Modeling of wind speed and relative humidity for Malaysia using ANNs: Approach to estimate dust deposition on PV systems

Tamer Khatib, Azah Mohamed, Kamaruzzaman Sopian, M. Mahmod

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents a wind speed and relative humidity predictions using feedforward artificial neural network (FFNN). Wind speed and relative humidity values obtained from weather records for Malaysia are used in training the FFNNs for estimating dust deposition on photovoltaic (PV) systems. Three statistical parameters, namely, mean absolute percentage error, MAPE, mean bias error, MBE, and root mean square error, RMSE are used to evaluate the neural networks. Based on results, the proposed neural network gives accurate prediction of hourly wind speed with MAPE, RMSE and MBE values of 43%, 0.56 and -0.35, respectively. Meanwhile, the MAPE values for predicting daily and monthly wind speed are 13.04% and 4.8%, respectively. On the other hand, the MAPE, RMSE and MBE values in predicting hourly relative humidity are 5.08%, 5.8 and -0.041, respectively. While the MAPE values for the daily and monthly predicted values are 2.66% and 0.57%.

Original languageEnglish
Title of host publication2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts
Pages42-47
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Shah Alam, Selangor
Duration: 6 Jun 20117 Jun 2011

Other

Other2011 5th International Power Engineering and Optimization Conference, PEOCO 2011
CityShah Alam, Selangor
Period6/6/117/6/11

Fingerprint

Dust
Atmospheric humidity
Molecular beam epitaxy
Neural networks
Mean square error

Keywords

  • ANN
  • dust deposition
  • PV systems
  • relative speed prediction
  • wind speed prediction

ASJC Scopus subject areas

  • Energy Engineering and Power Technology

Cite this

Khatib, T., Mohamed, A., Sopian, K., & Mahmod, M. (2011). Modeling of wind speed and relative humidity for Malaysia using ANNs: Approach to estimate dust deposition on PV systems. In 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts (pp. 42-47). [5970383] https://doi.org/10.1109/PEOCO.2011.5970383

Modeling of wind speed and relative humidity for Malaysia using ANNs : Approach to estimate dust deposition on PV systems. / Khatib, Tamer; Mohamed, Azah; Sopian, Kamaruzzaman; Mahmod, M.

2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts. 2011. p. 42-47 5970383.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khatib, T, Mohamed, A, Sopian, K & Mahmod, M 2011, Modeling of wind speed and relative humidity for Malaysia using ANNs: Approach to estimate dust deposition on PV systems. in 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts., 5970383, pp. 42-47, 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011, Shah Alam, Selangor, 6/6/11. https://doi.org/10.1109/PEOCO.2011.5970383
Khatib T, Mohamed A, Sopian K, Mahmod M. Modeling of wind speed and relative humidity for Malaysia using ANNs: Approach to estimate dust deposition on PV systems. In 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts. 2011. p. 42-47. 5970383 https://doi.org/10.1109/PEOCO.2011.5970383
Khatib, Tamer ; Mohamed, Azah ; Sopian, Kamaruzzaman ; Mahmod, M. / Modeling of wind speed and relative humidity for Malaysia using ANNs : Approach to estimate dust deposition on PV systems. 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts. 2011. pp. 42-47
@inproceedings{31881f83f9af4e17b18bb7c812f10eb2,
title = "Modeling of wind speed and relative humidity for Malaysia using ANNs: Approach to estimate dust deposition on PV systems",
abstract = "This paper presents a wind speed and relative humidity predictions using feedforward artificial neural network (FFNN). Wind speed and relative humidity values obtained from weather records for Malaysia are used in training the FFNNs for estimating dust deposition on photovoltaic (PV) systems. Three statistical parameters, namely, mean absolute percentage error, MAPE, mean bias error, MBE, and root mean square error, RMSE are used to evaluate the neural networks. Based on results, the proposed neural network gives accurate prediction of hourly wind speed with MAPE, RMSE and MBE values of 43{\%}, 0.56 and -0.35, respectively. Meanwhile, the MAPE values for predicting daily and monthly wind speed are 13.04{\%} and 4.8{\%}, respectively. On the other hand, the MAPE, RMSE and MBE values in predicting hourly relative humidity are 5.08{\%}, 5.8 and -0.041, respectively. While the MAPE values for the daily and monthly predicted values are 2.66{\%} and 0.57{\%}.",
keywords = "ANN, dust deposition, PV systems, relative speed prediction, wind speed prediction",
author = "Tamer Khatib and Azah Mohamed and Kamaruzzaman Sopian and M. Mahmod",
year = "2011",
doi = "10.1109/PEOCO.2011.5970383",
language = "English",
isbn = "9781457703546",
pages = "42--47",
booktitle = "2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts",

}

TY - GEN

T1 - Modeling of wind speed and relative humidity for Malaysia using ANNs

T2 - Approach to estimate dust deposition on PV systems

AU - Khatib, Tamer

AU - Mohamed, Azah

AU - Sopian, Kamaruzzaman

AU - Mahmod, M.

PY - 2011

Y1 - 2011

N2 - This paper presents a wind speed and relative humidity predictions using feedforward artificial neural network (FFNN). Wind speed and relative humidity values obtained from weather records for Malaysia are used in training the FFNNs for estimating dust deposition on photovoltaic (PV) systems. Three statistical parameters, namely, mean absolute percentage error, MAPE, mean bias error, MBE, and root mean square error, RMSE are used to evaluate the neural networks. Based on results, the proposed neural network gives accurate prediction of hourly wind speed with MAPE, RMSE and MBE values of 43%, 0.56 and -0.35, respectively. Meanwhile, the MAPE values for predicting daily and monthly wind speed are 13.04% and 4.8%, respectively. On the other hand, the MAPE, RMSE and MBE values in predicting hourly relative humidity are 5.08%, 5.8 and -0.041, respectively. While the MAPE values for the daily and monthly predicted values are 2.66% and 0.57%.

AB - This paper presents a wind speed and relative humidity predictions using feedforward artificial neural network (FFNN). Wind speed and relative humidity values obtained from weather records for Malaysia are used in training the FFNNs for estimating dust deposition on photovoltaic (PV) systems. Three statistical parameters, namely, mean absolute percentage error, MAPE, mean bias error, MBE, and root mean square error, RMSE are used to evaluate the neural networks. Based on results, the proposed neural network gives accurate prediction of hourly wind speed with MAPE, RMSE and MBE values of 43%, 0.56 and -0.35, respectively. Meanwhile, the MAPE values for predicting daily and monthly wind speed are 13.04% and 4.8%, respectively. On the other hand, the MAPE, RMSE and MBE values in predicting hourly relative humidity are 5.08%, 5.8 and -0.041, respectively. While the MAPE values for the daily and monthly predicted values are 2.66% and 0.57%.

KW - ANN

KW - dust deposition

KW - PV systems

KW - relative speed prediction

KW - wind speed prediction

UR - http://www.scopus.com/inward/record.url?scp=80052290480&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052290480&partnerID=8YFLogxK

U2 - 10.1109/PEOCO.2011.5970383

DO - 10.1109/PEOCO.2011.5970383

M3 - Conference contribution

AN - SCOPUS:80052290480

SN - 9781457703546

SP - 42

EP - 47

BT - 2011 5th International Power Engineering and Optimization Conference, PEOCO 2011 - Program and Abstracts

ER -