Banca de DEFESA: BRUNO RODOLFO DE OLIVEIRA FLORIANO

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : BRUNO RODOLFO DE OLIVEIRA FLORIANO
DATE: 15/12/2023
TIME: 14:00
LOCAL: Videoconferência
TITLE:

Neural-network-based model predictive control for consensus of nonlinear systems

KEY WORDS:

Consensus control. Neural networks. Model predictive control. Multi-agent systems.

PAGES: 59
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUBÁREA: Medidas Elétricas, Magnéticas e Eletrônicas; Instrumentação
SPECIALTY: Sistemas Eletrônicos de Medida e de Controle
SUMMARY:

This work addresses, through a model predictive control (MPC) approach, the consensus problem for discrete-time nonlinear multi-agent systems subjected to switching communication topologies. For systems following a random switching law, there is not any MPC solution that results in a reliable optimization in real-time. We propose a new neural-network-based algorithm that reduces the effects of communication deficiencies, caused by Markovian switching, by approximating and minimizing, in real-time, the MPC’s cost function. The convenience of the proposed method is certified in simulations for different applications and scenarios. Finally, the future steps of the current research are detailed.

COMMITTEE MEMBERS:
Externo à Instituição - ATILA MADUREIRA BUENO - USP
Interno - 1958922 - EDUARDO STOCKLER TOGNETTI
Presidente - 1721810 - HENRIQUE CEZAR FERREIRA
Interno - 1766513 - JOSE ALFREDO RUIZ VARGAS
Externo à Instituição - MARCO HENRIQUE TERRA - USP