Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Preprint-Experimental and deep learning artificial neural network approach for evaluating grid‐connected photovoltaic systems
This article evaluates a 1.4 kW building integrated grid-connected photovoltaic plant. The PV plant installed in Faculty of Engineering solar energy lab, Sohar University, Oman and the system data has collected for a year from July 2017 to June 2018. The grid-connected system was evaluated in term of power, energy, specific yield, capacity factor, and cost of energy, and payback period. The measured diffuse and global solar irradiations are 3289 Wh/m2 and 6182 Wh/m2, respectively. Four predictive models (TLRN, FRNN-1, FRNN-2 and FRNN-3) using deep learning approach based on RNN and TLRN were proposed to predict the PV current performance through data input of temperature (T) and solar irradiance (G). The experiment results found that the highest energy production, array, reference, and final yields are 245.8 kWh, 3.43-5.65 kWh/kWp-day, 4.61-7.33 kWh/kWp-day, and 3.24-4.82 kWh/kWp-day, respectively. Meanwhile CF, CoE and PBP found to be 21.7%, 0.045 USD/kWh and 11.17 years, respectively. The highest performance for prediction models were found for FRNN-2 and FRNN-3 due to exhibits lower MSE which means being tightly fitted to experiments.
Preprint-Experimental and deep learning artificial neural network approach for evaluating grid‐connected photovoltaic systems
This article evaluates a 1.4 kW building integrated grid-connected photovoltaic plant. The PV plant installed in Faculty of Engineering solar energy lab, Sohar University, Oman and the system data has collected for a year from July 2017 to June 2018. The grid-connected system was evaluated in term of power, energy, specific yield, capacity factor, and cost of energy, and payback period. The measured diffuse and global solar irradiations are 3289 Wh/m2 and 6182 Wh/m2, respectively. Four predictive models (TLRN, FRNN-1, FRNN-2 and FRNN-3) using deep learning approach based on RNN and TLRN were proposed to predict the PV current performance through data input of temperature (T) and solar irradiance (G). The experiment results found that the highest energy production, array, reference, and final yields are 245.8 kWh, 3.43-5.65 kWh/kWp-day, 4.61-7.33 kWh/kWp-day, and 3.24-4.82 kWh/kWp-day, respectively. Meanwhile CF, CoE and PBP found to be 21.7%, 0.045 USD/kWh and 11.17 years, respectively. The highest performance for prediction models were found for FRNN-2 and FRNN-3 due to exhibits lower MSE which means being tightly fitted to experiments.
Preprint-Experimental and deep learning artificial neural network approach for evaluating grid‐connected photovoltaic systems
Kazem, Hussein A (Autor:in)
04.10.2021
oai:zenodo.org:5546790
Paper
Elektronische Ressource
Englisch
DDC:
690
Grid-connected photovoltaic converters: Topology and grid interconnection
| American Institute of Physics | 2014
Distributed photovoltaic grid-connected protection equipment
| Europäisches Patentamt | 2023