journal article · 2022

Deep Reinforcement Learning-Based Approach for Autonomous Power Flow Control Using Only Topology Changes

Ivana Damjanovic , Ivica Pavic , Mate Puljiz , Mario Brcic

Energies, Volume 15, Issue 19, 6920

DOI: 10.3390/en15196920

Notes

Trains a deep reinforcement-learning agent that controls power flows in an electrical grid using only topology switching actions, without adjusting generation. Demonstrates that learned policies can match or exceed expert heuristics on the L2RPN benchmark.

How to cite

@article{brcic2022damjanovic,
  author = {Ivana Damjanovic and Ivica Pavic and Mate Puljiz and Mario Brcic},
  title = {Deep Reinforcement Learning-Based Approach for Autonomous Power Flow Control Using Only Topology Changes},
  journal = {Energies, Volume 15, Issue 19, 6920},
  year = {2022},
  doi = {10.3390/en15196920},
  url = {https://doi.org/10.3390/en15196920},
}

Topics:

decision intelligence