Delft AI Energy Lab

AI for sustainable, reliable and effective energy systems

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.

The Delft AI Energy Lab is part of the TU Delft AI Labs programme.

The team



Ali Rajaei

PhD candidate

Mohammad Boveiri

PhD candidate



  1. EE4720 Machine Learning for Energy System Applications, 4 ECTS, EEMCS, Electrical Engineering MSc program
  2. MOOC Digitalisation of Intelligent and Integrated Energy Systems
  3. SC42150 Statistical Signal Processing, 3 ECTS, 3ME, Systems & Control MSc program
  4. SC42110 Dynamic Programming & Stochastic Control, 5 ECTS, 3ME, Systems & Control MSc program


Master projects


  1. Neural Ordinary Differential Equations for Power System Dynamics
  2. From disease spreading to energy transition: AI in agent-based models
  3. Deep Reinforcement Learning for Coordinating Energy communities
  4. Machine Learning for Secure Operation of Power Systems
  5. AI to Predict Sustainable Energy Flexibility for TSO-DSO Coordination

See also DAI Energy lab MSc Cataloge.pdf


Applied AI projects

  1. Machine Learning Applications for ex-ante LCA, Niklas Engberg, TU Delft, Leiden University
  2. End-to-End Learning for Sustainable Energy Systems with PV and Wind, Rushil Vohra, TU Delft
  3. Meter Placement for Estimating Power System States, Sattama Datta, TU Delft thesis together with Alliander, DSO Netherlands
  4. Graph Neural Networks for State Estimation, Benjamin Habib, TU Delft thesis together with Stedin, DSO Netherlands
  5. Prediction of malfunctioning of PV panels with Machine Learning, Dion de Mooy, TU Delft

Fundamental AI projects

  1. Non-intrusive load monitoring for residential houses
  2. Scalable dictionary learning to learn high-level features
  3. Multivariable Anomaly Detection Framework for Multi-sensor Network
  4. Fault Detection and Isolation of Nonlinear Systems with Optimized Model Mismatch
  5. Robustness in Fault Diagnosis applied in the Lateral Control of Automated Vehicles
  6. Transferring Domain Knowledge to Data-driven Controller


  1. End-to-End Learning for Sustainable Energy Scheduling, Dariush Wahdany, TU Delft, RWTH Aachen University
  2. Multi-Agent Reinforcement Learning for Incentive-based Residential Demand Response, Jasper van Tilburg, TU Delft
  3. On the Road from Active Inference to Regret Minimization, TU Delft, 2021
  4. Conjugate Dynamic Programming, TU Delft, 2021
  5. Tractable Algorithms for Large Scale Mixed Integer Quadratic Programming: A Principal Component Analysis Approach, TU Delft, 2021
  6. Learning Parametric Mixed Integer Quadratic Programming via Inverse Optimization, TU Delft, 2021
  7. On Complexity of Data-driven Controls in Stochastic Environments, TU Delft, 2021
/* */