M. Sc. Mohamed Hassouna

Autonomous Energy Systems (AESy)

Email: mohamed.hassouna[at]uni-kassel[dot]de

Website: Mohamed Hassouna

Publications

[ 2026 ]
[ 2025 ]
[ 2024 ]
[ 2022 ]

2026[ to top ]

Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach.Hassouna, Mohamed; Holzhüter, Clara; Lehna, Malte; de Jong, Matthijs; Viebahn, Jan; Sick, Bernhard; Scholz, Christoph. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 129–146. Springer, 2026.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The rising proportion of renewable energy in the electricity mix introduces significant operational challenges for power grid operators. Effective power grid management demands adaptive decision-making strategies capable of handling dynamic conditions. With the increase in complexity, more and more Deep Learning (DL) approaches have been proposed to find suitable grid topologies for congestion management. In this work, we contribute to this research by introducing a novel Imitation Learning (IL) approach that leverages soft labels derived from simulated topological action outcomes, thereby capturing multiple viable actions per state. Unlike traditional IL methods that rely on hard labels to enforce a single optimal action, our method constructs soft labels that capture the effectiveness of actions that prove suitable in resolving grid congestion. To further enhance decision-making, we integrate Graph Neural Networks (GNNs) to encode the structural properties of power grids, ensuring that the topology-aware representations contribute to better agent performance. Our approach significantly outperforms its hard-label counterparts as well as state-of-the-art Deep Reinforcement Learning (DRL) baseline agents. Most notably, it achieves a 17% better performance compared to the greedy expert agent from which the imitation targets were derived.
@inproceedings{hassouna2025learning, abstract = {The rising proportion of renewable energy in the electricity mix introduces significant operational challenges for power grid operators. Effective power grid management demands adaptive decision-making strategies capable of handling dynamic conditions. With the increase in complexity, more and more Deep Learning (DL) approaches have been proposed to find suitable grid topologies for congestion management. In this work, we contribute to this research by introducing a novel Imitation Learning (IL) approach that leverages soft labels derived from simulated topological action outcomes, thereby capturing multiple viable actions per state. Unlike traditional IL methods that rely on hard labels to enforce a single optimal action, our method constructs soft labels that capture the effectiveness of actions that prove suitable in resolving grid congestion. To further enhance decision-making, we integrate Graph Neural Networks (GNNs) to encode the structural properties of power grids, ensuring that the topology-aware representations contribute to better agent performance. Our approach significantly outperforms its hard-label counterparts as well as state-of-the-art Deep Reinforcement Learning (DRL) baseline agents. Most notably, it achieves a 17% better performance compared to the greedy expert agent from which the imitation targets were derived.}, author = {Hassouna, Mohamed and Holzhüter, Clara and Lehna, Malte and de Jong, Matthijs and Viebahn, Jan and Sick, Bernhard and Scholz, Christoph}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {129–146}, publisher = {Springer}, title = {Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach}, year = 2026 }
%0 Conference Paper %1 hassouna2025learning %A Hassouna, Mohamed %A Holzhüter, Clara %A Lehna, Malte %A de Jong, Matthijs %A Viebahn, Jan %A Sick, Bernhard %A Scholz, Christoph %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2026 %I Springer %P 129--146 %R 10.1007/978-3-032-06129-4_8 %T Learning Topology Actions for Power Grid Control: A Graph-Based Soft-Label Imitation Learning Approach %U https://link.springer.com/chapter/10.1007/978-3-032-06129-4_8 %X The rising proportion of renewable energy in the electricity mix introduces significant operational challenges for power grid operators. Effective power grid management demands adaptive decision-making strategies capable of handling dynamic conditions. With the increase in complexity, more and more Deep Learning (DL) approaches have been proposed to find suitable grid topologies for congestion management. In this work, we contribute to this research by introducing a novel Imitation Learning (IL) approach that leverages soft labels derived from simulated topological action outcomes, thereby capturing multiple viable actions per state. Unlike traditional IL methods that rely on hard labels to enforce a single optimal action, our method constructs soft labels that capture the effectiveness of actions that prove suitable in resolving grid congestion. To further enhance decision-making, we integrate Graph Neural Networks (GNNs) to encode the structural properties of power grids, ensuring that the topology-aware representations contribute to better agent performance. Our approach significantly outperforms its hard-label counterparts as well as state-of-the-art Deep Reinforcement Learning (DRL) baseline agents. Most notably, it achieves a 17% better performance compared to the greedy expert agent from which the imitation targets were derived.
