login

Search documents

Browse topics

Document details

 
Title:
 
Application of Machine Learning to Assess the Thermal Behaviour of PV Modules in Different Climate Zones
 
Author(s):
 
J. Ascencio-Vásquez, I. Kaaya, K.-A. Weiß, M. Topic
 
Keywords:
 
Thermal Model, PV Module, Photovoltaic (PV), Machine Learning
 
Topic:
 
PV Systems – Modelling, Design, Operation and Performance
Subtopic: Operation, Performance and Maintenance of PV Systems
Event: 38th European Photovoltaic Solar Energy Conference and Exhibition
Session: 5DO.1.5
 
Pages:
 
1028 - 1032
ISBN: 3-936338-78-7
Paper DOI: 10.4229/EUPVSEC20212021-5DO.1.5
 
Price:
 
 
0,00 EUR
 
Document(s): paper, presentation
 

Abstract/Summary:


Identifying the main factors for PV module performance losses, degradation and failures are still under research. Researchers have developed physical models to characterize the weather and the local environment where PV modules operate. , Indeed, published physical models can help to estimate PV long-term yield and degradation rates. These models highly depend on the operating PV module temperature, UV irradiance, and relative humidity as main inputs. In most cases, these input variables need to be modelled. For example, several models to estimate PV module temperature are available. However, improvements in their accuracy are still needed. Therefore, in this paper, we apply Machine Learning approaches to identify the combination of climate variables needed to model the PV module temperature. We then propose a modifiedtFaiman model that includes the effect of UV irradiance. Lastly, the modified model is benchmarked with other physical temperature models and shows an improvement over other models.