Jochen L. Cremer

Jochen L. Cremer

he/him

Electrical Power Engineer with Computer Science Expertise, PhD Imperial College London, MSc BSc BSc RWTH Aachen University

Posts by Collection

projects

AI EFFECT: Testing and Experimentation Facilities for the energy sector – bringing technology to the market

As the digital age transforms the energy landscape, the integration of artificial intelligence (AI) into critical energy infrastructure is set to boost efficiency, resilience, and sustainability. To drive this innovation, the AI-EFFECT project has been launched, aimed at accelerating the development, testing, and validation of AI applications in the energy sector. The project will run until September 2027 and is funded by the European Union’s Horizon Europe programme, under agreement no. 101172952.

Research Programme on Power Systems Operation & Planning with AI: AIT and TU Delft

AI-based approaches have emerged to accelerate the transformation of our energy systems toward sustainability. With digitalisation revolutionising the energy sector, there is now a vast potential to achieve more efficient, reliable, and secure operation of our energy infrastructure. Artificial Intelligence (AI) has become a powerful and disruptive tool for decision-making, helping to tackle the increased complexity and uncertainty of the transition towards a sustainable and renewable energy system.

Delft AI Energy Lab

Energy systems are the backbone of our modern society. It is of great importance that these systems are sustainable, reliable and effective now and in the future. There is strong expertise in this field on the TU Delft campus. The Delft AI Energy Lab investigates how new AI-based methods can contribute to the management of dynamic energy systems. Therefore we combine groundbreaking machine learning with the reliable theory of the physical energy system. For example, it is possible with the AI technique ‘neural networks’ to model differential equations describing dynamics in areas such as fluid dynamics, and for predicting extreme, rare events. Delft AI Energy Lab investigates these promising methods for applicability for monitoring the ‘health’ of parts of energy systems, and for the early detection of threats.

GAIM: Graph-based AI Monitoring Tools for Complex-Systems

The project aims to develop a heterogeneous Graph Neural Network architecture for identifying and learning active topologies in distribution grids based on measurement data. This will address challenges related to varying topologies and provide a feasible solution within a guaranteed convergence time.

MEGAMIND Measuring, Gathering, Mining and Integrating Data for Self-management in the Edge of the Electricity System

Network operators and market parties are looking for ways to prevent intelligently overloading the network and to link supply and demand. The MEGAMIND programme brings together knowledge of energy systems, artificial intelligence and regulation to develop both the necessary technology and appropriate regulations. The researchers aim to develop models to predict when problems will arise. Then, they will have devices that consume energy interact directly with devices that produce energy to avoid these situations.

ROBUST Trustworthy AI-based Systems for Sustainable Growth ROBUST ICAI Project

ROBUST ‘Trustworthy AI systems for sustainable growth’ is a Long Term Program (LTP) from NWO. The robust program aims to achieve breakthroughs in five core dimensions of robust artificial intelligence (AI): accuracy, reliability, repeatability, resilience, and security. The reliability of an AI-based system is formalized through so-called contracts, that is, explicit guarantees about the intended behavior of the system. Explanations can bring intrinsic confidence to general users. Therefore, the development of explanation and evaluation methods is an essential part of this research.

NWO Veni: Physics-informed AI to avoid power blackouts in the energy transition

The energy grid of the future will use a complex network of small, sustainable energy sources, such as solar panels and wind turbines. Increased complexity will make the network vulnerable to disruptions, made still worse by the extreme weather events caused by far-reaching climate change. Sudden catastrophic power outages can take place that potentially last for months and span entire regions, with serious consequences for society. Effective countermeasures depend on understanding the causes of these blackouts quickly, thsi research uses artificial intelligence both to predict power outages and to identify and address effective solutions. By managing these risks, the research will help to accelerate the energy transition and protect society from the next pan-European power outage.

publications

Electric Energy Procurement for Large Industrial Consumers Under Uncertainty in Electricity Price and Product Demand

Published in AIChE Annual Meeting, USA, 2014

This paper examines electric energy procurement strategies for large industrial consumers, considering uncertainties in electricity prices and product demand. The approach balances cost efficiency with risk mitigation.

Recommended citation: Zhang, Q., Cremer, J. L., Grossmann, I. E., Sundaramoorthy, A., & Pinto, J. M. (2014). 'Electric Energy Procurement for Large Industrial Consumers Under Uncertainty in Electricity Price and Product Demand.' AIChE Annual Meeting, USA, 366568.

Risk-Based Integrated Production Scheduling and Electricity Procurement for Continuous Power-Intensive Processes

Published in Computers & Chemical Engineering, 2016

This paper proposes a risk-based integrated approach to production scheduling and electricity procurement for continuous power-intensive processes. The framework optimizes operational efficiency while managing market risks.

Recommended citation: Zhang, Q., Cremer, J. L., Grossmann, I. E., Sundaramoorthy, A., & Pinto, J. M. (2016). 'Risk-Based Integrated Production Scheduling and Electricity Procurement for Continuous Power-Intensive Processes.' Computers & Chemical Engineering, 86, 90-105.
Download Paper

Optimal Scheduling of Heat Pumps for Power Peak Shaving and Customers’ Thermal Comfort

Published in International Conference on Smart Cities and Green ICT Systems, Portugal, 2017

This paper presents an optimal scheduling framework for heat pumps aimed at peak shaving while maintaining customers’ thermal comfort. The approach balances energy efficiency and user satisfaction.

Recommended citation: Cremer, J. L., Pau, M., Ponci, F., & Monti, A. (2017). 'Optimal Scheduling of Heat Pumps for Power Peak Shaving and Customers’ Thermal Comfort.' International Conference on Smart Cities and Green ICT Systems, Portugal, 23-34.
Download Paper

Impact of Customers Flexibility in Heat Pumps Scheduling for Demand Side Management

Published in IEEE International Conference on Environment and Electrical Engineering, 2017

This study investigates the role of customer flexibility in scheduling heat pumps for demand-side management. The findings highlight the potential for improved energy distribution and grid stability.

Recommended citation: Pau, M., Cremer, J. L., Ponci, F., & Monti, A. (2017). 'Impact of Customers Flexibility in Heat Pumps Scheduling for Demand Side Management.' IEEE International Conference on Environment and Electrical Engineering, 1-6.
Download Paper

Sample-Derived Disjunctive Rules for Secure Power System Operation

Published in IEEE International Conference on Probabilistic Methods Applied to Power Systems, Boise, USA, 2018

This research introduces a sample-derived approach to formulating disjunctive rules for secure power system operation. The method enhances operational decision-making under uncertain grid conditions.