Graph reinforcement learning for power grids: A comprehensive survey.Hassouna, Mohamed; Holzhüter, Clara; Lytaev, Pawel; Thomas, Josephine; Sick, Bernhard; Scholz, Christoph. In Energy and AI, 23, bl 100671. Elsevier, 2026.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The increasing share of renewable energy and distributed electricity generation requires the development of deep learning approaches to address the lack of flexibility inherent in traditional power grid methods. In this context, Graph Neural Networks are a promising solution due to their ability to learn from graph-structured data. Combined with Reinforcement Learning, they can be used as control approaches to determine remedial actions. This review analyzes how Graph Reinforcement Learning can improve representation learning and decision-making in power grid applications, particularly transmission and distribution grids. We analyze the reviewed approaches in terms of the graph structure, the Graph Neural Network architecture, and the Reinforcement Learning approach. Although Graph Reinforcement Learning has demonstrated adaptability to unpredictable events and noisy data, its current stage is primarily proof-of-concept, and it is not yet deployable to real-world applications. We highlight the open challenges and limitations for real-world applications..
@article{hassouna2026graph, abstract = {The increasing share of renewable energy and distributed electricity generation requires the development of deep learning approaches to address the lack of flexibility inherent in traditional power grid methods. In this context, Graph Neural Networks are a promising solution due to their ability to learn from graph-structured data. Combined with Reinforcement Learning, they can be used as control approaches to determine remedial actions. This review analyzes how Graph Reinforcement Learning can improve representation learning and decision-making in power grid applications, particularly transmission and distribution grids. We analyze the reviewed approaches in terms of the graph structure, the Graph Neural Network architecture, and the Reinforcement Learning approach. Although Graph Reinforcement Learning has demonstrated adaptability to unpredictable events and noisy data, its current stage is primarily proof-of-concept, and it is not yet deployable to real-world applications. We highlight the open challenges and limitations for real-world applications..}, author = {Hassouna, Mohamed and Holzhüter, Clara and Lytaev, Pawel and Thomas, Josephine and Sick, Bernhard and Scholz, Christoph}, journal = {Energy and AI}, keywords = {itegpub}, pages = 100671, publisher = {Elsevier}, title = {Graph reinforcement learning for power grids: A comprehensive survey}, volume = 23, year = 2026 }
%0 Journal Article %1 hassouna2026graph %A Hassouna, Mohamed %A Holzhüter, Clara %A Lytaev, Pawel %A Thomas, Josephine %A Sick, Bernhard %A Scholz, Christoph %D 2026 %I Elsevier %J Energy and AI %P 100671 %R 10.1016/j.egyai.2025.100671 %T Graph reinforcement learning for power grids: A comprehensive survey %U https://www.sciencedirect.com/science/article/pii/S2666546825002034 %V 23 %X The increasing share of renewable energy and distributed electricity generation requires the development of deep learning approaches to address the lack of flexibility inherent in traditional power grid methods. In this context, Graph Neural Networks are a promising solution due to their ability to learn from graph-structured data. Combined with Reinforcement Learning, they can be used as control approaches to determine remedial actions. This review analyzes how Graph Reinforcement Learning can improve representation learning and decision-making in power grid applications, particularly transmission and distribution grids. We analyze the reviewed approaches in terms of the graph structure, the Graph Neural Network architecture, and the Reinforcement Learning approach. Although Graph Reinforcement Learning has demonstrated adaptability to unpredictable events and noisy data, its current stage is primarily proof-of-concept, and it is not yet deployable to real-world applications. We highlight the open challenges and limitations for real-world applications..

