Efthymios Karangelos
University of Liège
31 Papers
126 Citations
Efthymios Karangelos is an academic researcher from University of Liège. The author has contributed to research in topics: Probabilistic logic & Computer science. The author has an hindex of 12, co-authored 28 publications. Previous affiliations of Efthymios Karangelos include University of Manchester & National Technical University of Athens.
Chat about Author
Papers
Recent Developments in Machine Learning for Energy Systems Reliability Management
Laurine Duchesne,Efthymios Karangelos,Louis Wehenkel +2 more
- 12 May 2020
TL;DR: This article reviews recent works applying machine learning techniques in the context of energy systems’ reliability assessment and control and argues that the methods, tools, etc. can be extended to other similar systems, such as distribution systems, microgrids, and multienergy systems.
Optimization under uncertainty of thermal storage-based flexible demand response with quantification of residential users' discomfort
Nicholas Good,Efthymios Karangelos,Alejandro Navarro-Espinosa,Pierluigi Mancarella +3 more
- 17 Jul 2016
TL;DR: In this paper, a two-stage stochastic programming model for provision of flexible demand response (DR) based on thermal energy storage in the form of hot water storage and/or storage in building material is presented.
•Posted Content
Whither probabilistic security management for real-time operation of power systems ?
TL;DR: In this paper, the authors investigate the risks of introducing probabilistic approaches for the management of power system's security, while taking into account the prior probabilities of contingencies, the possible failure modes of corrective control actions, and the socio-economic consequences of service interruptions.
31
Using Machine Learning to Enable Probabilistic Reliability Assessment in Operation Planning
Laurine Duchesne,Efthymios Karangelos,Louis Wehenkel +2 more
- 01 Jun 2018
TL;DR: An approach combining Monte Carlo simulation, machine learning and variance reduction techniques such as control variates is proposed to speedup the crude Monte Carlo approach and allows to reduce the number of heavy computations by about an order of magnitude.
Whither probabilistic security management for real-time operation of power systems?
Efthymios Karangelos,Patrick Panciatici,Louis Wehenkel +2 more
- 24 Oct 2013
TL;DR: This work is a first step towards the construction of a globally coherent decision making framework for security management from long-term system expansion, via mid-term asset management, towards short-term operation planning and real-time operation.
27