Adam Abdin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Adam Abdin has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Jakob Puchinger
EM Normandie Business School, Métis Lab, 92110 Clichy, France; and Université Paris-Saclay, CentraleSupélec, Laboratoire Génie Industriel, 91190 Gif-Sur-Yvette, France
8 shared publications - Yi-Ping Fang
Laboratoire Génie Industriel CentraleSupélec Université Paris-Saclay
8 shared publications - Flore Vallet6 shared publications
- Laura Mariana Reyes Madrigal
Laboratoire Génie Industriel (LGI), Université Paris-Saclay, CentraleSupélec, Gif-sur-Yvette, France
6 shared publications - Sebastian Hörl
Institut de Recherche Technologique SystemX
6 shared publications - Tjark Gall
Independent scholar
6 shared publications
Latest Publications
- 3 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Techno-economic modeling and robust optimization of power systems planning under a high share of renewable energy sources and extreme weather events
Modélisation technico-économique et optimisation robuste de la planification des systèmes de production électrique sous une large part de sources d'énergie renouvelables et d'événements climatiques extrêmes: Les objectifs récents en ce qui concerne la durabilité des systèmes électriques et l'atténuation des menaces liées au changement climatique modifient la portée des exigences de planification de ces systèmes. D'une part, les systèmes durables d'énergie à faible émission de carbone qui comportent une part élevée de sources d'énergie renouvelables intermittentes(IRES) se caractérisent par une forte augmentation de la variabilité intertemporelle et nécessitent des systèmes flexibles capables d'assurer la sécurité de l'approvisionnement électrique. D'autre part, la fréquence et la gravité accrues des phénomènes climatiques extrêmes menacent la fiabilité du fonctionnement des réseaux électriques et exigent des systèmes résilients capables de résister à ces impacts potentiels. Tout en s'assurant que les incertitudes inhérentes au système sont bien prises en compte directement au moment de la prise des décisions de planification à long terme. Dans ce contexte, la présente thèse vise à développer une modélisation technicoéconomique et un cadre d'optimisation robuste pour la planification des systèmes électriques multi-périodes en considérant une part élevée d'IRES et la résilience aux phénomènes climatiques extrêmes. Le problème spécifique de planification considéré est celui du choix de la technologie, de la taille et du programme de mise en service des unités de production conventionnelles et renouvelables sous des contraintes techniques, économiques,environnementales et opérationnelles. Dans le cadre de ce problème, les principales questions de recherche à aborder sont : (i) l'intégration et l'évaluation appropriées des besoins de flexibilité opérationnelle en raison de la variabilité accrue des parts élevées de la production d'IRES, (ii) la modélisation et l'intégration appropriées des exigences de résilience contre les phénomènes climatiques extrêmes dans la planification du système électrique et (iii) le traitement des incertitudes inhérentes de l'offre et la demande dans ce cadre de planification. En résumé, les contributions originales de cette thèse sont :- Proposer un modèle de planification du système électrique intégré multi période avec des contraintes dynamiques et en considérant un pourcentage élevé de pénétration des énergies renouvelables.- Introduire la mesure du déficit de flexibilité prévu pour l'évaluation de la flexibilité opérationnelle.- Proposer un ensemble de modèles linéaires pour quantifier l'impact des vagues de chaleur extrêmes et de la disponibilité de l'eau sur le déclassement des unités de production d'énergie thermique et nucléaire, la production d'énergie renouvelable et la consommation électrique du système.- Présenter une méthode permettant d'intégrer explicitement l'impact des phénomènes climatiques extrêmes dans le modèle de planification du système électrique.- Traiter les incertitudes inhérentes aux paramètres de planification du système électrique par la mise en oeuvre d'un nouveau modèle d'optimisation adaptatif robuste à plusieurs phases.- Proposer une nouvelle méthode de solution basée sur l'approximation des règles de décision linéaires du modèle de planification robuste.- Appliquer le cadre proposé à des études de cas de taille pratique basées sur des projections climatiques réalistes et selon plusieurs scénarios de niveaux de pénétration des énergies renouvelables et de limites de carbone pour valider la pertinence de la modélisation globale pour des applications réelles.
