In-Depth Analysis of a Solar Panel Performance: Efficiency and Productivity Methods Examination Based on Numerical Model and Emotional Artificial Neural Network

Abstract This article presents an analysis and evaluation of the performance of a standard 200 W solar cell, with a particular emphasis on the energy and exergy aspects of the cell. A numerical model and a novel machine-learning model (Emotional Artificial Neural Network) were employed to simulate and ascertain the electrical characteristics of the system, encompassing the open-circuit voltage, short-circuit current, system resistances, maximum power point characteristics, and characteristic curves. A novel approach has yielded mathematical equations capable of calculating efficiency levels. The system's operational and electrical parameters, along with environmental conditions such as solar radiation, wind speed, and ambient temperature, were empirically observed and documented during a day. A comparative analysis was conducted to validate the model by comparing its results with the data provided by the manufacturer and the data gathered through experimental means. During the duration of the trial, spanning from 7:00 to 17:00, the results indicate that the energy efficiency rate exhibited variations within a range of 10.34 to 14.00 percent. The average energy efficiency assessed throughout this time period was found to be 13.6 percent. During the duration of the experiment, the degree of exergy efficiency exhibited variability, ranging from 13.57 to 16.41 percent, with an average value of 15.70 percent. Furthermore, the results of the EANN model indicate that the suggested method to forecasting energy, exergy, and power is feasible for simulating problems at a reduced computational expense compared to the numerical model.