Recommended citation: Cremer, J. L., Konstantelos, I., Tindemans, S. H., & Strbac, G. (2018). 'Sample-Derived Disjunctive Rules for Secure Power System Operation.' IEEE International Conference on Probabilistic Methods Applied to Power Systems, Boise, USA, 1-6.
Download Paper

A Novel Data-Driven Scenario Generation Framework for Transmission Expansion Planning with High Renewable Energy Penetration

Published in Applied Energy, 2018

This research introduces a data-driven scenario generation framework for transmission expansion planning under high renewable energy penetration. The methodology addresses uncertainty and enhances planning robustness.

Recommended citation: Sun, M., Cremer, J. L., & Strbac, G. (2018). 'A Novel Data-Driven Scenario Generation Framework for Transmission Expansion Planning with High Renewable Energy Penetration.' Applied Energy, 228, 546-555.
Download Paper

Day-Ahead Scheduling of Electric Heat Pumps for Peak Shaving in Distribution Grids

Published in Communications in Computer and Information Science, Springer Journal, 2018

This paper presents a day-ahead scheduling framework for electric heat pumps, aimed at peak shaving in distribution grids. The approach optimizes energy usage while maintaining thermal comfort.

Recommended citation: Pau, M., Cremer, J. L., Ponci, F., & Monti, A. (2018). 'Day-Ahead Scheduling of Electric Heat Pumps for Peak Shaving in Distribution Grids.' Communications in Computer and Information Science, 921, 27–51.
Download Paper

Data-Driven Power System Operation: Exploring the Balance Between Cost and Risk

Published in IEEE Transactions on Power Systems, 2019

This paper explores data-driven approaches to power system operation, focusing on balancing cost and risk. It provides insights into optimizing operational decisions using advanced data analytics.

Recommended citation: Cremer, J. L., Konstantelos, I., Tindemans, S. H., & Strbac, G. (2019). 'Data-Driven Power System Operation: Exploring the Balance Between Cost and Risk.' IEEE Transactions on Power Systems, 34 (1), 791-801.
Download Paper

Optimized Operation Rules for Imbalanced Classes

Published in IEEE PES General Meeting of Power Systems, 2019

This paper introduces optimized operational rules tailored for imbalanced datasets in power systems. The proposed methodology enhances decision-making accuracy and system reliability under skewed data distributions.

Recommended citation: Cremer, J. L., Konstantelos, I., & Strbac, G. (2019). 'Optimized Operation Rules for Imbalanced Classes.' IEEE PES General Meeting of Power Systems.
Download Paper

From Optimization-Based Machine Learning to Interpretable Security Rules for Operation

Published in IEEE Transactions on Power Systems, 2019

This study develops interpretable security rules for power system operation using optimization-based machine learning techniques. The framework bridges the gap between machine learning models and operational insights.

Recommended citation: Cremer, J. L., Konstantelos, I., & Strbac, G. (2019). 'From Optimization-Based Machine Learning to Interpretable Security Rules for Operation.' IEEE Transactions on Power Systems, 34 (5), 5678-5690.
Download Paper

Published in , 1900

Operating strategies and preparedness for system operational resilience

Published in CIGRE Technical Brochure 833, Working Group C2.25, 2021

CIGRE C2.25 Working Group’s focus has been on operating strategies and preparedness for system operational resilience. The role of system operation is classified into power system resilience. For this objective, the WG prepared two surveys and assessed the responses of the respondents to the difference in understanding of resilience and reliability, the degree to which relevant HILF events have happened in different parts of the world and the operational resilience strategies that have been used to measure and manage these situations. Furthermore, improvements in the operational resilience have been the subject of questions in the surveys.

Recommended citation: CIGRE TB 833, 'Operating strategies and preparedness for system operational resilience', CIGRE WG C2.25.
Download Paper

A Confidence-Aware Machine-Learned Framework for Dynamic Security Assessment

Published in IEEE Transactions on Power Systems, 2021

This research introduces a confidence-aware machine-learned framework for dynamic security assessment (DSA) in power systems. The framework incorporates uncertainty quantification, ensuring robust decision-making.

Recommended citation: Zhang, T., Sun, M., Cremer, J. L., & Strbac, G. (2021). 'A Confidence-Aware Machine-Learned Framework for Dynamic Security Assessment.' IEEE Transactions on Power Systems, 36 (5), 1234-1245.
Download Paper

A Causality-Based Feature Selection Approach for Data-Driven Dynamic Security Assessment

Published in Electric Power Systems Research, 2021

This paper presents a causality-based feature selection methodology for dynamic security assessment. The approach enhances model interpretability and improves prediction accuracy in power systems.

Recommended citation: Bellizio, F., Cremer, J. L., & Strbac, G. (2021). 'A Causality-Based Feature Selection Approach for Data-Driven Dynamic Security Assessment.' Electric Power Systems Research, 201, 107537.
Download Paper

Selecting decision trees for power system security assessment

Published in Energy and AI, 2021

This study explores decision tree models for security assessment in power systems, using ROC and cost curves for model evaluation. The methodology optimizes decision-making for system reliability.

Recommended citation: Bugaje, A., Cremer, J. L., Sun, M., & Strbac, G. (2021). 'Selecting decision trees for power system security assessment.' Energy and AI, 6, 100110.
Download Paper

Machine-Learned Security Assessment for Changing System Topologies

Published in International Journal of Electrical Power & Energy Systems, 2022

This paper introduces a machine-learned framework for dynamic security assessment in power systems with evolving topologies. It demonstrates the adaptability of machine learning in diverse operational scenarios.

Recommended citation: Bellizio, F., Cremer, J. L., & Strbac, G. (2022). 'Machine-Learned Security Assessment for Changing System Topologies.' International Journal of Electrical Power & Energy Systems, 134, 107380.
Download Paper

State-of-the-Art of Data Collection, Analytics, and Future Needs of Transmission Utilities Worldwide

Published in International Journal of Electrical Power & Energy Systems, 2022

This collaborative paper reviews the current state of data collection and analytics in transmission utilities. It identifies future needs to support the growing demand for data-driven grid operations.

Recommended citation: Sevilla, F. R. S., Liu, Y., Barocio, E., Korba, P., & Cremer, J. L. (2022). 'State-of-the-Art of Data Collection, Analytics, and Future Needs of Transmission Utilities Worldwide.' International Journal of Electrical Power & Energy Systems, 137, 107772.
Download Paper

Verifying Machine Learning Conclusions for Securing Low Inertia Systems

Published in Sustainable Energy, Grids, and Networks, 2022

This paper focuses on verifying machine learning-based conclusions to secure low inertia power systems. It introduces a robust validation framework to enhance system reliability and operational trust.

