PhD position in “Optimization of complex multi-carrier energy systems guided by Machine Learning Algorithms” – MSCA Cofund SEED doctoral programme

Job title:

PhD position in “Optimization of complex multi-carrier energy systems guided by Machine Learning Algorithms” – MSCA Cofund SEED doctoral programme

Company:

Job description

Offer DescriptionThe PhD position is offered under a standard track (30 months at IMT Atlantique + 3 months at University of Wisconsin, Madison, USA + 3 months at an industrial partner to be determined).1.1. Domain and scientific/technical contextThe design and operation of today’s energy systems requires the inclusion of multiple technologies and resources, including external energy supplies and primary sources. These couplings between multiple technologies and resource supplies have given rise to the concept of the energy hub. Since most of the supply systems worldwide are interconnected and exchange resources, current supply systems can be considered as a set of interconnected hubs.The current energy transition processes require new strategies to generate models with immediate responses to problems, not only in terms of redesigning operating policies, but also in terms of including new technologies, whether for generation, storage or interaction. This implies the sizing, selection of technologies and interaction of technologies. The contribution of this work aims to propose new strategies for the resolution of complex models based on energy hub schemes.1.2. Scientific/technical challengesAlthough most current hub modeling proposals are based on linear models, most technologies do not correspond to this behavior. Operations such as storage, grid interconnection and coordination between operating units are strongly linked to the generation of nonlinear problems. This level of complexity increases when considering the multi-period operation of the system. These are difficult to solve using traditional strategies, so in recent years machine learning algorithms have been used to solve complex problems. However, these types of strategies, although popular, are heterogeneous or generated according to the needs of the case study.This has generated multiple strategies to approach the problem that can rarely be generalized. Solutions based on mathematical programming tend to consume significant computational resources and the application of heuristics leads to problems such as heterogeneity in solutions, high data dependency and low optimality guarantees.1.3. Considered methods, targeted results and impactsThe use of decomposition strategies is proven to be an efficient way to solve large scale optimization problems. This has been mainly done in the past by hand based on expert knowledge on the problems based on the nature of the model and the data structure with which it is fed. That is, the characteristics of the physical model of the hub and data such as demand, environmental and energy market conditions. In this project, it is proposed to use machine learning algorithms to generate subrogated models that allow identifying automatic solution strategies that improve the performance of solution environments. This implies a reduction of computational and analysis times associated with convergence and optimality of the computed solutions.Although the use of this tool is proposed for energy systems, the proposal can be easily extended to processing plants where there are multiple flows of matter and energy.1.4. Environment (partners, places, specific tools and hardware)It is proposed to carry out analyses with case studies where data on demand, energy resource carriers and environmental conditions are available both on a small scale and at a regional level. Two cases are proposed to test our ideas: a microgrid and a regional generation system (France). The strategy will be used to propose improvements in operational policies and storage capacities.To develop the project, The PhD student will be provided with adequate computer equipment and access to high-performance computing facilities.An international collaboration with the professor Victor Zavala (University Wisconsin,USA) is proposed, for which a stay of 3 months is planned.1.5. Interdisciplinarity aspectsThe project focuses on the development of strategies to address optimal power system design and control problems. However, this approach can be extended to other areas such as processing systems, industrial and supply chain systems. This makes it attractive to areas such as industrial management and economics.1.6. References * Eladl, A. A., El-Afifi, M. I., El-Saadawi, M. M., & Sedhom, B. E. (2023). A review on energy hubs: Models, methods, classification, applications, and future trends. Alexandria engineering journal, 68, 315-342.

• Engelmann, A., Shin, S., Pacaud, F., & Zavala, V. M. (2025). Scalable primal decomposition schemes for large-scale infrastructure networks. IEEE Transactions on Control of Network Systems.
• Fakih, S., Mabrouk, M. T., Batton-Hubert, M., & Lacarrière, B. (2023). Bi-level and multi-objective optimization of renewable energy sources and storage planning to support existing overloaded electricity grids. Energy Reports, 10, 1450-1466.
• Fuentes-Corte’s, L. F., Flores-Tlacuahuac, A., & Nigam, K. D. (2022). Machine learning algorithms used in PSE environments: A didactic approach and critical perspective. Industrial & Engineering Chemistry Research, 61(25), 8932-8962.
• García-Martínez, J., Reyes-Patiño, J. L., López-Sosa, L. B., & Fuentes-Cortés, L. F. (2022). Anticipating alliances of stakeholders in the optimal design of community energy systems. Sustainable Energy Technologies and Assessments, 54, 102880.
• Geidl, M., & Andersson, G. (2007). Optimal power flow of multiple energy carriers. IEEE Transactions on power systems, 22(1), 145-155.
• Hernández-Romero, I. M., Barajas-Villarruel, L. R., Flores-Tlacuahuac, A., Fuentes-Cortes, L. F., & Rico-Ramirez, V. (2023). Strategic planning for sustainable electric system operations: Integrating renewables and energy storage. Computers & Chemical Engineering, 177, 108312.
• Mitrai, I., & Daoutidis, P. (2024). Taking the human out of decomposition-based optimization via artificial intelligence, Part I: Learning when to decompose. Computers & Chemical Engineering, 186, 108688.
• Mitrai, I., & Daoutidis, P. (2024). Taking the human out of decomposition-based optimization via artificial intelligence, Part II: Learning to initialize. Computers & Chemical Engineering, 186, 108686.
• Rodrigue, D., Mabrouk, M. T., Pasdeloup, B., Meyer, P., & Lacarrière, B. (2024). Topology reduction through machine learning to accelerate dynamic simulation of district heating. Energy and AI, 17, 100393.