- 3 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Techno-economic modeling and robust optimization of power systems planning under a high share of renewable energy sources and extreme weather events
Modélisation technico-économique et optimisation robuste de la planification des systèmes de production électrique sous une large part de sources d'énergie renouvelables et d'événements climatiques extrêmes: Les objectifs récents en ce qui concerne la durabilité des systèmes électriques et l'atténuation des menaces liées au changement climatique modifient la portée des exigences de planification de ces systèmes. D'une part, les systèmes durables d'énergie à faible émission de carbone qui comportent une part élevée de sources d'énergie renouvelables intermittentes(IRES) se caractérisent par une forte augmentation de la variabilité intertemporelle et nécessitent des systèmes flexibles capables d'assurer la sécurité de l'approvisionnement électrique. D'autre part, la fréquence et la gravité accrues des phénomènes climatiques extrêmes menacent la fiabilité du fonctionnement des réseaux électriques et exigent des systèmes résilients capables de résister à ces impacts potentiels. Tout en s'assurant que les incertitudes inhérentes au système sont bien prises en compte directement au moment de la prise des décisions de planification à long terme. Dans ce contexte, la présente thèse vise à développer une modélisation technicoéconomique et un cadre d'optimisation robuste pour la planification des systèmes électriques multi-périodes en considérant une part élevée d'IRES et la résilience aux phénomènes climatiques extrêmes. Le problème spécifique de planification considéré est celui du choix de la technologie, de la taille et du programme de mise en service des unités de production conventionnelles et renouvelables sous des contraintes techniques, économiques,environnementales et opérationnelles. Dans le cadre de ce problème, les principales questions de recherche à aborder sont : (i) l'intégration et l'évaluation appropriées des besoins de flexibilité opérationnelle en raison de la variabilité accrue des parts élevées de la production d'IRES, (ii) la modélisation et l'intégration appropriées des exigences de résilience contre les phénomènes climatiques extrêmes dans la planification du système électrique et (iii) le traitement des incertitudes inhérentes de l'offre et la demande dans ce cadre de planification. En résumé, les contributions originales de cette thèse sont :- Proposer un modèle de planification du système électrique intégré multi période avec des contraintes dynamiques et en considérant un pourcentage élevé de pénétration des énergies renouvelables.- Introduire la mesure du déficit de flexibilité prévu pour l'évaluation de la flexibilité opérationnelle.- Proposer un ensemble de modèles linéaires pour quantifier l'impact des vagues de chaleur extrêmes et de la disponibilité de l'eau sur le déclassement des unités de production d'énergie thermique et nucléaire, la production d'énergie renouvelable et la consommation électrique du système.- Présenter une méthode permettant d'intégrer explicitement l'impact des phénomènes climatiques extrêmes dans le modèle de planification du système électrique.- Traiter les incertitudes inhérentes aux paramètres de planification du système électrique par la mise en oeuvre d'un nouveau modèle d'optimisation adaptatif robuste à plusieurs phases.- Proposer une nouvelle méthode de solution basée sur l'approximation des règles de décision linéaires du modèle de planification robuste.- Appliquer le cadre proposé à des études de cas de taille pratique basées sur des projections climatiques réalistes et selon plusieurs scénarios de niveaux de pénétration des énergies renouvelables et de limites de carbone pour valider la pertinence de la modélisation globale pour des applications réelles.
- Open Access
- 5 February 2026
- Published by Elsevier in SSRN Electronic Journal
The Policy Frontier: Balancing Profitability and Equity in Public Autonomous Mobility with Deep Reinforcement Learning
As public transport authorities transition from pilot to scaling on-demand shared autonomous vehicle (SAV) services, they face a persistent challenge—improving economic viability without undermining equitable and affordable access. Dynamic pricing offers a potential mechanism to manage this trade-off by aligning fares with real-time demand and capacity conditions. However, its application in public SAV systems requires modelling and solution approaches that reflect public-service objectives. This paper develops a deep reinforcement learning framework to study dynamic pricing in a publicly operated SAV service. The pricing problem is formulated as a continuous-action Markov Decision Process and solved using Proximal Policy Optimisation, with capped fare adjustments. Using a simulation calibrated with operational data from an on-demand SAV pilot in Oslo, we compare static pricing with capped and uncapped dynamic pricing policies. The results indicate that static pricing preserves accessibility but constrains economic performance, while unconstrained dynamic pricing improves profitability at the cost of increased price dispersion and reduced service accessibility. In contrast, a capped dynamic pricing policy achieves a more balanced outcome by maintaining accessibility and price stability while retaining most of the efficiency gains from adaptive pricing. These findings suggest that dynamic pricing can support the economic viability of public SAV services when implemented as a regulated policy instrument. The proposed framework provides a policy-relevant basis for analysing efficiency–equity trade-offs in dynamic pricing for public MaaS services.