Recommended citation: Bellizio, F., Bugaje, A.-A., Cremer, J. L., & Strbac, G. (2022). 'Verifying Machine Learning Conclusions for Securing Low Inertia Systems.' Sustainable Energy, Grids, and Networks, 30, 100656.
Download Paper

Transition to Digitalized Paradigms for Security Control and Decentralized Electricity Market

Published in IEEE Proceedings - Special Issue: The Evolution of Smart Grids, 2022

This paper examines the transition to secure, data-driven grid control and decentralized electricity markets. It discusses novel frameworks for leveraging data analytics to ensure grid reliability.

Recommended citation: Bellizio, F., Zu, W., Qiu, D., Ye, Y., & Cremer, J. L. (2022). 'Transition to Digitalized Paradigms for Security Control and Decentralized Electricity Market, 111(7), 1234-1245.
Download Paper

Perspectives on Future Power System Control Centers for Energy Transition

Published in IEEE Journal of Modern Power Systems and Clean Energy, 2022

This study explores the evolving role of power system control centers in the energy transition. It outlines new strategies and technologies to enhance grid stability and support renewable integration.

Recommended citation: Marot, A., Kelly, A., Naglic, M., Barbesant, V., Cremer, J. L., & Stefanov, A. (2022). 'Perspectives on Future Power System Control Centers for Energy Transition.' IEEE Journal of Modern Power Systems and Clean Energy, 10, 328-344.
Download Paper

Present situation on data acquisition, handling, and analytics of operators of the transmission system in different countries and their future needs to cope with the continuous growth of data

Published in IEEE PES Technical Brochure, IEEE PES-TR100, 2022

Presently, transmission system operators are tackling challenging dynamic issues in scenarios close to real-time utilizing their dynamic stability assessment tools and data acquisition devices that have in operation. These devices use different types of technology and the majority of the tools used in the control centers are tailored to each of them. Most challenges affecting the security of these systems are associated with current paradigms of management and planning such as the inclusion of deregulated markets, the interconnection with neighboring regional systems, the diversification of energy sources, and the involvement of environmental constraints. Under these conditions, the security and reliability of the transmission system can be compromised with unexpected disturbances causing violations of the security limits established and subsequently leading to the system collapse. To contribute to the finding of solutions to these problems, the members of this IEEE Task Force have worked together to gather information from eleven utilities in nine different countries in America and Europe. The main objective is to establish a baseline of these common concerns, which can be used to develop, in the next step, solutions based on machine learning and data-driven innovative algorithms.

Recommended citation: Marcos Netto, Venkat Krishnan, Michael Ingram, Yajun Wang, Junbo Zhao, Emilio Barocio, Manuel Andrade, Juan Jose Guerrero, Jorge Mola, Jaime C. Cepeda, David Panchi, Aharon B. De La Torre, Diego E. Echeverría, Hector Chavez, Alberto Trigueros, Miguel Herrera, Jose Luis Rueda Torres, Simon Tindemans, Marnick Huijsman, Jorrit Bos, Danny Klaar, Petr Korba, Mats Larsson, Mario Paolone, Miguel Ramirez, Rusejla Sadikovic, Walter Sattinger, Rafael Segundo, Camille Hamon, Robert Eriksson, Jochen Cremer, et.al. 'Present situation on data acquisition, handling, and analytics of operators of the transmission system in different countries and their future needs to cope with the continuous growth of data', IEEE PES Technical Brochure IEEE PES-TR100, (2022).
Download Paper

Learning to Run a Power Network with Trust

Published in Electric Power Systems Research, 2022

This paper addresses the challenge of training power network operators to manage systems reliably under uncertainty. It introduces a framework for learning operational trust through data-driven models and simulations.

Recommended citation: Marot, A., Donnot, B., Chaouache, K., Kelly, A., & Cremer, J. L. (2022). 'Learning to Run a Power Network with Trust.' Electric Power Systems Research, 212, 108487.
Download Paper

Application of spatio-temporal data-driven and machine learning algorithms for security assessment taskforce”, by IEEE AMPS taskforce on Application of Big Data Analytics on Transmission Systems for Dynamic Security Assessment

Published in IEEE PES Technical Brochure, IEEE PES-TR104, 2022

This technical document summarizes recent advancements on spatio-temporal data-driven and machine learning methods for static and dynamic security assessment, and their particular use cases. It is a collective effort of different research groups with the aim of providing transmission system operators (TSOs) with innovative tools and ideas for their potential implementation. The algorithms presented here are classified as non-training and training approaches, namely spatio-temporal and machine learning based, considering as input time series from time domain simulations, and or synchrophasor data from wide-area monitoring systems. The efficacy of these algorithms is then evaluated in different IEEE benchmark models and real-power systems such as the Mexican, USA, Chilean, Brazilian, Ecuadorian, Japanese and Swedish systems, respectively..

Recommended citation: Rafael Segundo, Yanli Liu, Emilio Barocio, Petr Korba, Aharon de la Torre, Al-Amin Bugaje, Alejandro Zamora-Mendez, Alexandra Karpilow, Carlos Toledo, Claudia Caro-Ruiz, Daniel Dotta, Daniel Müller, David Panchi, Diego Echeverría, Federica Bellizio, Francisco Zelaya, Gabriel V. de S. Lopes, Gao Qiu, Garibaldi Pineda-Garcia, Goran Strbac, Hector Chavez, Hjörtur Jóhannsson, Jaime Cepeda, Jochen L. Cremer, et.al., 'Application of spatio-temporal data-driven and machine learning algorithms for security assessment', IEEE PES Technical Brochure IEEE PES-TR104, (2022).
Download Paper

Real-Time Transmission Switching with Neural Networks

Published in IET Generation, Transmission & Distribution, 2023

This research introduces a neural network-based approach for real-time transmission switching in power systems. The framework enhances system resilience and operational efficiency under dynamic conditions.

Recommended citation: Bugaje, A.-A., Cremer, J. L., & Strbac, G. (2023). 'Real-Time Transmission Switching with Neural Networks.' IET Generation, Transmission & Distribution, 17(3), 696-705.
Download Paper

Split-based sequential sampling for realtime security assessment

Published in International Journal of Electrical Power & Energy Systems, 2023

This paper proposes a split-based sequential sampling technique for real-time security assessment in power systems. The method improves assessment accuracy while reducing computational overhead.

Recommended citation: Bugaje, A.-A., Cremer, J. L., & Strbac, G. (2023). 'Split-based sequential sampling for realtime security assessment.' International Journal of Electrical Power & Energy Systems, 146, 108790.
Download Paper

MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-Based Residential Demand Response

Published in IEEE PowerTech 2023, Belgrade, Serbia, 2023

This study presents MARL-iDR, a multi-agent reinforcement learning approach for incentive-based residential demand response. The framework optimizes demand response participation and grid stability.

Recommended citation: van Tilburg, J., Siebert, L. C., & Cremer, J. L. (2023). 'MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-Based Residential Demand Response.' IEEE PowerTech 2023, Belgrade, Serbia, 1-8.
Download Paper

End-to-End Learning with Multiple Modalities for System-Optimised Renewables Nowcasting

Published in IEEE PowerTech 2023, Belgrade, Serbia, 2023

This paper introduces a multi-modal learning framework for renewable power prediction, specifically optimized for power flow. The approach enhances prediction accuracy and system efficiency.

Recommended citation: Vohra, R., Rajaei, A., & Cremer, J. L. (2023). 'End-to-End Learning with Multiple Modalities for System-Optimised Renewables Nowcasting.' IEEE PowerTech 2023, Belgrade, Serbia, 1-8.
Download Paper

Exploring Operational Flexibility of Active Distribution Networks with Low Observability

Published in IEEE PowerTech 2023, Belgrade, Serbia, 2023

This paper discusses operational flexibility in active distribution networks with low observability, introducing techniques to enhance reliability and reduce uncertainties in operation.

Recommended citation: Chrysostomou, D., Torres, J. R., & Cremer, J. L. (2023). 'Exploring Operational Flexibility of Active Distribution Networks with Low Observability.' IEEE PowerTech 2023, Belgrade, Serbia, 1-8.
Download Paper

Regularized Learning with Physical Equations for Uncertain Power System Dynamics

Published in IEEE PowerTech 2023, Belgrade, Serbia, 2023

This research introduces a regularized learning framework incorporating physical equations to address uncertain power system dynamics. The approach ensures robustness and improved predictive accuracy.

Recommended citation: Xie, H., Bellizio, F., & Cremer, J. L. (2023). 'Regularized Learning with Physical Equations for Uncertain Power System Dynamics.' IEEE PowerTech 2023, Belgrade, Serbia, 1-8.
Download Paper

Transient Stable Corrective Control Using Neural Lyapunov Learning

Published in IEEE Transactions on Power Systems, 2023

This study introduces a neural Lyapunov learning-based approach for transient stable corrective control in smart grids. The method ensures system stability under varying grid conditions.

Recommended citation: Bellizio, F., Cremer, J. L., & Strbac, G. (2022). 'Transient Stable Corrective Control in Smart Grids Using Neural Lyapunov Learning.' IEEE Transactions on Power Systems, 38, 3245-3253.
Download Paper

More than accuracy: end-to-end wind power forecasting that optimises the energy system

Published in Electric Power System Research, 2023

This study proposes an end-to-end wind power forecasting method that integrates energy system optimization. The framework ensures accurate predictions while aligning with system-wide operational goals.

Recommended citation: Wahdany, D., Schmitt, C., & Cremer, J. L. (2023). 'More than accuracy: end-to-end wind power forecasting that optimises the energy system.' Electric Power System Research, 221, 109384.
Download Paper

Machine learning and digital twins: monitoring and control for dynamic security in power systems

Published in Elsevier, 2023

Monitoring and Control of Electrical Power Systems using Machine Learning Techniques bridges the gap between advanced machine learning techniques and their application in the control and monitoring of electrical power systems, particularly relevant for heavily distributed energy systems and real-time application. The book reviews key applications of deep learning, spatio-temporal, and advanced signal processing methods for monitoring power quality. This reference introduces guiding principles for the monitoring and control of power quality disturbances arising from integration of power electronic devices and discusses monitoring and control of electrical power systems using benchmark test systems for the creation of bespoke advanced data analytic algorithms.

Recommended citation: Brosinsky, Christoph, Mert Karaçelebi, and Jochen L. Cremer. 'Machine learning and digital twins: monitoring and control for dynamic security in power systems.' In Monitoring and Control of Electrical Power Systems Using Machine Learning Techniques, pp. 79-106. Elsevier, 2023.
Download Paper

Dynamic Incremental Learning for real-time disturbance event classification

Published in International Journal of Electrical Power & Energy Systems, 2023

This paper presents an incremental learning approach for real-time recognition of electrical disturbance events. The proposed method adapts to new data while maintaining accuracy, ensuring robustness in evolving power systems.

Recommended citation: Veera Kumar, N., Cremer, J. L., & Popov, M. (2023). 'Dynamic Incremental Learning for real-time disturbance event classification.' International Journal of Electrical Power & Energy Systems, 148, 108988.
Download Paper

Generating Quality Datasets for Real-Time Security Assessment: Balancing Historically Relevant and Rare Feasible Operating Conditions

Published in International Journal of Electrical Power & Energy Systems, 2023

This work addresses the challenge of generating datasets for real-time security assessment in power systems, focusing on balancing historical relevance with rare feasible scenarios. The methodology improves the reliability of security assessments.

Recommended citation: Bugaje, A.-A., Cremer, J. L., & Strbac, G. (2023). 'Generating Quality Datasets for Real-Time Security Assessment: Balancing Historically Relevant and Rare Feasible Operating Conditions.' International Journal of Electrical Power & Energy Systems, 154, 109427.
Download Paper

Game-Theoretic Learning for Power System Dynamic Ancillary Service Provisions

Published in IEEE Control Systems Letters, 2024

This paper introduces a game-theoretic learning approach to coordinate aggregators in power systems for providing fast frequency response as dynamic ancillary services. The proposed method ensures efficient and adaptive provision of services, enhancing system stability.

Recommended citation: Xie, H., & Cremer, J. L. (2024). 'Game-Theoretic Learning for Power System Dynamic Ancillary Service Provisions.' IEEE Control Systems Letters, 8, 1307-1312.
Download Paper

Deep Statistical Solver for Distribution System State Estimation

Published in IEEE Transactions on Power Systems, 2024

This paper introduces a deep statistical solver for state estimation in distribution systems, combining machine learning techniques with statistical inference. The approach improves accuracy and computational efficiency in complex grid environments.

