To track accurately and fast the Maximum Power Point (MPP), a hybrid technique NN-P&O switched between Neural Network (NN) and Perturb and Observe method (P&O) according to the variation of irradiation was proposed. The considered methodology is based on voltage reference estimated by NN and achieved using proportional-integral controller (PI). The error between the actual power and the optimal power was minimized using a small duty cycle steps generated by P&O method, which initial duty cycle value was updated adaptively. To approve the efficiency of the proposed control algorithms, simulations have been performed considering different system responses as the current, voltage and essentially the power under changing weather conditions (irradiance or temperature values).

Hybrid MPPT method based on Neural Network and Perturb & Observe for PV systems

Ogliari, Emanuele;
2022-01-01

Abstract

To track accurately and fast the Maximum Power Point (MPP), a hybrid technique NN-P&O switched between Neural Network (NN) and Perturb and Observe method (P&O) according to the variation of irradiation was proposed. The considered methodology is based on voltage reference estimated by NN and achieved using proportional-integral controller (PI). The error between the actual power and the optimal power was minimized using a small duty cycle steps generated by P&O method, which initial duty cycle value was updated adaptively. To approve the efficiency of the proposed control algorithms, simulations have been performed considering different system responses as the current, voltage and essentially the power under changing weather conditions (irradiance or temperature values).
2022
proceedings of 2022 19th International Multi-Conference on Systems, Signals & Devices (SSD)
978-1-6654-7108-4
File in questo prodotto:
File Dimensione Formato  
Hybrid_MPPT_method_based_on_Neural_Network_and_Perturb_amp_Observe_for_PV_systems.pdf

Accesso riservato

: Publisher’s version
Dimensione 891.98 kB
Formato Adobe PDF
891.98 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1224955
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact