Developing Machine Learning-Based Intelligent Control System for Performance Optimization of Solar PV-Powered Refrigerators

Mohamed A. Eltawil, Maged Mohammed () and Nayef M. Alqahtani
Additional contact information
Mohamed A. Eltawil: Department of Agricultural Systems Engineering, College of Agricultural and Food Sciences, King Faisal University, Al-Ahsa 31982, Saudi Arabia
Maged Mohammed: Date Palm Research Center of Excellence, King Faisal University, Al-Ahsa 31982, Saudi Arabia
Nayef M. Alqahtani: Department of Agricultural Systems Engineering, College of Agricultural and Food Sciences, King Faisal University, Al-Ahsa 31982, Saudi Arabia

Sustainability, 2023, vol. 15, issue 8, 1-35

Abstract: Display refrigerators consume significantly high energy, and improving their efficiency is essential to minimize energy consumption and greenhouse gas emissions. Therefore, providing the refrigeration system with a reliable and energy-efficient mechanism is a real challenge. This study aims to design and evaluate an intelligent control system (ICS) using artificial neural networks (ANN) for the performance optimization of solar-powered display refrigerators (SPDRs). The SPDR was operated using the traditional control system at a fixed frequency of 60 Hz and then operated based on variable frequencies ranging from 40 to 60 Hz using the designed ANN-based ICS combined with a variable speed drive. A stand-alone PV system provided the refrigerator with the required energy at the two control options. For the performance evaluation, the operating conditions of the SPDR after the modification of its control system were compared with its performance with a traditional control system (TCS) at target refrigeration temperatures of 1, 3, and 5 °C and ambient temperatures of 23, 29, and 35 °C. Based on the controlled variable frequency speed by the modified control system (MCS), the power, energy consumption, and coefficient of performance (COP) of the SPDR are improved. The results show that both refrigeration control mechanisms maintain the same cooling temperature, but the traditional refrigerator significantly consumes more energy ( p < 0.05). At the same target cooling temperature, increasing the ambient temperature decreased the COP for the SPDR with both the TCS and MCS. The average daily COP of the SPDR varied from 2.8 to 3.83 and from 1.91 to 2.82 for the SPDR with the TCS and MCS, respectively. The comparison results of the two refrigerators’ conditions indicated that the developed ICS for the SPDR saved about 35.5% of the energy at the 5 °C target cooling temperature and worked with smoother power when the ambient temperature was high. The COP of the SPDR with the MCS was higher than the TCS by 26.37%, 26.59%, and 24.22% at the average daily ambient temperature of 23 °C, 29 °C, and 35 °C, respectively. The developed ANN-based control system optimized the SPDR and proved to be a suitable tool for the refrigeration industry.

Keywords: AI; artificial neural networks (ANN); coefficient of performance (COP); control; energy; machine learning (ML); photovoltaic (PV); optimization; variable speed drive (VSD) (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/8/6911/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/8/6911/ (text/html)

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:gam:jsusta:v:15:y:2023:i:8:p:6911-:d:1127776

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().