Recommended citation: Habib, B., Isufi, E., Breda, W. v., Jongepier, A., & Cremer, J. L. (2024). 'Deep Statistical Solver for Distribution System State Estimation.' IEEE Transactions on Power Systems, 39(2), 4039-4050.
Download Paper

Spatio-Temporal Data-Driven and Machine Learning-Based Applications for Transmission Systems

Published in IEEE PES General Meeting 2024, 2024

This paper reviews spatio-temporal machine learning applications for transmission systems, highlighting use cases in system stability and operational planning. It identifies trends and future research directions.

Recommended citation: Sevilla, F. R. S., Liu, Y., Barocio, E., Korba, P., & Cremer, J. L. (2024). 'Spatio-Temporal Data-Driven and Machine Learning-Based Applications for Transmission Systems.' IEEE PES General Meeting 2024.
Download Paper

Automatic Detection of Subsynchronous Oscillations

Published in CIGRE Annual Meeting 2024, 2024

This study proposes a machine learning framework for automatic detection of subsynchronous oscillations in power grids. The approach improves monitoring and enhances grid reliability.

Recommended citation: Neagu, A., Chakravorty, D., & Cremer, J. L. (2024). 'Automatic Detection of Subsynchronous Oscillations.' CIGRE Annual Meeting 2024, C4-11096-2024.
Download Paper

Tensor Convolution-Based Aggregated Flexibility Estimation in Active Distribution Systems

Published in IEEE Transactions on Smart Grid, 2024

This paper proposes a novel approach using tensor convolutions to estimate flexibility in distribution grids. The methodology enhances accuracy and scalability, enabling improved grid management and planning.

Recommended citation: Chrysostomou, D., Torres, J. R., & Cremer, J. L. (2024). 'Tensor Convolution-Based Aggregated Flexibility Estimation in Active Distribution Systems.' IEEE Transactions on Smart Grid.
Download Paper

Constraint-driven deep learning for N-k security constrained optimal power flow

Published in Electric Power System Research, 2024

This paper introduces a deep learning framework incorporating operational constraints for solving N-k security constrained optimal power flow problems. Results highlight enhanced computational efficiency and accuracy.

Recommended citation: Giraud, B., Rajaei, A., & Cremer, J. L. (2024). 'Constraint-Driven Deep Learning for N-k Security Constrained Optimal Power Flow.' Electric Power System Research, 235, 110692.
Download Paper

Few-Shot Transfer Learning for Battery Cycle Life

Published in IEEE ISGT Europe 2024, 2024

This study explores few-shot transfer learning for predicting battery cycle life. The method leverages limited data to provide accurate predictions, aiding in efficient battery management.

Recommended citation: Yu, R., Wang, J., Han, Y., O’Connor, T. S., & Cremer, J. L. (2024). 'Few-Shot Transfer Learning for Battery Cycle Life.' IEEE ISGT Europe 2024

Learning a reward function for user-preferred appliance scheduling

Published in Electric Power System Research, 2024

This study develops a machine learning-based approach to learn reward functions for optimal appliance scheduling, balancing user convenience and grid efficiency. The proposed framework enhances decision-making in smart home energy systems.

Recommended citation: Covic, N., Cremer, J. L., & Pandžić, H. (2024). 'Learning a reward function for user-preferred appliance scheduling.' Electric Power System Research, 235, 110667.
Download Paper

A Pioneering Roadmap for ML-Driven Algorithmic Advancements in Electrical Networks

Published in IEEE ISGT Europe 2024, 2024

This paper outlines a roadmap for advancing machine learning algorithms in electrical networks. It identifies challenges and proposes innovative solutions to drive the future of grid automation.

Recommended citation: Cremer, J. L., Kelly, A., Bessa, R. J., Subasic, M., & Papadopoulos, P. (2024). 'A Pioneering Roadmap for ML-Driven Algorithmic Advancements in Electrical Networks.' IEEE ISGT Europe 2024.
Download Paper

Non-stationarity in multiagent reinforcement learning in electricity market simulation

Published in Electric Power System Research, 2024

This paper explores the challenges of non-stationarity in multiagent reinforcement learning applications for electricity markets. It proposes novel techniques to adapt learning strategies dynamically, ensuring robust market operations.

Recommended citation: Renshaw-Whitman, C., Zobernig, V., Cremer, J. L., & de Vries, L. (2024). 'Non-stationarity in multiagent reinforcement learning in electricity market simulation.' Electric Power System Research, 235, 110712.
Download Paper

Polynomial Line Outage Distribution Factors for Estimating Expected Congestion and Security

Published in IEEE Transactions on Power Systems, 2024

This paper introduces polynomial line outage distribution factors to estimate expected congestion and security in power systems. The method improves operational planning and reliability analysis.

Recommended citation: Cremer, J. L. (2024). 'Polynomial Line Outage Distribution Factors for Estimating Expected Congestion and Security.' IEEE Transactions on Power Systems.
Download Paper

Real-Time Ground Fault Detection for Inverter-Based Microgrid Systems

Published in IEEE Transactions on Control Systems, 2024

This research addresses ground fault detection in inverter-based microgrids, introducing a real-time algorithm. The study demonstrates improved fault localization and system reliability.

Recommended citation: Dong, J., Xie, H., Liao, Y., Cremer, J. L., & Esfahani, P. M. (2024). 'Real-Time Ground Fault Detection for Inverter-Based Microgrid Systems.' IEEE Transactions on Control Systems.
Download Paper

The impact of the growing use of machine learning/artificial intelligence in the operation and control of power networks from an operational perspective

Published in CIGRE Technical Brochure 946, Working Group C2.42, 2024

This TB aims to assess the state-of-the-art AI/ML deployments in system operations, the desired capabilities for wider AI/ML deployment, and how system operators may take advantage of these technologies while understanding their impacts, limitations, and risks. It intends to bridge the gap between technological innovation and operational efficiency by highlighting practical applications and presenting possible journeys for deploying this technology.

Recommended citation: Mouadh Yagoubi, Sjoerd P.J. Kop, Jochen Cremer, Marija Ilic, Amarsagar Reddy Ramapuram, Ming Dong, Karin Rodrigues, Guangchao Geng, Milos Subasic, Adrian Kelly, Alberto Kopiler, Rohit Anand, Teerasak Arunthanakij, Victor Meza, Fabian Heymann, Wolf Berwouts, Jingyu Wang, Medha Subramanian, Panagiotis Papadopoulos, Koen Vandermot, Samuel Young, Rohit Trivedi, Spyros Chatzivasileiadis, Viktor Eriksson Möllerstedt, Arnaud Zinflou., 'The impact of the growing use of machine learning/artificial intelligence in the operation and control of power networks from an operational perspective', CIGRE TB 946, WG C2.42.
Download Paper

A Hybrid Curriculum Learning and Tree Search Approach for Network Topology Control

Published in Electric Power Systems Research, 2025

This paper presents a hybrid approach combining curriculum-trained reinforcement learning (RL) and Monte Carlo tree search (MCTS) for network topology control. The proposed method enhances training stability, improves sample efficiency, and mitigates unforeseen RL actions, offering a novel solution for grid congestion management.

