Maximum power point tracking for grid tied solar fed DTC controlled IM drive using artificial neural network with energy management

S. Senthamizh Selvan

International Journal of Environmental Technology and Management, 2024, vol. 27, issue 1/2, 151-172

Abstract: In the mechanised world, carbon-less emission of energy production is vitalised. Despite varied renewable energy sources available, solar PV seems to be an optimum choice due to its ease of installation and maintenance. Though conventional algorithm exists for extracting maximum power, non-conventional algorithm by soft computing is foreseen for high stability during a sudden change in irradiation and load transients. In this article, artificial neural network-based maximum power point tracking is focused. A comparative analysis is carried out between single layer neural network and multi-layer neural network for varied parameters. The multi-layer neural network is found to be advantageous in the case of neuron's requirement, implementation complexity and testing MSE. Hence, the trained neural model is implemented in PV-grid fed DTC-IM drive system with various operating conditions. Simulation results are found to satisfactory. Added energy management condition is also validated for various irradiations.

Keywords: artificial neural network; ANN; single layer feed forward; multi-layer feed forward neural network; maximum power point tracking. (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=135556 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijetma:v:27:y:2024:i:1/2:p:151-172

Access Statistics for this article

More articles in International Journal of Environmental Technology and Management from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().