Artificial Intelligence and Data Analytics for Energy Systems
Work description
The increasing deployment of Positive Energy Districts (PEDs), characterised by local renewable energy generation exceeding annual consumption, reinforces the need for advanced solutions for the management, sharing, and valorisation of energy data. In such contexts, the coordination of multiple stakeholders, distributed resources, and digital services requires efficient mechanisms for integrating data and models, particularly in relation to energy forecasting. The heterogeneity of data sources, formats, and forecasting horizons, together with challenges related to interoperability, privacy, and business models, pose significant barriers to the development of collaborative data sharing platforms (data marketplaces). In this context, the present work plan aims to analyse and structure the design of a collaborative data marketplace to support the sharing and economic valorisation of energy data and forecasting models, in alignment with the project objectives. The fellow will contribute to the definition of technical and functional requirements, as well as to the study of semantic interoperability approaches, model evaluation mechanisms, and data governance and privacy strategies. The main activities include: - Review of the state of the art in data marketplaces and data/model sharing in the energy sector. - Analysis of technical and functional requirements for integrating data and forecasting models into collaborative platforms. - Study and application of semantic interoperability methodologies, including ontologies and semantic mapping approaches. - Definition of approaches for the evaluation, comparison, and performance traceability of forecasting models. - Analysis of incentive mechanisms, compensation models, and strategies for the economic valorisation of data and models. - Study of data governance strategies and privacy-preserving techniques. - Contribution to the specification of conceptual architectures for data marketplaces in the energy sector. - Preparation of technical reports, scientific publications, and dissemination materials in collaboration with the research team.
Minimum profile required
- Basic knowledge of data analysis and time-series analysis;- Programming skills in Python;- Fundamental understanding of machine learning;- Basic knowledge of energy systems;- Fluency in English (written and spoken);
Preference factors
- Demonstrated experience in energy data analysis and modelling, preferably in collaborative or multi-stakeholder environments; - Strong background in time series forecasting applied to energy systems (e.g., renewable generation, demand, consumption); - Proven knowledge of machine learning and/or deep learning techniques for predictive modelling; - Experience with data platforms, data architectures, or data marketplace concepts; - Solid understanding of semantic interoperability, ontologies, and data modelling approaches; - Advanced programming skills in Python, including experience with libraries such as Pandas, NumPy, Scikit-learn, and/or PyTorch/TensorFlow; - Experience in developing reproducible data pipelines and handling heterogeneous datasets; - Knowledge of energy systems, including renewable integration and distributed energy resources; - Familiarity with data governance frameworks, privacy-preserving techniques, or secure data sharing mechanisms; - Proven ability to conduct independent research, critically analyse scientific literature, and contribute to scientific publications; - Strong communication skills, both written and oral, in an academic or research environment;
Application Period
Since 07 May 2026 to 21 May 2026
Centre
Power and Energy Systems