2025[ to top ]

PPTopoGym: Towards an RL Environment for Topology Actions on Power Grids.Köhler, Dominik; Hassouna, Mohamed; Degtyar, Dmitry; Krauß, Jonas; Brendlicger, Kurt; Scholz, Christoph. In Workshop on Machine Learning for Sustainable Power Systems (ML4SPS 2025), ECML PKDD. Springer, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Power grids are facing growing challenges, arising from the increasing share of renewable energy sources and highly variable loads, in- troducing significant variability into both power generation and demand. This variability can create transmission line bottlenecks, which in turn lead to overheating. Transmission system operators address this prob- lem by rerouting the power flow via topological control, which is more cost-effective than redispatch measures. While reinforcement learning has shown promise in optimizing such topology changes, existing reinforce- ment learning environments exhibit notable differences from real-world operations. To support research and bridge the gap to real-world ap- plications, we present PPTopoGym—a reinforcement learning environ- ment for evaluating the impact of topology actions on the power flow in pandapower-based grids. It allows for simulations with variable load and generation profiles, and supports direct computation of key grid security metrics, i.e., N−0 and N−1 security constraints for each time step. PP- TopoGym addresses key limitations of existing environments by enabling realistic grid modeling and the integration of real-world data. The code is publicly available.
@inproceedings{kohler2025pptopogym, abstract = {Power grids are facing growing challenges, arising from the increasing share of renewable energy sources and highly variable loads, in- troducing significant variability into both power generation and demand. This variability can create transmission line bottlenecks, which in turn lead to overheating. Transmission system operators address this prob- lem by rerouting the power flow via topological control, which is more cost-effective than redispatch measures. While reinforcement learning has shown promise in optimizing such topology changes, existing reinforce- ment learning environments exhibit notable differences from real-world operations. To support research and bridge the gap to real-world ap- plications, we present PPTopoGym—a reinforcement learning environ- ment for evaluating the impact of topology actions on the power flow in pandapower-based grids. It allows for simulations with variable load and generation profiles, and supports direct computation of key grid security metrics, i.e., N−0 and N−1 security constraints for each time step. PP- TopoGym addresses key limitations of existing environments by enabling realistic grid modeling and the integration of real-world data. The code is publicly available.}, author = {Köhler, Dominik and Hassouna, Mohamed and Degtyar, Dmitry and Krauß, Jonas and Brendlicger, Kurt and Scholz, Christoph}, booktitle = {Workshop on Machine Learning for Sustainable Power Systems (ML4SPS 2025), ECML PKDD}, keywords = {itegpub}, note = {(accepted)}, publisher = {Springer}, title = {PPTopoGym: Towards an RL Environment for Topology Actions on Power Grids}, year = 2025 }
%0 Conference Paper %1 kohler2025pptopogym %A Köhler, Dominik %A Hassouna, Mohamed %A Degtyar, Dmitry %A Krauß, Jonas %A Brendlicger, Kurt %A Scholz, Christoph %B Workshop on Machine Learning for Sustainable Power Systems (ML4SPS 2025), ECML PKDD %D 2025 %I Springer %T PPTopoGym: Towards an RL Environment for Topology Actions on Power Grids %X Power grids are facing growing challenges, arising from the increasing share of renewable energy sources and highly variable loads, in- troducing significant variability into both power generation and demand. This variability can create transmission line bottlenecks, which in turn lead to overheating. Transmission system operators address this prob- lem by rerouting the power flow via topological control, which is more cost-effective than redispatch measures. While reinforcement learning has shown promise in optimizing such topology changes, existing reinforce- ment learning environments exhibit notable differences from real-world operations. To support research and bridge the gap to real-world ap- plications, we present PPTopoGym—a reinforcement learning environ- ment for evaluating the impact of topology actions on the power flow in pandapower-based grids. It allows for simulations with variable load and generation profiles, and supports direct computation of key grid security metrics, i.e., N−0 and N−1 security constraints for each time step. PP- TopoGym addresses key limitations of existing environments by enabling realistic grid modeling and the integration of real-world data. The code is publicly available.
