Reinforcement Learning Based Weighting Factor Design of Model Predictive Control for Power Electronic Converters

Yihao Wan, Tomislav Dragicevic, Nenad Mijatovic, Chang Li, Jose Rodriguez

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

Weighting factor design is one of the challenges for finite-set model predictive control (FS-MPC) controlled power electronic converters, which plays an important role in the balance of control objectives in the cost function to achieve desired performance. This paper investigates the application of reinforcement learning algorithm for the weighting factor design for FS-MPC regulated voltage source converter in uninterrupted power supply (UPS) system. The deep deterministic policy gradient (DDPG) agent is employed to learn the optimal weighting factor design policy. The reinforcement learning (RL) agent is trained in the system and the weighting factor is optimized based on reward calculation with the interactions between the agent and environment. The key performance metric, total harmonic distortion (THD), is incorporated in the reward function. Effectiveness of the proposed reinforcement learning based weighting factor design method is validated by simulations.

Idioma originalInglés
Título de la publicación alojada6th IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics, PRECEDE 2021
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas738-743
Número de páginas6
ISBN (versión digital)9781665425575
DOI
EstadoPublicada - 2021
Evento6th IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics, PRECEDE 2021 - Jinan, China
Duración: 20 nov. 202122 nov. 2021

Serie de la publicación

Nombre6th IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics, PRECEDE 2021

Conferencia

Conferencia6th IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics, PRECEDE 2021
País/TerritorioChina
CiudadJinan
Período20/11/2122/11/21

Áreas temáticas de ASJC Scopus

  • Ingeniería eléctrica y electrónica
  • Ingeniería mecánica
  • Control y optimización
  • Ingeniería energética y tecnologías de la energía
  • Ingeniería de control y sistemas

Huella

Profundice en los temas de investigación de 'Reinforcement Learning Based Weighting Factor Design of Model Predictive Control for Power Electronic Converters'. En conjunto forman una huella única.

Citar esto