2. Partners and study periods2.1. Supervisors and study periods

• IMT Atlantique:

and , IMT Atlantique, Nantes, FranceInternational partner: , University of Wisconsin, Madison, USA.The PhD student will stay 3 months at Prof. Zavala’s lab. * Industrial partner(s): not yet determined.2.2. Hosting organizations2.2.1. IMT Atlantique, internationally recognized for the quality of its research, is a leading French technological university under the supervision of the Ministry of Industry and Digital Technology. IMT Atlantique maintains privileged relationships with major national and international industrial partners, as well as with a dense network of SMEs, start-ups, and innovation networks. With 290 permanent staff, 2,200 students, including 300 doctoral students, IMT Atlantique produces 1,000 publications each year and raises 18€ million in research funds.2.2.2. University of WisconsinSince the founding of the in 1848, its Madison campus has been a catalyst for the extraordinary. As a public land-grant university and major research institution, our students, staff, and faculty engage in a world-class education while solving real-world problems. With public service – or as we call it, the Wisconsin Idea – as our guiding principle, Badgers are creating a better future for everyone.Where to apply WebsiteRequirementsResearch Field Engineering Education Level Master Degree or equivalentSkills/QualificationsKnowledge of energy systems modeling, mathematical programming and machine learning algorithms.Use of software such as Julia or Python.Experience in database management, statistical analysis and processing systems is desirable.Languages ENGLISH Level ExcellentResearch Field Computer scienceMathematicsAdditional InformationBenefitsBenefitsA PhD programme of high quality training : 4 reasons to apply

• SEED is a programme of excellence that is aware of its responsibilities: to provide a programme of high quality training to develop conscientious researchers, including training in responsible research and ethics.
• SEED’s unique approach of providing interdisciplinary, international and cross-sector experience is tailored to work in a career-focused manner to enhance employability and market integration.
• SEED offers a competitive funding scheme, aiming for an average monthly salary of EUR 2,000 net per ESR, topped by additional mobility allowances as well as optional family allowances.
• SEED is a forward-looking programme that actively engages with current issues and challenges, providing research opportunities addressing industrial and academic relevant themes.

Eligibility criteriaEligibility criteria. In accordance with MSCA rules, SEED will open to applicants without any conditions of nationality nor age criteria. SEED applies the MSCA mobility standards and necessary background. Eligible candidates must fulfil the following criteria

• Mobility rule: Candidates must show transnational mobility by having not resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the three years immediately before the deadline of the co-funded program’s call (March 20 for call #3). Compulsory national service, short stays such as holidays and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account.
• Early-stage researchers (ESR): Candidates must have a master’s degree or an equivalent diploma at the time of their enrolment and must be in the first four years (full-time equivalent research experience) of their research career. Moreover, they must not have been awarded a doctoral degree.

Extensions may be granted (under certain conditions) for maternity leave, paternity leave, as well as long-term illness or national service.Selection processThe selection process is described on the guide for applicants available here:Additional commentsApplications can only be provided through the application system available under the SEED website: Website for additional job detailsWork Location(s)Number of offers available 1 Company/Institute IMT Atlantique Country France City Nantes Postal Code 44300 Street 655 Av. du Technopôle GeofieldContact CityNantes WebsiteStreet4, rue Alfred Kastler Postal Code44300 E-Mailseed-contact@imt-atlantique.fr Phone+33251858721STATUS: EXPIREDShare this page

Expected salary

€2000 per month

Location

Nantes, Loire-Atlantique

Job date

Wed, 26 Feb 2025 23:31:23 GMT

To help us track our recruitment effort, please indicate in your email/cover letter where (vacanciesin.eu) you saw this job posting.