Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study
Dust accumulation on the photovoltaic system adversely degrades its power conversion efficiency (PCE). Focusing on residential installations, dust accumulation on PV modules installed in tropical regions may be vulnerable due to lower inclination angles and rainfall that encourage dust settlement on...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Diponegoro University
2022-05-01
|
| Series: | International Journal of Renewable Energy Development |
| Subjects: | |
| Online Access: | https://ijred.cbiore.id/index.php/ijred/article/view/42195 |
| _version_ | 1827632039451426816 |
|---|---|
| author | Emy Zairah Ahmad Hasila Jarimi Tajul Rosli Razak |
| author_facet | Emy Zairah Ahmad Hasila Jarimi Tajul Rosli Razak |
| author_sort | Emy Zairah Ahmad |
| collection | DOAJ |
| description | Dust accumulation on the photovoltaic system adversely degrades its power conversion efficiency (PCE). Focusing on residential installations, dust accumulation on PV modules installed in tropical regions may be vulnerable due to lower inclination angles and rainfall that encourage dust settlement on PV surfaces. However, most related studies in the tropics are concerned with studies in the laboratory, where dust collection is not from the actual field, and an accurate performance prediction model is impossible to obtain. This paper investigates the dust-related degradation in the PV output performance based on the developed Artificial Neural Network (ANN) predictive model. For this purpose, two identical monocrystalline modules of 120 Wp were tested and assessed under real operating conditions in Melaka, Malaysia (2.1896° N, 102.2501° E), of which one module was dust-free (clean). At the same time, the other was left uncleaned (dusty) for one month. The experimental datasets were divided into three sets: the first set was used for training and testing purposes, while the second and third, namely Data 2 and Data 3, were used for validating the proposed ANN model. The accuracy study shows that the predicted data using the ANN model and the experimentally acquired data are in good agreement, with MAE and RMSE for the cleaned PV module are as low as 1.28 °C, and 1.96 °C respectively for Data 2 and 3.93 °C and 4.92 °C respectively for Data 3. Meanwhile, the RMSE and MAE for the dusty PV module are 1.53°C and 2.82 °C respectively for Data 2 and 4.13 °C and 5.26 °C for Data 3. The ANN predictive model was then used for yield forecasting in a residential installation and found that the clean PV system provides a 7.29 % higher yield than a dusty system. The proposed ANN model is beneficial for PV system installers to assess and anticipate the impacts of dust on the PV installation in cities with similar climatic conditions. |
| first_indexed | 2024-03-09T14:30:27Z |
| format | Article |
| id | doaj.art-31c23b5b69bd4846b22f1cfd32ac2543 |
| institution | Directory Open Access Journal |
| issn | 2252-4940 |
| language | English |
| last_indexed | 2024-03-09T14:30:27Z |
| publishDate | 2022-05-01 |
| publisher | Diponegoro University |
| record_format | Article |
| series | International Journal of Renewable Energy Development |
| spelling | doaj.art-31c23b5b69bd4846b22f1cfd32ac25432023-11-28T02:08:36ZengDiponegoro UniversityInternational Journal of Renewable Energy Development2252-49402022-05-0111236537310.14710/ijred.2022.4219519763Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case StudyEmy Zairah Ahmad0https://orcid.org/0000-0001-9100-3116Hasila Jarimi1https://orcid.org/0000-0003-0921-3283Tajul Rosli Razak2https://orcid.org/0000-0002-6389-8108Solar Energy Research Institute, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, MalaysiaSolar Energy Research Institute, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, MalaysiaFaculty of Computer and Mathematical Science, Universiti Teknologi MARA, Perlis Branch, Perlis, MalaysiaDust accumulation on the photovoltaic system adversely degrades its power conversion efficiency (PCE). Focusing on residential installations, dust accumulation on PV modules installed in tropical regions may be vulnerable due to lower inclination angles and rainfall that encourage dust settlement on PV surfaces. However, most related studies in the tropics are concerned with studies in the laboratory, where dust collection is not from the actual field, and an accurate performance prediction model is impossible to obtain. This paper investigates the dust-related degradation in the PV output performance based on the developed Artificial Neural Network (ANN) predictive model. For this purpose, two identical monocrystalline modules of 120 Wp were tested and assessed under real operating conditions in Melaka, Malaysia (2.1896° N, 102.2501° E), of which one module was dust-free (clean). At the same time, the other was left uncleaned (dusty) for one month. The experimental datasets were divided into three sets: the first set was used for training and testing purposes, while the second and third, namely Data 2 and Data 3, were used for validating the proposed ANN model. The accuracy study shows that the predicted data using the ANN model and the experimentally acquired data are in good agreement, with MAE and RMSE for the cleaned PV module are as low as 1.28 °C, and 1.96 °C respectively for Data 2 and 3.93 °C and 4.92 °C respectively for Data 3. Meanwhile, the RMSE and MAE for the dusty PV module are 1.53°C and 2.82 °C respectively for Data 2 and 4.13 °C and 5.26 °C for Data 3. The ANN predictive model was then used for yield forecasting in a residential installation and found that the clean PV system provides a 7.29 % higher yield than a dusty system. The proposed ANN model is beneficial for PV system installers to assess and anticipate the impacts of dust on the PV installation in cities with similar climatic conditions.https://ijred.cbiore.id/index.php/ijred/article/view/42195dust effectpv performanceannyield forecastingelectrical output |
| spellingShingle | Emy Zairah Ahmad Hasila Jarimi Tajul Rosli Razak Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study International Journal of Renewable Energy Development dust effect pv performance ann yield forecasting electrical output |
| title | Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study |
| title_full | Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study |
| title_fullStr | Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study |
| title_full_unstemmed | Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study |
| title_short | Artificial Neural Network Prediction Model of Dust Effect on Photovoltaic Performance for Residential applications: Malaysia Case Study |
| title_sort | artificial neural network prediction model of dust effect on photovoltaic performance for residential applications malaysia case study |
| topic | dust effect pv performance ann yield forecasting electrical output |
| url | https://ijred.cbiore.id/index.php/ijred/article/view/42195 |
| work_keys_str_mv | AT emyzairahahmad artificialneuralnetworkpredictionmodelofdusteffectonphotovoltaicperformanceforresidentialapplicationsmalaysiacasestudy AT hasilajarimi artificialneuralnetworkpredictionmodelofdusteffectonphotovoltaicperformanceforresidentialapplicationsmalaysiacasestudy AT tajulroslirazak artificialneuralnetworkpredictionmodelofdusteffectonphotovoltaicperformanceforresidentialapplicationsmalaysiacasestudy |