Recommended citation: Meppelink, G. J., Rajaei, A., & Cremer, J. L. (2025). 'A Hybrid Curriculum Learning and Tree Search Approach for Network Topology Control.' Electric Power Systems Research, 242, 111455.
Download Paper

Deep Diffusion on Sky Images for Probabilistic Ultra-Short-Term PV Forecasting

Published in IEEE PES PowerTech 2025, Kiel, Germany, 2025

This paper presents a novel approach utilizing deep diffusion models on sky images to achieve probabilistic ultra-short-term photovoltaic (PV) forecasting. The method enhances the accuracy of PV power predictions by capturing the stochastic nature of cloud movements.

Recommended citation: Lopez Romero, O., Poland, J., & Cremer, J. L. (2025). 'Deep Diffusion on Sky Images for Probabilistic Ultra-Short-Term PV Forecasting.' Proceedings of IEEE PES PowerTech 2025, Kiel, Germany, 1–6.
Download Paper

Exploring the Extrapolation Performance of Machine Learning Models for Power System Time Domain Simulations

Published in Sustainable Energy, Grids and Networks (accepted), 2025

This paper investigates the extrapolation capabilities of machine learning models in power system time domain simulations. The study assesses model performance beyond trained scenarios to ensure reliability in unforeseen conditions.

Recommended citation: Arowolo, O., Stiasny, J., & Cremer, J. L. (2025). 'Exploring the Extrapolation Performance of Machine Learning Models for Power System Time Domain Simulations.' Sustainable Energy, Grids and Networks (accepted).
Download Paper

Exploring Market Designs for Enhanced Flexibility Procurement with Deep Reinforcement Learning

Published in The International Conference on European Energy Markets, Lisboa, Portugal, 2025

This paper investigates market design strategies for improved flexibility procurement in electricity markets using deep reinforcement learning. The study evaluates how different market mechanisms influence system adaptability and efficiency.

Recommended citation: Zobernig, V., Fanta, S., Strömer, S., Hemm, R., Cremer, J. L., & de Vries, L. J. (2025). 'Exploring Market Designs for Enhanced Flexibility Procurement with Deep Reinforcement Learning.' The International Conference on European Energy Markets, Lisboa, Portugal, 2025.
Download Paper

Predicting Power System Frequency with Neural Ordinary Differential Equations

Published in Sustainable Energy, Grids and Networks (accepted), 2025

This paper presents a novel application of Neural Ordinary Differential Equations (NODEs) to predict power system frequency dynamics. The approach offers a data-driven solution for real-time frequency monitoring and control.

Recommended citation: Karaçelebi, M., & Cremer, J. L. (2025). 'Predicting Power System Frequency with Neural Ordinary Differential Equations.' Sustainable Energy, Grids and Networks (accepted).
Download Paper

Exploratory Analysis on the Impact of Grid Tariffs in Transmission Expansion Planning

Published in IEEE PES PowerTech 2025, Kiel, Germany, 2025

This paper conducts an exploratory analysis of how grid tariffs influence transmission expansion planning. It evaluates regulatory and economic scenarios to understand the role of tariff schemes in infrastructure investment decisions.

Recommended citation: Hofstadler, L., Gavriluta, C., Stiasny, J., & Cremer, J. (2025). 'Exploratory Analysis on the Impact of Grid Tariffs in Transmission Expansion Planning.' Proceedings of IEEE PES PowerTech 2025, Kiel, Germany, 1–6.
Download Paper

Learning-Accelerated ADMM for Stochastic Power System Scheduling

Published in IEEE Transactions on Sustainable Energy, 2025

This paper introduces a learning-accelerated Alternating Direction Method of Multipliers (ADMM) approach for stochastic power system scheduling. The method enhances convergence speed and solution quality under uncertainty.

Recommended citation: Rajaei, A., Arowolo, O., & Cremer, J. L. (2025). 'Learning-Accelerated ADMM for Stochastic Power System Scheduling.' IEEE Transactions on Sustainable Energy.
Download Paper

Multi-Objective Reinforcement Learning for Power Grid Topology Control

Published in IEEE PES PowerTech 2025, Kiel, Germany, 2025

This paper presents a multi-objective reinforcement learning framework for power grid topology control. The method enables operators to optimize trade-offs between competing objectives such as security, cost, and congestion relief.

Recommended citation: Lautenbacher, T., Rajaei, A., Barbieri D., Viebahn, J., & Cremer, J. L. (2025). 'Multi-Objective Reinforcement Learning for Power Grid Topology Control.' Proceedings of IEEE PES PowerTech 2025, Kiel, Germany, 1–6.
Download Paper

Online Neural Dynamics Forecasting for Power System Security

Published in International Journal of Electrical Power & Energy Systems, Volume 167, 2025

This paper proposes a machine learning framework for online forecasting of neural dynamics in power systems. Trained on post-fault data, the model enables accurate and real-time stability assessments, enhancing operational security.

Recommended citation: Karaçelebi, M., & Cremer, J. L. (2025). 'Online Neural Dynamics Forecasting for Power System Security.' International Journal of Electrical Power & Energy Systems, 167, 110566.
Download Paper

Learning to Control a Battery Through Reinforcement: Balancing Lifetime and Profit

Published in IEEE PES PowerTech 2025, Kiel, Germany, 2025

This paper introduces a reinforcement learning framework to control battery operation while balancing degradation and profitability. The model learns optimal strategies under varying market and technical conditions.

Recommended citation: Santos Neves, C., Čović, N., & Cremer, J. (2025). 'Learning to Control a Battery Through Reinforcement: Balancing Lifetime and Profit.' Proceedings of IEEE PES PowerTech 2025, Kiel, Germany, 1–6.
Download Paper

talks

Data Analytic Tools for Security Assessment of Bulk Power Systems

Published:

During the IEEE Power & Energy Society General Meeting 2019, held from August 4–8 in Atlanta, USA, a panel session titled “Data Analytic Tools for Security Assessment of Bulk Power Systems” was conducted. This session explored the application of data analytics in assessing and enhancing the security of large-scale power systems, discussing tools and methodologies to improve grid resilience.

