Maximum power point tracking based on self-adaptive neural network combined with incremental conductance

ABSTRACT

This article proposes a hybrid method that combines the self-adaptive neural network (SANN) and incremental conductance (IC) algorithm for maximum power point tracking (MPPT) in a photovoltaic (PV) system. The main objective of the proposed algorithm is to extract the maximum power of solar panels quickly and faster than the recent artificial neural network (ANN)-IC MPPT algorithm. Compared to the previous ANN-IC algorithm, a minimum number of data sets were used to obtain the GMP without compromising accuracy. Furthermore, comparison demonstrates that the suggested SANN-IC provides high efficiency, reliability, rapid tracking, and less response time tracking of GMP than w.r.t. all state-of-the-art techniques and ANN-IC method. The simulation is done with the help of MATLAB/SIMULINK. This is the first article about the performance of the hybrid MPPT technique tested by a sun simulator. The benefit of this hybrid method is that it reduces the search space of ANN, and hence, convergence speed is significantly increased. Training time and computing power are optimized by altering the number of epochs and requiring less memory. The experimental result showed the best convergence time and less oscillation than the ANN-IC method. Hence, the overall performance of SANN-IC in a steady-state condition with a partial shading condition meets the motive of the work.

KEYWORDS:

• Hybrid MPPT
• partial shading
• photovoltaic system
• self-Adaptive neural network
• global maximum power point

Acknowledgment

The authors would like to thank Mr. K. Arun, Director, USL Photovoltaics Pvt. Ltd., Coimbatore for their support of the experimental setup.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Karthikeyan Balachandran

Karthikeyan Balachandran received his Diploma in Electrical Electronics Engineering in 2003 from Tamilnadu Technical Education and Training, India. He worked as Research Assistant in USL photovoltaic Pvt. Ltd., India between 2003 to 2005. He received B.E in Electrical Electronics Engineering and M.E degree in Power Electronics and Drives from Anna University, India in 2009 and 2011, respectively. He worked as an Assistant Professor in the Department of Electrical and Electronics Engineering at Sethu Institute of Technology, India from 2011 to 2019. Currently, he is pursuing a full-time Ph.D. Degree in Electrical Engineering with PSNA College of Engineering and Technology, India. He is working on Solar PV, DC-DC converters, and Electric vehicles and Machine Learning.

Karthigaivel Ramasamy

Karthigaivel Ramasamy received his Bachelor of Engineering degree from Madurai Kamaraj University, India in 2001, and he received the Master of Technology Degree in Power system and Doctor of Philosophy in Electrical Engineering from the National Institute of Technology, Tiruchirappalli in 2005 and 2012, respectively. He currently works as a professor in the Department of Electrical and Electronics Engineering at PSNA College of Engineering and Technology, Dindigul, India. His field of interest is the design of power electronics controllers for Renewable Energy Sources, power system operation control, Electrical Vehicle and Machine Learning.