Volume 6 Issue 4 November - January 2019
Research Paper
Maximum Power Point Tracking in Solar PV systems using Artificial Neural Networks
Jyotsana Pandey*
* Department of Electrical Engineering, Raipur Institute of Technology, Raipur, Chhattisgarh, India.
Pandey, J. (2019). Maximum Power Point Tracking in Solar PV systems using Artificial Neural Networks i-manager’s Journal on Power Systems Engineering, 6(4), 45-52. https://doi.org/10.26634/jps.6.4.16409
Abstract
Maximum power point tracking (MPPT) is critical in the design and use of solar PV cells. However, attaining MPPT is often challenging due to the random fluctuations in solar irradiation. Off late Artificial Neural Networks (ANN) are being used for maximum power point tracking of solar PV cells. In the proposed work, the Levenberg-Marqardt (LM) algorithm has been used to train a neural network with training features. Subsequently, the neural network is tested and an accuracy of 98.84% has been achieved. The high accuracy can be attributed to the structuring of the training data and the effectiveness of the Levenberg Marqardt back-propagation algorithm which is both fast and stable. The performance of the system has been evaluated in terms of the number of epochs for training, the mean absolute percentage error, accuracy and regression.