A Student Perspective on Climate Change

Published:

At the AAPG Energy Transition Forum 2019, held on October 10 in Edinburgh, UK, a keynote address titled “A Student Perspective on Climate Change” was delivered. This address provided insights into the concerns and expectations of the younger generation regarding climate change, emphasizing the role of education and innovation in driving the energy transition.

Machine Learning Based Operation of Dynamic Sustainable Energy Systems

Published:

At the IEEE Sustainable Power and Energy Conference (iSPEC) 2019, held from November 21–23 in Beijing, China, a panel session focused on innovations in sustainable power and energy. The session brought together experts to discuss advancements and challenges in the field, promoting sustainable practices in power generation and distribution.

Advanced Data Analytics in Power Systems

Published:

In December 2019, a presentation titled “Advanced Data Analytics in Power Systems” was delivered as part of the IEEE Big Data & Analytics Webinar series. This webinar focused on the application of big data techniques in the energy sector, discussing how data analytics can enhance the efficiency and reliability of power systems.

CIGRE C2.25 Operational Resilience

Published:

At the CIGRE Annual Meeting 2021, held online from August 18–23, a tutorial session was conducted around the Technical Brochure from CIGRE Working Group C2.25, titled “Operating Strategies and Preparedness for System Operational Resilience.” This tutorial provided detailed insights into strategies for enhancing the operational resilience of power systems.

AI: Real-Time Operations or Full Automation?

Published:

During the ISA Knowledge Days 2021, organized by Interconexión Eléctrica S.A. (ISA), the largest energy transmission company in Latin America, a keynote address titled “AI: Real-Time Operations or Full Automation?” was delivered.

AI Innovations in Energy Systems

Published:

At the World Summit AI 2021, held on October 13–14 in Amsterdam, Netherlands, a lightning talk titled “AI Innovations in Energy Systems” was presented. This short pitch provided insights into the latest advancements in artificial intelligence applications within energy systems, highlighting how AI can enhance efficiency, reliability, and sustainability in the energy sector.

On Dynamics and Artificial Intelligence for Power Systems

Published:

At the IEEE SGSMA 2022 conference, held from May 24–26 in Split, Croatia, a panel session titled “Synchrophasor and Monitoring Data Handling: A Perspective of Ongoing TSOs Approach” was conducted. This session focused on the methodologies employed by Transmission System Operators (TSOs) in handling synchrophasor and monitoring data to enhance grid stability and reliability.

AI Methods For Realtime Dynamic Security Assessment

Published:

During the IEEE SGSMA 2022 conference, a panel session titled “PMU- and AI-Based Analysis for a Resilient Operation of Future Power Systems” was held. This session delved into the utilization of Phasor Measurement Units (PMUs) and artificial intelligence to enhance the resilience and reliability of future power systems.

Learning to Run a Power Network with Trust

Published:

The IEEE PES General Meeting 2022 hosted a session titled “Enhancing Power System Operation Through Online Analytics,” which explored innovative applications of data analytics and AI in optimizing power system operations. The session emphasized real-time approaches to improve decision-making in grid management.

Multi-Agent Reinforcement Learning for Incentivized Flexibility from Residents

Published:

The IEEE PES General Meeting 2022 featured a session titled “Advanced Applications of Modern Optimization and Artificial Intelligence Methods on Active Distribution Networks.” This session focused on cutting-edge optimization techniques and AI applications in planning and managing active distribution systems.

Machine Learning for Security Assessments in Low Inertia Grids

Published:

At the IEEE Power & Energy Society General Meeting 2022, held from July 17–21 in Denver, Colorado, a supersession titled “Artificial Intelligence in Power Systems” was conducted. This session brought together leading experts from research, government, and industrial organizations to discuss past achievements and future directions of AI and machine learning applications in power systems.

AI for Distributed Energy Systems

Published:

The Intelligent Systems Conference (IntelliSys) 2022, held from September 1–2 in Amsterdam, Netherlands, brought together researchers and practitioners to discuss the latest advancements in intelligent systems.

AI and ML for Smart Grids

Published:

During the Smart Grid Tech Week in March 2023, a round table discussion titled “AI and ML for Smart Grids” was held, focusing on the integration of artificial intelligence and machine learning in the development and optimization of smart grid technologies.

Graph Neural Networks for Distribution State Estimation

Published:

At the IEEE PES PowerTech 2023 conference, held from June 25–29 in Belgrade, Serbia, a special session SS19 titled “Contemporary and Emergent Methods for Planning and Analysis of Distribution Networks” was conducted.

Young Professionals Panel Session on Future Power System Workforce

Published:

The IEEE PES PowerTech 2023 conference, held from June 25–29 in Belgrade, Serbia, included a Young Professionals Panel Session focusing on the future power system workforce. This session addressed the evolving skill sets required in the power and energy sector, considering technological advancements and industry trends.

Machine Learning to Prevent Blackouts in Power Systems

Published:

The IEEE Power & Energy Society General Meeting 2023, held from July 16–20 in Orlando, Florida, featured a panel session titled “Application of Big Data and AI/ML in Monitoring, Operations, Planning, and Protection.” This session focused on the utilization of data-driven machine learning and artificial intelligence for automated analysis of power system events and disturbances, aiming to enhance reliability and resilience in power system operations.

Graph Neural Networks for Distribution State Estimation

Published:

During the IEEE PES General Meeting 2023, a panel session titled “Machine Learning and Modern Heuristic Optimization for Planning and Operation of Active Distribution Networks” was conducted. This session delved into advanced machine learning techniques and heuristic optimization methods to enhance the planning and operation of active distribution networks.

Weakly Supervised Learning for Power Grid State Estimation

Published:

The 10th International Congress on Industrial and Applied Mathematics (ICIAM 2023) was held from August 20–25, 2023, at Waseda University in Tokyo, Japan. This congress brought together applied mathematicians, researchers, and practitioners from around the world to discuss advancements and applications in various fields of mathematics.

AI-based Monitoring for Sustainable Energy Systems

Published:

The Stichting Pipeliner Symposium ‘23, held on November 09, 2023, in Rotterdam, Netherlands, centered on advancements in pipeline technology and infrastructure. The symposium brought together industry experts to discuss innovative solutions for sustainable energy systems.

33rd Workshop on Computational Intelligence

Published:

The 33rd Workshop on Computational Intelligence, held from November 23–24, 2023, at HTW Berlin, focused on methods, applications, and tools for fuzzy systems, artificial neural networks, evolutionary algorithms, and data mining methods. The workshop emphasized comparing these methods based on industrial and benchmark problems.