Human-AI interaction in safety-critical network infrastructures.Mussi, Marco; Metelli, Alberto Maria; Restelli, Marcello; Losapio, Gianvito; Bessa, Ricardo J.; Boos, Daniel; Borst, Clark; Leto, Giulia; Castagna, Alberto; Chavarriaga, Ricardo; Dias, Duarte; Egli, Adrian; Eisenegger, Andrina; El Manyari, Yassine; Fuxjäger, Anton; Geraldes, Joaquim; Hamouche, Samira; Hassouna, Mohamed; Lemetayer, Bruno; Leyli-Abadi, Milad; Liessner, Roman; Lundberg, Jonas; Marot, Antoine; Meddeb, Maroua; Schiaffonati, Viola; Schneider, Manuel; Stadelmann, Thilo; Usher, Julia; Van Hoof, Herke; Viebahn, Jan; Waefler, Toni; Zanotti, Giacomo. In iScience, 28(9), bl 113400. Elsevier, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Artificial Intelligence (AI) is transforming every aspect of modern society. It demonstrates a high potential to contribute to more flexible operations of safety-critical network infrastructures under deep transformation to tackle global challenges, such as climate change, energy transition, efficiency, and digital transformation, including increasing infrastructure resilience to natural and human-made hazards. The widespread adoption of AI creates the conditions for a new and inevitable interaction between humans and AI-based decision systems. In such a scenario, creating an ecosystem in which humans and AI interact healthily, where the roles and positions of both actors are well-defined, is a critical challenge for research and industry in the coming years. This perspective article outlines the challenges and requirements for effective human-AI interaction by taking an interdisciplinary point of view that merges computer science, decision-making sciences, psychological constructs, and industrial practices. The work focuses on three emblematic safety-critical scenarios from two different domains: energy (power grids) and mobility (railway networks and air traffic management)
@article{mussi2025human, abstract = {Artificial Intelligence (AI) is transforming every aspect of modern society. It demonstrates a high potential to contribute to more flexible operations of safety-critical network infrastructures under deep transformation to tackle global challenges, such as climate change, energy transition, efficiency, and digital transformation, including increasing infrastructure resilience to natural and human-made hazards. The widespread adoption of AI creates the conditions for a new and inevitable interaction between humans and AI-based decision systems. In such a scenario, creating an ecosystem in which humans and AI interact healthily, where the roles and positions of both actors are well-defined, is a critical challenge for research and industry in the coming years. This perspective article outlines the challenges and requirements for effective human-AI interaction by taking an interdisciplinary point of view that merges computer science, decision-making sciences, psychological constructs, and industrial practices. The work focuses on three emblematic safety-critical scenarios from two different domains: energy (power grids) and mobility (railway networks and air traffic management)}, author = {Mussi, Marco and Metelli, Alberto Maria and Restelli, Marcello and Losapio, Gianvito and Bessa, Ricardo J. and Boos, Daniel and Borst, Clark and Leto, Giulia and Castagna, Alberto and Chavarriaga, Ricardo and Dias, Duarte and Egli, Adrian and Eisenegger, Andrina and El Manyari, Yassine and Fuxjäger, Anton and Geraldes, Joaquim and Hamouche, Samira and Hassouna, Mohamed and Lemetayer, Bruno and Leyli-Abadi, Milad and Liessner, Roman and Lundberg, Jonas and Marot, Antoine and Meddeb, Maroua and Schiaffonati, Viola and Schneider, Manuel and Stadelmann, Thilo and Usher, Julia and Van Hoof, Herke and Viebahn, Jan and Waefler, Toni and Zanotti, Giacomo}, journal = {iScience}, keywords = {itegpub}, number = 9, pages = 113400, publisher = {Elsevier}, title = {Human-AI interaction in safety-critical network infrastructures}, volume = 28, year = 2025 }
%0 Journal Article %1 mussi2025human %A Mussi, Marco %A Metelli, Alberto Maria %A Restelli, Marcello %A Losapio, Gianvito %A Bessa, Ricardo J. %A Boos, Daniel %A Borst, Clark %A Leto, Giulia %A Castagna, Alberto %A Chavarriaga, Ricardo %A Dias, Duarte %A Egli, Adrian %A Eisenegger, Andrina %A El Manyari, Yassine %A Fuxjäger, Anton %A Geraldes, Joaquim %A Hamouche, Samira %A Hassouna, Mohamed %A Lemetayer, Bruno %A Leyli-Abadi, Milad %A Liessner, Roman %A Lundberg, Jonas %A Marot, Antoine %A Meddeb, Maroua %A Schiaffonati, Viola %A Schneider, Manuel %A Stadelmann, Thilo %A Usher, Julia %A Van Hoof, Herke %A Viebahn, Jan %A Waefler, Toni %A Zanotti, Giacomo %D 2025 %I Elsevier %J iScience %N 9 %P 113400 %R 10.1016/j.isci.2025.113400 %T Human-AI interaction in safety-critical network infrastructures %U https://www.cell.com/iscience/fulltext/S2589-0042(25)01661-X %V 28 %X Artificial Intelligence (AI) is transforming every aspect of modern society. It demonstrates a high potential to contribute to more flexible operations of safety-critical network infrastructures under deep transformation to tackle global challenges, such as climate change, energy transition, efficiency, and digital transformation, including increasing infrastructure resilience to natural and human-made hazards. The widespread adoption of AI creates the conditions for a new and inevitable interaction between humans and AI-based decision systems. In such a scenario, creating an ecosystem in which humans and AI interact healthily, where the roles and positions of both actors are well-defined, is a critical challenge for research and industry in the coming years. This perspective article outlines the challenges and requirements for effective human-AI interaction by taking an interdisciplinary point of view that merges computer science, decision-making sciences, psychological constructs, and industrial practices. The work focuses on three emblematic safety-critical scenarios from two different domains: energy (power grids) and mobility (railway networks and air traffic management)
