Search

Motivated by the growing significance of solar energy, the paper presents the findings of the maiden study on the long-term seasonal performance assessment of three PV module technologies—monocrystalline (m-Si), polycrystalline (p-Si), and amorphous silicon (a-Si) housed in a 1 MW solar plant installed at a local steppe climate in Gandhinagar, Gujarat, India using the key performance indicators (KPIs), daily power generation, final yield (Y f), reference yield (Y r), total energy loss (T EL) and performance ratio (PR). Notably, the am-Si PV modules were found to be the best performing technology, with an average PR of 71.26% and the lowest average total energy loss of 631 h during the monitored period. Moreover, PV systems have become more popular as a source of green, clean energy; yet, they have low base-load energy sustainability. Explainable AI (XAI) aids in understanding predictions made by the machine learning models. The importance of XAI lies in the comprehension and trust which is embedded into the results of machine learning algorithms. Therefore, the present work builds a comprehensive XAI model for predicting KPIs and assesses the performance of several learning algorithms using R-value, MAE, the number of iterations, and execution time. The Levenberg-Marquardt algorithm predicts the KPIs for p-Si, am-Si, and m-Si with prediction accuracies of 98.63%, 98.58%, and 90.09%, respectively. In summary, this study not only advances our understanding of PV module performance in a steppe climate context but also contributes to the broader field by integrating an XAI model for transparent and reliable predictions of the KPIs. [Display omitted] • Comparison of m-Si, p-Si, and a-Si PV modules in a 1 MW solar plant, Gandhinagar, India, showed long-term performance. • a-Si PV modules outperformed with a 71.26% PR and the lowest 631 hours energy loss, surpassing m-Si and p-Si technologies. • Study underscores XAI's role in ML predictions, developing a robust model to predict KPIs and evaluate learning algorithms. • Levenberg-Marquardt showed high accuracy: 98.63% for p-Si, 98.58% for a-Si, and 90.09% for m-Si PV modules. [ABSTRACT FROM AUTHOR]

This study provides experimental validation of a previously published optimal design theory for photovoltaic (PV)-powered electrodialysis reversal (EDR) desalination systems. The prior work describes the co-optimization of PV and EDR subsystems, and flexible operation to accommodate daily and annual solar irradiance variability, significantly reducing water cost. This study presents the fabrication of a PV-EDR pilot system designed using the co-optimization theory and field testing results from the rural village of Chelluru, India. Testing in the field enabled observation and evaluation of real-world factors on system performance, resulting in updates to the previous theory to include unaccounted factors that affect costs, including: filling and draining of water tanks, salt and water accumulation in tanks from prior batches, unexpected energy losses due to locally purchased converters, and scaling in the ED stack. Therefore, water cost in the PV-EDR pilot system was updated from previous estimates based on field performance. The estimated capital cost and lifetime cost of the Chelluru system are 34% and 45% lower, respectively, than the corresponding costs if the PV-EDR system was designed using conventional design practice. The theory and experimental insights presented in this paper will enable desalination engineers to better design and optimize PV-EDR systems. • This study validated previous published optimal design theory of PV-EDR systems. • A pilot-scale co-optimized PV-EDR system was built and tested in rural India. • Testing in the field enabled accounting real-world factors in future PV-EDR design. • 34% and 45% reductions of LCOW and capital cost are achieved by the pilot system. [ABSTRACT FROM AUTHOR]