Article: A multivariate regression model of solar photovoltaic and its validation through ANN Journal: International Journal of Power and Energy Conversion (IJPEC) 2023 Vol.14 No.4 pp.359 - 375 Abstract: The rapid integration of solar photovoltaic (PV) systems into the global energy landscape necessitates the development of accurate predictive models for PV system performance. A solar photovoltaic (PV) system is modelled either by its equivalent single-diode, double-diode or multiple-diode model. The model equations of these models need to be solved through iterative process which sometimes may not suitable for analysis. One cannot analyse a system using modal analysis, state-space analysis, linearisation, etc., when an iterative process is involved. Therefore, this paper suggests a multivariate regression based novel function of solar PV which replicates the actual PV system model. The model incorporates key factors such as solar irradiance, temperature, and system configuration to provide a comprehensive understanding of PV system behaviour. The proposed regressed model of the solar PV has been tested under various operating conditions and realistic solar data. To validate the accuracy and robustness of our multivariate regression model function, a feedforward back-propagation neural network has been used considering the data generated by the proposed regression model. It was also observed that the proposed model is good enough for the mathematical analysis of the PV integrated systems. Inderscience Publishers - linking academia, business and industry through research

You can view the full text of this article for free using the link below.

Title: A multivariate regression model of solar photovoltaic and its validation through ANN

Authors: Ganesh P. Prajapat; Surender Singh Tanwar; Rahul Kumar Dubey

Addresses: Engineering College Bikaner, Bikaner Technical University, Bikaner, Rajasthan, 334004, India ' Engineering College Bikaner, Bikaner Technical University, Bikaner, Rajasthan, 334004, India ' Bosch Global Software Technologies, Bengaluru, 560095, India

Abstract: The rapid integration of solar photovoltaic (PV) systems into the global energy landscape necessitates the development of accurate predictive models for PV system performance. A solar photovoltaic (PV) system is modelled either by its equivalent single-diode, double-diode or multiple-diode model. The model equations of these models need to be solved through iterative process which sometimes may not suitable for analysis. One cannot analyse a system using modal analysis, state-space analysis, linearisation, etc., when an iterative process is involved. Therefore, this paper suggests a multivariate regression based novel function of solar PV which replicates the actual PV system model. The model incorporates key factors such as solar irradiance, temperature, and system configuration to provide a comprehensive understanding of PV system behaviour. The proposed regressed model of the solar PV has been tested under various operating conditions and realistic solar data. To validate the accuracy and robustness of our multivariate regression model function, a feedforward back-propagation neural network has been used considering the data generated by the proposed regression model. It was also observed that the proposed model is good enough for the mathematical analysis of the PV integrated systems.

Keywords: feedforward neural network; maximum power point tracking control; MPPTC; multivariate regression; solar PV system.

DOI: 10.1504/IJPEC.2023.135477

International Journal of Power and Energy Conversion, 2023 Vol.14 No.4, pp.359 - 375

Received: 24 Mar 2023
Accepted: 13 Sep 2023
Published online: 14 Dec 2023 *

Full-text access for editors Full-text access for subscribers Free access Comment on this article

Title: A multivariate regression model of solar photovoltaic and its validation through ANN

Keep up-to-date