Graph Neural Networks for Grid Control: Prospects in AI-assisted Transmission Grid Operation.Holzhueter, Clara; Lytaev, Pawel; Dipp, Marcel; Hassouna, Mohamed; Brendlinger, Kurt; Viebahn, Jan; Gegelman, Wiktor; Merz, Christian. In ETG Kongress 2025; Voller Energie – heute und morgen., bll 874–881. VDE, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Transmission grid congestion management and outage planning are critical tasks in modern grid operation due to the non-linear nature of power flows and the large-scale optimization challenges faced by operators. Traditionally, overloads are addressed through generator redispatch, a costly and therefore suboptimal measure. In the project "Graph Neural Networks for Grid Control" (GNN4GC), we investigate alternative strategies, focusing on topological remedial actions that could minimize or even completely eliminate redispatch costs. Topology optimization, a core aspect of this project, presents significant challenges due to its combinatorial nature, requiring extensive computational resources for power flow calculations. To address this, GNN4GC is split into three stages. In the first stage, we explore the use of Graph Neural Networks (GNNs) to accelerate these calculations and benchmark their performance against established tools like pandapower and a DC power flow solver developed by 50Hertz Transmission GmbH and TenneT TSO GmbH. In the second stage, we use Reinforcement Learning and other heuristics to select suitable topologies and solve the topology optimization problem. As a third stage, we test the respective agent on real-life grids to benchmark the methodology. The aim of the final stage is to build a recommender system that can be used in a control room in the future.
@inproceedings{holzhueter2025graph, abstract = {Transmission grid congestion management and outage planning are critical tasks in modern grid operation due to the non-linear nature of power flows and the large-scale optimization challenges faced by operators. Traditionally, overloads are addressed through generator redispatch, a costly and therefore suboptimal measure. In the project "Graph Neural Networks for Grid Control" (GNN4GC), we investigate alternative strategies, focusing on topological remedial actions that could minimize or even completely eliminate redispatch costs. Topology optimization, a core aspect of this project, presents significant challenges due to its combinatorial nature, requiring extensive computational resources for power flow calculations. To address this, GNN4GC is split into three stages. In the first stage, we explore the use of Graph Neural Networks (GNNs) to accelerate these calculations and benchmark their performance against established tools like pandapower and a DC power flow solver developed by 50Hertz Transmission GmbH and TenneT TSO GmbH. In the second stage, we use Reinforcement Learning and other heuristics to select suitable topologies and solve the topology optimization problem. As a third stage, we test the respective agent on real-life grids to benchmark the methodology. The aim of the final stage is to build a recommender system that can be used in a control room in the future.}, author = {Holzhueter, Clara and Lytaev, Pawel and Dipp, Marcel and Hassouna, Mohamed and Brendlinger, Kurt and Viebahn, Jan and Gegelman, Wiktor and Merz, Christian}, booktitle = {ETG Kongress 2025; Voller Energie – heute und morgen.}, keywords = {itegpub}, pages = {874–881}, publisher = {VDE}, title = {Graph Neural Networks for Grid Control: Prospects in AI-assisted Transmission Grid Operation}, year = 2025 }
%0 Conference Paper %1 holzhueter2025graph %A Holzhueter, Clara %A Lytaev, Pawel %A Dipp, Marcel %A Hassouna, Mohamed %A Brendlinger, Kurt %A Viebahn, Jan %A Gegelman, Wiktor %A Merz, Christian %B ETG Kongress 2025; Voller Energie – heute und morgen. %D 2025 %I VDE %P 874--881 %T Graph Neural Networks for Grid Control: Prospects in AI-assisted Transmission Grid Operation %U https://ieeexplore.ieee.org/abstract/document/11201946 %X Transmission grid congestion management and outage planning are critical tasks in modern grid operation due to the non-linear nature of power flows and the large-scale optimization challenges faced by operators. Traditionally, overloads are addressed through generator redispatch, a costly and therefore suboptimal measure. In the project "Graph Neural Networks for Grid Control" (GNN4GC), we investigate alternative strategies, focusing on topological remedial actions that could minimize or even completely eliminate redispatch costs. Topology optimization, a core aspect of this project, presents significant challenges due to its combinatorial nature, requiring extensive computational resources for power flow calculations. To address this, GNN4GC is split into three stages. In the first stage, we explore the use of Graph Neural Networks (GNNs) to accelerate these calculations and benchmark their performance against established tools like pandapower and a DC power flow solver developed by 50Hertz Transmission GmbH and TenneT TSO GmbH. In the second stage, we use Reinforcement Learning and other heuristics to select suitable topologies and solve the topology optimization problem. As a third stage, we test the respective agent on real-life grids to benchmark the methodology. The aim of the final stage is to build a recommender system that can be used in a control room in the future.