Weakly-supervised Graph Neural Networks for Distribution System State Estimation

Published:

The 3rd Champéry Power Conference, held from February 4–9, 2024, was organized by the Institute of Sustainable Energy at the School of Engineering of Valais and the Automatic Control Laboratory of the Swiss Institute of Technology (ETH) in Zürich. The conference gathered international experts in the field of electric power systems to identify current and future challenges, as well as opportunities facing electric power systems in the context of the energy transition.

Constraint-Driven Deep Learning for N-k Security Constrained Optimal Power Flow

Published:

The EPSRC Supergen Energy Networks Hub Risk and Resilience Day is an annual seminar that continues the tradition of the previous Durham Risk Day series (2010-2014). It brings together researchers involved in all aspects of risk and uncertainty analysis applied to current and future power and energy systems.

Rise of AI: Opportunity or Threat?

Published:

The symposium “Rise of AI: Opportunity or Threat?” organized by Dutchpower, focused on the rapidly evolving landscape of artificial intelligence and its implications for society and industry. Discussions covered the opportunities presented by AI in innovation and efficiency, as well as potential risks related to ethics, security, and workforce displacement. My short workshop was on the role of AI to accelerate the energy transition from research perspective.

Webinar at IEEE PES Chapter Spain, Women in Power

Published:

This webinar, organized by the IEEE PES Spain Chapter’s Women in Power initiative, focused on artificial intelligence applications in energy systems. Researchers from CITCEA-UPC and TU Delft presented recent developments, including new computational methods for system operation and control that combine statistical machine learning and mathematical optimization.

Reinforcement Learning for Energy Community Management

Published:

The Workshop on Reinforcement Learning for Stochastic Networks (RL4SN), held from June 17–21, 2024, at ENSEEIHT in Toulouse, France, focused on the development of learning algorithms suitable for situations where data is scarce or computational power is limited, with a particular emphasis on stochastic networks.

Dynamic Modeling of Multi-Energy Systems

Published:

This panel focused on the dynamic modeling of multi-energy systems, discussing the integration and interaction of various energy carriers such as electricity, heat, and gas. Topics included modeling techniques, simulation tools, and the challenges in achieving coordinated control and optimization across different energy infrastructures.

AI for NetZero Webinar Series

Published:

The AI for NetZero webinar series, organized by the AI4NetZero research group, explores diverse applications of artificial intelligence across sectors crucial to achieving NetZero objectives, including energy, transport, environment, agriculture, and food systems.

Inverter-Based Power Systems Summer School

Published:

The “Inverter-Based Power Systems” summer school, held from September 2–6, 2024, at Imperial College London, provided a comprehensive overview of the challenges and emerging research directions in power systems dominated by inverter-based resources (IBRs).

IEEE PES & Power Africa Conference 2024

Published:

This tutorial “AI in power system reliability monitoring” was part of the IEEE PES & IAS PowerAfrica Conference, focusing on power and energy systems in Africa. The session covered the implementation of AI technologies in power system reliability monitoring, aiming to enhance the efficiency and resilience of energy infrastructure across the continent.

ML/AI Applications in Power Systems: Drivers and Barriers

Published:

This panel explored the key drivers enabling machine learning and AI applications in power systems, as well as the barriers hindering their adoption. Topics included challenges in data availability, computational requirements, regulatory concerns, and the future potential for smart grids.

Energietage 2024

Published:

Energietage is a prominent conference in Austria and focuses on energy policy, innovation, and technology.

Tutorial CIGRE C2.42 at AI-Day for Grid Operations

Published:

This event was organized alongside the Tutorial of CIGRE Working Group C2.42 “The impact of the growing use of AI/ML for power system operations from an operational perspective”. This full day event had additional presentations and discussions to foster connections in the power system community on this topic, connecting other initiaves likes projects, competitions, working groups. This day aimed to accelerate the much needed developments of AI/ML for future grid operations.

1-Day Course on AI in Power System Reliability Monitoring

Published:

This 1-day course, hosted by Tallinn University, focuses on the application of AI in monitoring the reliability of power systems. It is part of the Smart and Green Energy Systems and Business Models program, aiming to educate participants on the integration of AI technologies to enhance the efficiency and reliability of modern power grids.

All AI models are wrong, but some are useful… for power systems

Published:

Artificial intelligence (AI) holds great promise for the future of power system operation, yet widespread technological breakthroughs remain elusive. This talk addresses the question of why AI has not yet transformed power systems and explores the pathway to achieving this transformation. While modern AI systems benefit from vast data and immense computational resources, their application in power systems is constrained by physical laws, safety-critical decisions, and limited real-world data.

Seminar Liège: Deep Learning for Power System Reliability Assessments

Published:

Preparing power systems for large-scale implementation of inverter-based generators and renewables requires future reliability tools to anticipate uncertainties in the monitoring and control that mitigate energy supply disruptions. Deep Learning (DL) approaches first proposed to the power system domain in the 90s have seen the first successes in the industry including renewable or load forecasting.

Tutorial at DTU Summer School 2025

Published:

This talk at the DTU PES Summer School 2025 focuses on novel research topics and methods in deep learning applied to reliability assessment. It highlights applications of machine learning and optimization in energy systems, featuring insights from leading researchers and industry experts.

Tutorial at ACM e-Energy 2025

Published:

This tutorial on “Power System Reliability with Deep Learning” focuses on methods from deep learning applied to reliability assessment. Expanding grids with renewable energy challenges their reliability.

teaching

EEX01: Introduction to Machine Learning

Undergraduate course, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, 2024

EEX01 is an undergraduate elective course designed for 2nd (or 3rd) year BSc Electrical Engineering students at TU Delft. The course introduces the fundamentals of machine learning (ML) tailored for electrical engineering applications. Students will gain both theoretical knowledge and practical skills to design and implement ML algorithms using Python.

EE4C12: Machine Learning for Electrical Engineering

Graduate course, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, 2024

EE4C12 is a graduate-level course designed for MSc students in Electrical Engineering at TU Delft. This course provides a comprehensive introduction to machine learning concepts, with a focus on applications relevant to electrical and energy systems. Students will gain theoretical knowledge and hands-on experience, equipping them to apply machine learning techniques effectively in real-world problems.

SET3125: Machine Learning Workflows for Digital Energy Systems

Graduate course, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, 2024

SET3125 is a graduate-level course offered to MSc students at TU Delft, focusing on the fundamentals of machine learning and its applications in sustainable energy systems, with an emphasis on digital technologies. The course provides a foundation for further studies in digital energy technologies and machine learning, and prepares students for thesis work involving artificial intelligence.