Thermo-electro-environmental analysis of a photovoltaic solar panel using machine learning and real-time data for smart and sustainable energy generation

• Published in: Journal of cleaner production 2022-06, Vol.353, p.131611, Article 131611
• Main Authors: Sohani, Ali, Sayyaadi, Hoseyn, Miremadi, Seyed Rahman, Samiezadeh, Saman, Doranehgard, Mohammad Hossein
• Format: Article
• Language: English
• Subjects: Artificial neural network; CO2 emission reduction; Renewable energy technologies; Sustainable energy generation; Thermo-electro-environmental analysis
• ISSN: 0959-6526; 1879-1786
• DOI: 10.1016/j.jclepro.2022.131611

The impact of meteorological parameters, including ambient temperature, wind velocity, ambient relative humidity, and solar radiation on photocurrent and thermal voltage of diode, as two main thermo-electrical parameters of a solar panel, is found. For this purpose, the experimental data obtained during a year, in addition to the post-processed images captured by an infrared thermal imaging camera, are used, and models for performance prediction by the artificial neural network are developed and validated. In addition, the impact of photocurrent and thermal voltage of diode on CO2 saving of the system is found. According to the results, for the investigated 320W polycrystalline panel, with 200.0% increase in the range of 500–1500 W m−2, solar radiation has the strongest impact on photocurrent. Moreover, the most effective meteorological parameter on the thermal voltage of diode is ambient temperature. Changing ambient temperature from 27 to 47 °C is accompanied by 9.36% growth in that parameter. The conducted sensitivity analysis also reveals that between photocurrent and thermal voltage of diode, the former is a more effective parameter on CO2 emission reduction of the system. When photocurrent values are 20% lower and 20% higher than the base case, the amounts of CO2 saving are 18.0% smaller and 14.6% greater, respectively. It means 32.6% variation within the range.