Login / Signup

Hardware-in-the-loop Testing of a Deep Deterministic Policy Gradient Algorithm as a Microgrid Secondary Controller.

Pedro I. N. BarbalhoDenis Vinicius CouryVinícius Albernaz LacerdaRicardo A. S. Fernandes
Published in: ISGT EUROPE (2023)
Keyphrases
  • neural network
  • learning algorithm
  • cost function
  • dynamic programming
  • policy gradient
  • objective function
  • optimal solution
  • search space
  • control system
  • worst case
  • approximation methods
  • gradient ascent