- 5 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessThe Policy Frontier: Balancing Profitability and Equity in Public Autonomous Mobility with Deep Reinforcement Learning
As public transport authorities transition from pilot to scaling on-demand shared autonomous vehicle (SAV) services, they face a persistent challenge—improving economic viability without undermining equitable and affordable access. Dynamic pricing offers a potential mechanism to manage this trade-off by aligning fares with real-time demand and capacity conditions. However, its application in public SAV systems requires modelling and solution approaches that reflect public-service objectives. This paper develops a deep reinforcement learning framework to study dynamic pricing in a publicly operated SAV service. The pricing problem is formulated as a continuous-action Markov Decision Process and solved using Proximal Policy Optimisation, with capped fare adjustments. Using a simulation calibrated with operational data from an on-demand SAV pilot in Oslo, we compare static pricing with capped and uncapped dynamic pricing policies. The results indicate that static pricing preserves accessibility but constrains economic performance, while unconstrained dynamic pricing improves profitability at the cost of increased price dispersion and reduced service accessibility. In contrast, a capped dynamic pricing policy achieves a more balanced outcome by maintaining accessibility and price stability while retaining most of the efficiency gains from adaptive pricing. These findings suggest that dynamic pricing can support the economic viability of public SAV services when implemented as a regulated policy instrument. The proposed framework provides a policy-relevant basis for analysing efficiency–equity trade-offs in dynamic pricing for public MaaS services.
- Open Access
Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments
We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a configurable encounter simulator, a distance-dependent observation model, and a sequential state estimator to represent uncertainty in relative motion. A central contribution of this work is the use of transformer-based Partially Observable Markov Decision Process (POMDP) architecture, which leverage long-range temporal attention to interpret noisy and intermittent observations more effectively than traditional architectures. This integration provides a foundation for training collision avoidance agents that can operate more reliably under imperfect monitoring environments.
Open AccessTransformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments
We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a configurable encounter simulator, a distance-dependent observation model, and a sequential state estimator to represent uncertainty in relative motion. A central contribution of this work is the use of transformer-based Partially Observable Markov Decision Process (POMDP) architecture, which leverage long-range temporal attention to interpret noisy and intermittent observations more effectively than traditional architectures. This integration provides a foundation for training collision avoidance agents that can operate more reliably under imperfect monitoring environments.
- Open Access
Toward Decision-Oriented Prognostics: An Integrated Estimate-Optimize Framework for Predictive Maintenance
Recent research increasingly integrates machine learning (ML) into predictive maintenance (PdM) to reduce operational and maintenance costs in data-rich operational settings. However, uncertainty due to model misspecification continues to limit widespread industrial adoption. This paper proposes a PdM framework in which sensor-driven prognostics inform decision-making under economic trade-offs within a finite decision space. We investigate two key questions: (1) Does higher predictive accuracy necessarily lead to better maintenance decisions? (2) If not, how can the impact of prediction errors on downstream maintenance decisions be mitigated? We first demonstrate that in the traditional estimate-then-optimize (ETO) framework, errors in probabilistic prediction can result in inconsistent and suboptimal maintenance decisions. To address this, we propose an integrated estimate-optimize (IEO) framework that jointly tunes predictive models while directly optimizing for maintenance outcomes. We establish theoretical finite-sample guarantees on decision consistency under standard assumptions. Specifically, we develop a stochastic perturbation gradient descent algorithm suitable for small run-to-failure datasets. Empirical evaluations on a turbofan maintenance case study show that the IEO framework reduces average maintenance regret up to 22% compared to ETO. This study provides a principled approach to managing prediction errors in data-driven PdM. By aligning prognostic model training with maintenance objectives, the IEO framework improves robustness under model misspecification and improves decision quality. The improvement is particularly pronounced when the decision-making policy is misaligned with the decision-maker's target. These findings support more reliable maintenance planning in uncertain operational environments.
Open AccessToward Decision-Oriented Prognostics: An Integrated Estimate-Optimize Framework for Predictive Maintenance
Recent research increasingly integrates machine learning (ML) into predictive maintenance (PdM) to reduce operational and maintenance costs in data-rich operational settings. However, uncertainty due to model misspecification continues to limit widespread industrial adoption. This paper proposes a PdM framework in which sensor-driven prognostics inform decision-making under economic trade-offs within a finite decision space. We investigate two key questions: (1) Does higher predictive accuracy necessarily lead to better maintenance decisions? (2) If not, how can the impact of prediction errors on downstream maintenance decisions be mitigated? We first demonstrate that in the traditional estimate-then-optimize (ETO) framework, errors in probabilistic prediction can result in inconsistent and suboptimal maintenance decisions. To address this, we propose an integrated estimate-optimize (IEO) framework that jointly tunes predictive models while directly optimizing for maintenance outcomes. We establish theoretical finite-sample guarantees on decision consistency under standard assumptions. Specifically, we develop a stochastic perturbation gradient descent algorithm suitable for small run-to-failure datasets. Empirical evaluations on a turbofan maintenance case study show that the IEO framework reduces average maintenance regret up to 22% compared to ETO. This study provides a principled approach to managing prediction errors in data-driven PdM. By aligning prognostic model training with maintenance objectives, the IEO framework improves robustness under model misspecification and improves decision quality. The improvement is particularly pronounced when the decision-making policy is misaligned with the decision-maker's target. These findings support more reliable maintenance planning in uncertain operational environments.
