procédés

PhD Country: France

Candidate Requirements:

• Engineer and/or Master of Science degree (candidates may apply before completing their master's, but the PhD starts after degree completion)
• Good scientific and cultural background
• Analytical, synthesis, innovation, and communication skills
• Adaptability, creativity, motivation for research, coherent professional project
• Programming skills (e.g., Python)

Preferred competencies include applied mathematics, statistics, probabilities, data science, machine learning, AI, and energy forecasting. A good level of French is recommended.