Akylas Stratigakos
- Imperial College London
Présentation
Hi, welcome to my profile! I am currently a Research Associate at Imperial College London working on data-driven methods to enabling 100% renewable-based power systems. Before that, I was a PhD candidate at Center PERSEE, Mines Paris, PSL University, working on energy analytics to improve decision-making in power systems. My research interests are on the intersection of machine learning, forecasting, and optimization tools to enable power systems to cope with the uncertainty introduced by the large-scale penetration of renewables. I enjoy participating in data science challenges, mostly related to energy forecasting. If you want to collaborate, feel free to contact me!
Domaines de recherche
Compétences
Publications
Publications
Resilient Feature-driven Trading of Renewable Energy with Missing DataIEEE PES ISGT Europe 2023, IEEE Power & Energy Society (PES), Université Grenoble Alpes,, Oct 2023, Grenoble, France |
|
|
|
End-to-end Learning for Hierarchical Forecasting of Renewable Energy Production with Missing Values17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022, Jun 2022, Manchester - Online, United Kingdom. ⟨10.1109/PMAPS53380.2022.9810610⟩ |
Prescriptive Trees for Integrated Forecasting and Optimization Applied in Trading of Renewable Energy17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022, Jun 2022, Manchester - Online, United Kingdom |
|
|
|
Highlight results of the Smart4RES project on weather modelling and forecasting dedicated to renewable energy applicationsEGU General Assembly 2022, May 2022, Vienna, Austria. pp.EGU22-12923, ⟨10.5194/egusphere-egu22-12923⟩ |
Making Energy Forecasting Resilient to Missing Features: a Robust Optimization Approach42nd International Symposium on Forecasting, Jul 2022, Oxford, United Kingdom |
|
|
|
A Value-Oriented Price Forecasting Approach to Optimize Trading of Renewable Generation2021 IEEE Madrid PowerTech, IEEE, Jun 2021, Madrid, Spain |
|
|
A robust fix-and-optimize matheuristic for timetabling problems with uncertain renewable energy productionIEEE Symposium Series on Computational Intelligence 2021, IEEE, Dec 2021, Orlando, United States |
Short-term trading of wind energy production using data-driven prescriptive optimizationWind Energy Science Conference, May 2021, Hannover, Germany |
Interpretable Machine Learning for DC Optimal Power Flow with Feasibility Guarantees2024 IEEE Power & Energy Society General Meeting (PESGM), Jul 2024, Seattle, Washington, United States. IEEE, pp.1-1, 2024, ⟨10.1109/PESGM51994.2024.10688644⟩ |
|
|
|
Next Generation Forecasting Solutions for Wind Energy – Results from the Smart4RES ProjectWindEurope Annual Event 2023, Apr 2023, Copenhagen, Denmark. 2023 |
|
|
Learning Data-Driven Uncertainty Set Partitions for Robust and Adaptive Energy Forecasting with Missing Data2025 |
|
|
Decision-Focused Linear Pooling for Probabilistic Forecast Combination2024 |
|
|
Decision-Focused Data Pooling for Contextual Stochastic Optimization2023 |
|
|
Resilient Feature-driven Trading of Renewable Energy with Missing Data2023 |
|
|
Comparison and Evaluation of Methods for a Predict+Optimize Problem in Renewable Energy2023 |
|
|
Prescriptive Trees for Value-oriented Forecasting and Optimization: Applications on Storage Scheduling and Market Clearing2021 |