- Open Access
Hazard Intensity Threshold for Exposure Modeling of Systems of Interest to Climate Change
This Preprint was prepared for ESREL 2025.
Open AccessHazard Intensity Threshold for Exposure Modeling of Systems of Interest to Climate Change
This Preprint was prepared for ESREL 2025.
- Open Access
Toward Decision-Oriented Prognostics: An Integrated Estimate-Optimize Framework for Predictive Maintenance
Recent research increasingly integrates machine learning (ML) into predictive maintenance (PdM) to reduce operational and maintenance costs in data-rich operational settings. However, uncertainty due to model misspecification continues to limit widespread industrial adoption. This paper investigates a PdM framework in which sensor-driven prognostics inform decision-making under economic trade-offs within a finite decision space. We investigate two key questions: (1) Does higher predictive accuracy necessarily lead to better maintenance decisions? (2) If not, how can the impact of prediction errors on downstream maintenance decisions be mitigated? We first demonstrate that in the traditional estimate-then-optimize (ETO) framework, errors in probabilistic prediction can result in inconsistent and suboptimal maintenance decisions. To address this, we propose an integrated estimate-optimize (IEO) framework that jointly tunes predictive models while directly optimizing for maintenance outcomes. We establish theoretical finite-sample guarantees on decision consistency under standard assumptions. Specifically, we develop a stochastic perturbation gradient descent algorithm suitable for small run-to-failure datasets. Empirical evaluations on a turbofan maintenance case study show that the IEO framework reduces average maintenance regret up to 22% compared to ETO. This study provides a principled approach to managing prediction errors in data-driven PdM. By aligning prognostic model training with maintenance objectives, the IEO framework improves robustness under model misspecification and improves decision quality. The improvement is particularly pronounced when the decision-making policy is misaligned with the decision-maker's target. These findings support more reliable maintenance planning in uncertain operational environments.
Open AccessToward Decision-Oriented Prognostics: An Integrated Estimate-Optimize Framework for Predictive Maintenance
Recent research increasingly integrates machine learning (ML) into predictive maintenance (PdM) to reduce operational and maintenance costs in data-rich operational settings. However, uncertainty due to model misspecification continues to limit widespread industrial adoption. This paper investigates a PdM framework in which sensor-driven prognostics inform decision-making under economic trade-offs within a finite decision space. We investigate two key questions: (1) Does higher predictive accuracy necessarily lead to better maintenance decisions? (2) If not, how can the impact of prediction errors on downstream maintenance decisions be mitigated? We first demonstrate that in the traditional estimate-then-optimize (ETO) framework, errors in probabilistic prediction can result in inconsistent and suboptimal maintenance decisions. To address this, we propose an integrated estimate-optimize (IEO) framework that jointly tunes predictive models while directly optimizing for maintenance outcomes. We establish theoretical finite-sample guarantees on decision consistency under standard assumptions. Specifically, we develop a stochastic perturbation gradient descent algorithm suitable for small run-to-failure datasets. Empirical evaluations on a turbofan maintenance case study show that the IEO framework reduces average maintenance regret up to 22% compared to ETO. This study provides a principled approach to managing prediction errors in data-driven PdM. By aligning prognostic model training with maintenance objectives, the IEO framework improves robustness under model misspecification and improves decision quality. The improvement is particularly pronounced when the decision-making policy is misaligned with the decision-maker's target. These findings support more reliable maintenance planning in uncertain operational environments.
- 1 January 2025
- Published by Research Publishing Services
- p. 517-524
Hazard Intensity Threshold for Exposure Modeling of Systems of Interest to Climate Change
- 1 January 2025
- Published by Research Publishing Services
- p. 517-524
Hazard Intensity Threshold for Exposure Modeling of Systems of Interest to Climate Change
- 1 January 2025
- Published by Research Publishing Services
- p. 2868-2875
Space Systems as Critical Infrastructure - A Soft Systems Approach
- 1 January 2025
- Published by Research Publishing Services
- p. 2868-2875
Space Systems as Critical Infrastructure - A Soft Systems Approach
- 1 January 2025
- Published by Research Publishing Services
- p. 1514-1521
Decision-Focused Predictive Maintenance: Bridging the Gap between Data-Driven RUL Prognostics and Maintenance Planning
- 1 January 2025
- Published by Research Publishing Services
- p. 1514-1521
Decision-Focused Predictive Maintenance: Bridging the Gap between Data-Driven RUL Prognostics and Maintenance Planning
- 1 January 2025
- Published by Research Publishing Services
- p. 1065-1072
Condition-Based Maintenance for Large-Scale Fleets under Multiple Constraints: A Constrained MDP Model with Primal-Dual Solution
- 1 January 2025
- Published by Research Publishing Services
- p. 1065-1072
Condition-Based Maintenance for Large-Scale Fleets under Multiple Constraints: A Constrained MDP Model with Primal-Dual Solution