A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures.Leyli abadi, Milad; Bessa, Ricardo J.; Viebahn, Jan; Boos, Daniel; Borst, Clark; Castagna, Alberto; Chavarriaga, Ricardo; Hassouna, Mohamed; Lemetayer, Bruno; Leto, Giulia; Marot, Antoine; Meddeb, Maroua; Meyer, Manuel; Schiaffonati, Viola; Schneider, Manuel; Waefler, Toni. In IEEE International Conference on Systems, Man and Cybernetics (SMC). IEEE, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The interaction between humans and AI in safety-critical systems presents a unique set of challenges that remain partially addressed by existing frameworks. These challenges stem from the complex interplay of requirements for transparency, trust, and explainability, coupled with the necessity for robust and safe decision-making. A framework that holistically integrates human and AI capabilities while addressing these concerns is notably required, bridging the critical gaps in designing, deploying, and maintaining safe and effective systems. This paper proposes a holistic conceptual framework for critical infrastructures by adopting an interdisciplinary approach. It integrates traditionally distinct fields such as mathematics, decision theory, computer science, philosophy, psychology, and cognitive engineering and draws on specialized engineering domains, particularly energy, mobility, and aeronautics. Its flexibility is further demonstrated through a case study on power grid management.
@inproceedings{leyliabadi2025conceptual, abstract = {The interaction between humans and AI in safety-critical systems presents a unique set of challenges that remain partially addressed by existing frameworks. These challenges stem from the complex interplay of requirements for transparency, trust, and explainability, coupled with the necessity for robust and safe decision-making. A framework that holistically integrates human and AI capabilities while addressing these concerns is notably required, bridging the critical gaps in designing, deploying, and maintaining safe and effective systems. This paper proposes a holistic conceptual framework for critical infrastructures by adopting an interdisciplinary approach. It integrates traditionally distinct fields such as mathematics, decision theory, computer science, philosophy, psychology, and cognitive engineering and draws on specialized engineering domains, particularly energy, mobility, and aeronautics. Its flexibility is further demonstrated through a case study on power grid management.}, author = {Leyli abadi, Milad and Bessa, Ricardo J. and Viebahn, Jan and Boos, Daniel and Borst, Clark and Castagna, Alberto and Chavarriaga, Ricardo and Hassouna, Mohamed and Lemetayer, Bruno and Leto, Giulia and Marot, Antoine and Meddeb, Maroua and Meyer, Manuel and Schiaffonati, Viola and Schneider, Manuel and Waefler, Toni}, booktitle = {IEEE International Conference on Systems, Man and Cybernetics (SMC)}, keywords = {itegpub}, note = {(accepted)}, publisher = {IEEE}, title = {A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures}, year = 2025 }
%0 Conference Paper %1 leyliabadi2025conceptual %A Leyli abadi, Milad %A Bessa, Ricardo J. %A Viebahn, Jan %A Boos, Daniel %A Borst, Clark %A Castagna, Alberto %A Chavarriaga, Ricardo %A Hassouna, Mohamed %A Lemetayer, Bruno %A Leto, Giulia %A Marot, Antoine %A Meddeb, Maroua %A Meyer, Manuel %A Schiaffonati, Viola %A Schneider, Manuel %A Waefler, Toni %B IEEE International Conference on Systems, Man and Cybernetics (SMC) %D 2025 %I IEEE %R 10.48550/arXiv.2504.16133 %T A Conceptual Framework for AI-based Decision Systems in Critical Infrastructures %U https://arxiv.org/abs/2504.16133 %X The interaction between humans and AI in safety-critical systems presents a unique set of challenges that remain partially addressed by existing frameworks. These challenges stem from the complex interplay of requirements for transparency, trust, and explainability, coupled with the necessity for robust and safe decision-making. A framework that holistically integrates human and AI capabilities while addressing these concerns is notably required, bridging the critical gaps in designing, deploying, and maintaining safe and effective systems. This paper proposes a holistic conceptual framework for critical infrastructures by adopting an interdisciplinary approach. It integrates traditionally distinct fields such as mathematics, decision theory, computer science, philosophy, psychology, and cognitive engineering and draws on specialized engineering domains, particularly energy, mobility, and aeronautics. Its flexibility is further demonstrated through a case study on power grid management.

