Skip to content

AI for Intelligent Energy Systems Workshop is a three day workshop hosted by TU Delft DAI Lab. The workshop focuses on the applications of NLP/LLM, GNNS and RL in Energy Systems. The code labs in workshop have been provided for interested students and researchers.

Notifications You must be signed in to change notification settings

thomaslautenb/Workshop_AI_for_Intelligent_Energy_Systems

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Workshop AI for Intelligent Energy Systems

The AI for Intelligent Energy Systems Workshop is a 3-day workshop hosted by the Delft AI Energy Lab. The workshop explores the use of AI algorithms to solve emerging challenges in energy systems. Codes from the workshop have been provided for students and researchers. The workshop repository is organized as follows:

Large Language Models (LLMs) in Energy Markets

LLM_for_energy_market.ipynb

  • Interacting with OpenAI API
  • Introduction to Prompt Engineering
  • Using role-playing for LLMs
  • Training your own LLM with Llama and Stable Beluga2
  • Fine-tuning locally trained LLM to predict electricity price

Graph Neural Networks for Power Systems

GNN_for_power_systems

  • Introduction to graphs with pytorch_geometric and networkx
  • Solving common graph tasks with graph neural networks (GNN)
  • Solving Optimal Power Flow (DCOPF) problem with GNN

Deep Reinforcement Learning for Power Systems

DRL_for_power_systems

  • Q-learning for Taxi-driver environment
  • Deep Q networks for cart-pole environment
  • DDPG for mountain car environment
  • Training an intelligent battery storage system

For questions, please contact dai-energy-lab@tudelft.nl

License

This work is licensed under a License: MIT

About

AI for Intelligent Energy Systems Workshop is a three day workshop hosted by TU Delft DAI Lab. The workshop focuses on the applications of NLP/LLM, GNNS and RL in Energy Systems. The code labs in workshop have been provided for interested students and researchers.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%