Assessment of Deep Reinforcement Learning Algorithms for Three-Phase Inverter Control

Oswaldo Menéndez, Diana López-Caiza, Luca Tarisciotti, Felipe Ruiz, Fernando Auat-Cheein, José Rodríguez

Producción científica: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

Resumen

Deep reinforcement learning (DRL) offers outstanding algorithms to develop optimal controllers for power converters with uncertainties and non-linear dynamics. This work comprehensively analyses a model-free control algorithm for three-phase inverters using DRL agents. To this end, different deep deterministic policy gradient (DDPG) agents with variable hyperparameters were conceptualized, designed, and tested. On average, DDPG agents were shown to have excellent performance in the control of power inverters. Indeed, DDPG agents reduce the impact of model uncertainties and non-linear dynamics. To validate the proposed control policy, the two-level voltage source power inverter is simulated. Also, the main features of the control strategy are analyzed in terms of computational cost, root medium square error (RMSE), and total harmonic distortion (THD). Simulated results reveal that the proposed control strategy exhibits strong performance in the current control task, achieving a maximum RMSE of 0.78 A and a THD of 3.17% for a 6 kHz sampling frequency.

Idioma originalInglés
Título de la publicación alojadaCOBEP 2023 - 17th Brazilian Power Electronics Conference and SPEC 2023 - 8th IEEE Southern Power Electronics Conference, Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9798350321128
DOI
EstadoPublicada - 2023
Evento8th Southern Power Electronics Conference and the 17th Brazilian Power Electronics Conference, SPEC / COBEP 2023 - Florianopolis, Brasil
Duración: 26 nov. 202329 nov. 2023

Serie de la publicación

NombreCOBEP 2023 - 17th Brazilian Power Electronics Conference and SPEC 2023 - 8th IEEE Southern Power Electronics Conference, Proceedings

Conferencia

Conferencia8th Southern Power Electronics Conference and the 17th Brazilian Power Electronics Conference, SPEC / COBEP 2023
País/TerritorioBrasil
CiudadFlorianopolis
Período26/11/2329/11/23

Áreas temáticas de ASJC Scopus

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

Huella

Profundice en los temas de investigación de 'Assessment of Deep Reinforcement Learning Algorithms for Three-Phase Inverter Control'. En conjunto forman una huella única.

Citar esto