2024[ to top ]

Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis.Lehna, Malte; Hassouna, Mohamed; Degtyar, Dmitry; Tomforde, Sven; Scholz, Christoph. In Machine Learning for Sustainable Power Systems (ML4SPS), ECML. Springer, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.
@inproceedings{lehna2024fault, abstract = {Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.}, author = {Lehna, Malte and Hassouna, Mohamed and Degtyar, Dmitry and Tomforde, Sven and Scholz, Christoph}, booktitle = {Machine Learning for Sustainable Power Systems (ML4SPS), ECML}, keywords = {itegpub}, note = {(accepted)}, publisher = {Springer}, title = {Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis}, year = 2024 }
%0 Conference Paper %1 lehna2024fault %A Lehna, Malte %A Hassouna, Mohamed %A Degtyar, Dmitry %A Tomforde, Sven %A Scholz, Christoph %B Machine Learning for Sustainable Power Systems (ML4SPS), ECML %D 2024 %I Springer %T Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis %X Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.

2022[ to top ]

Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning.Hassouna, Mohamed. In Organic Computing -- Doctoral Dissertation Colloquium 2022, S. Tomforde, C. Krupitzer (reds.), bll 1–16. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.
@incollection{hassouna2022self, abstract = {Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.}, author = {Hassouna, Mohamed}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2022}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {1–16}, publisher = {kassel university press}, title = {Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning}, year = 2022 }
%0 Book Section %1 hassouna2022self %A Hassouna, Mohamed %B Organic Computing -- Doctoral Dissertation Colloquium 2022 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 1--16 %T Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning %X Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.