Improved Artificial Neural Network Method for Predicting Temperature of Solar Panel Output Performance

• Main Authors: Susanti, Mia Dwi, Suyanto, Musyafa, Ali, Stendafity, Selfi, Shoffiana, Nur Alfiani, Dian Hartati, Ayu, Damayanti, Ayu Anisa, Kartika Pertiwi, Nabilah
• Format: Conference Proceeding
• Language: English
• Subjects: ANN; Artificial neural networks; Data models; Predictive models; Solar energy; solar panel; Solar panels; temperature; Temperature distribution; Temperature measurement
• ISSN: 2832-8353
• DOI: 10.1109/ICAMIMIA60881.2023.10427613

Solar energy in Indonesia has great potential for advancing solar panel technology as an electrical energy source. Photovoltaic (solar panel) technology is known as a technology that utilizes solar energy and then converts it into electrical energy. There is a wide array of strategies available to articulate PV models. Artificial Intelligence (AI) is one of the diagnosis methods used to model, control, forecast, diagnosis and classification detection and prediction. The application of artificial neural networks (ANNs) to renewable power systems has been developed many times before. Previous research has conducted studies on how to optimally size photovoltaic power systems and optimize installation costs. However, solar cell models have been developed to analyze the power characteristics of PV (photovoltaic) cell elements. Renewable power systems has been developed many times before. In this simulation of solar panel temperature prediction, measurements were taken including measurements of solar panel temperature, ambient temperature and irradiation as primary data. The training phase reveals a compelling regression plot, demonstrating an impressive R value of 0.8231. The minuscule error rate in the prediction system unequivocally affirms the exceptional quality of this ANN model.