Title :
Microcontroller based maximum power point tracking through FCC and MLP Neural Networks
Author :
Lozito, Gabriele Maria ; Bozzoli, Ludovica ; Salvini, Alessandro
Author_Institution :
Dipt. di Ing., Univ. degli Studi di “Roma Tre”, Rome, Italy
Abstract :
This paper covers the study towards the implementation of a Neural Network based approach for the efficiency control of Photovoltaic systems. The algorithm aims to track the maximum power point for the PV device whenever abrupt changes in climatic conditions occur. The core of the algorithm is a Neural Network (NN) trained by using a suitable mathematical model of the photovoltaic device. Different NN architectures and several optimization solutions were studied to investigate the best approach in terms of computational efficiency, memory footprint and prediction accuracy. The best found architecture has been implemented and tested on the microcontroller unit LM4F120H5QR by Texas Instruments by using a prototype board to drive the operating point of a low-power solar cell.
Keywords :
Texas Instruments computers; maximum power point trackers; microcontrollers; multilayer perceptrons; neurocontrollers; optimisation; photovoltaic power systems; solar cells; FCC; LM4F120H5QR; MLP neural network; NN architecture; PV device; Texas instruments; computational efficiency; efficiency control; fully connected cascade architecture; low-power solar cell; mathematical model; memory footprint; microcontroller based maximum power point tracking; multilayer perceptron; neural network based approach; optimization; photovoltaic device; photovoltaic system; prediction accuracy; prototype board; Artificial neural networks; Computer architecture; FCC; Microcontrollers; Neurons; Temperature measurement;
Conference_Titel :
Education and Research Conference (EDERC), 2014 6th European Embedded Design in
Conference_Location :
Milano
Print_ISBN :
978-1-4799-6841-1
DOI :
10.1109/EDERC.2014.6924389
