AI-enabled eco-flexible and market-aware renewable portfolio management including hydropower.

Context and challenges:

Hydropower is a cornerstone of Europe’s renewable energy strategy, supplying nearly 30% of renewable electricity and providing essential flexibility for integrating large shares of variable renewable energy sources (vRES) such as wind and solar. Beyond generation, it delivers critical grid services including energy storage, frequency regulation, and black-start capability, that are increasingly vital in highly decarbonized power systems. When aggregated with other vRES in virtual power plants (VPPs) to jointly participate in electricity markets, hydro power plants (HPP) play an important role. Their storage capacity helps compensate for the uncertainties of vRES, reducing financial penalties while enabling more reliable provision of ancillary services (AS) to the grid. For cascaded run-of-the-river HPPs, the storage capacity is limited and must be smartly optimized in combination with other constraints. In large HPPs with dams, the AS provision can induce mechanical stress on critical components, accelerating wear and fatigue. In such cases, fatigue-aware optimization strategies are required to safeguard asset lifetime and ensure long-term reliability. Hydropower operation is inherently complex. HPP operators already consider constraints imposed by regulation related to water usage (i.e. for irrigation, flood control, river navigation etc). Despite that, hydropower faces substantial ecological and social challenges. Many plants disrupt river continuity, alter natural flow regimes, and threaten freshwater biodiversity, while hydropeaking affects hundreds of kilometers of river stretches across Europe. Social acceptance is another critical factor; local communities often perceive limited direct benefits from hydropower projects, and participation mechanisms remain largely informational rather than empowering. As a result, hydropower’s technical potential is often constrained by ecological and societal expectations, highlighting the urgent need for advanced operational strategies that reconcile energy objectives with ecological protection and community engagement.

Main objective of the thesis:

The PhD aims to develop an eco-flexible, market-aware operational framework for existing HPPs capable of reconciling techno-economic performance with ecological and societal impacts. The thesis does not address the design of new facilities; rather, it focuses on enhancing the operation of existing assets in increasingly complex and dynamic energy systems.

Specifically, the research will propose an integrated framework that will couple two core components: 1) advanced algorithms to optimise participation of HPPs, or more generally of VPPs integrating HPPs with solar and wind farms, in multiple electricity markets (incl. day-ahead, intraday, ancillary services, PPAs). These algorithms will enable the co-optimization with ecological requirements and other techno-economic operational constraints (i.e. smart strategies in cases of negative market prices to avoid curtailment). Current state-of-the-art approaches focus on market-aware centralized or distributed optimization and do not adequately integrate ecological constraints, mechanical fatigue considerations or the need for adaptive and scalable solutions. This need is becoming critical as VPPs portfolios grow and evolve dynamically due to maintenance or integration of new assets. 2) A dynamic control framework that allows HPPs or VPPs portfolios to respond in real-time to grid conditions and resource variability, while ensuring compliance with environmental flows (e-flows) and ecological constraints. This thesis will benefit from the Social Sciences and Humanities (SSH) approach, developed in the SE-HYDRO project, to incorporate societal aspects in the design and evaluation of the proposed tools. By embedding ecological and societal considerations directly into operational and market decision-making processes, the thesis will contribute to narrowing the gap between hydropower’s technical potential and its societal legitimacy, producing solutions that are economically viable, environmentally responsible, and community supported.

Methodology and expected results:

Market participation strategies for HPPs will be co-optimized with environmental constraints, including e-flow requirements and ecology-sensitive operational limits. By embedding ecological indicators and hydrological variability directly into the decision-making logic, the outcome of the proposed approach will enable plant operators to navigate economic-environmental trade-offs and unlock new revenue streams from grid services without compromising sustainability. The baseline model chain for VPP portfolio optimization will rely on stochastic/robust distributed optimization methods, accounting for uncertainty in weather conditions, demand forecasts, and hydrological inflows. Distributed methods are motivated both by the complexity of the optimization of HPP plants and by the high dimensionality of VPPs. Spatiotemporal synergies between renewable sources, for instance, using hydro ramping to balance daily solar peaks, will improve system-level resilience and reduce curtailment. Environmental constraints will be incorporated as either hard or soft limits. Given the complexity of the optimization problem, the research will explore the contribution of AI approaches at different levels of the model chain, i.e. by implementing end-to-end learning frameworks that link data, forecasts, and operational decisions, while incorporating diverse contextual information, or by using AI to process optimization outputs to facilitate decision making. While the initial focus will be on a single HPP, the methodology will be extended to integrated renewable VPP portfolios, jointly optimizing the HPPs with solar and wind generation. Finally, the scheduling framework will be coupled with a dynamic control layer, enabling HPPs or VPPs to reliably execute the schedules proposed to the markets, while adapting to real-time to deviations from forecasted conditions. Validation will be done using real-world data provided by the SE-HYDRO project.

MINES PARIS - PSL, Centre PERSEE

The PERSEE Center is one of the 18 research centers of MINES Paris. Its field of expertise concerns New Energy Technologies and Renewable Energy Sources (RES). Its research strategy is based on a "micro/macro" approach ranging from (nano)materials to energy systems. It is built around three structuring themes: i) materials and components for energy, ii) sustainable energy conversion and storage processes and technologies, and iii) renewable energies and smart energy systems.

This late is developped by one of the three groups of the Center, ERSEI, which stands for “Renewable Energies and Smart Energy Systems”. The ERSEI group develops methods and tools allowing the optimal integration of decentralized sources, including RES, storage devices, electric vehicles, active demand and other technologies, in energy systems and electricity markets. The research activity of the group is developped through three main axes. The first is based on the development of advanced short-term forecasting methods for different applications in power systems (i.e. forecasting of RES production, demand, dynamic line rating, market quantities, etc.). The second concerns the control and predictive management of energy systems. The aim is to design innovative approaches to optimise the operation (from real-time to days ahead) of different types of systems (smart-homes, microgrids, virtual power plants, energy communities, hybrid RES/storage plants, distribution grids multi-energy systems a.o.) considering uncertainties. The third axis concern planning and prospective studies that aim to optimise the design of future energy systems, generate furture scenarios, optimise investements etc.  

The PERSEE Center is located within the scientific parc of Sophia-Antipolis, near the cities of Nice, Cannes and Antibes in the south of France. Its workforce is around 55 people.

Profile:  Engineer and / or Master of Science degree (candidates may apply prior to obtaining their master's degree. The PhD will start though after the degree is succesfully obtained).

Good level of general and scientific culture. Good analytical, synthesis, innovation and communication skills. Qualities of adaptability and creativity. Motivation for research activity. Coherent professional project. Skills in programming (eg Python, Julia,…).  A succesful candidate will have a solid background in three or more of the following competencies:

• applied mathematics, statistics and probabilities
• data science, machine learning, artificial intelligence
• optimisation
• power system management, integration of renewables
• energy forecasting

Expected level in french : bon niveau souhaitable

Expected level in english : excellent