Estimating Ambient Temperature for Malaysia Using Generalized Regression Neural Network
- 23 January 2012
- journal article
- research article
- Published by Taylor & Francis Ltd in International Journal of Green Energy
- Vol. 9 (3), 195-201
- https://doi.org/10.1080/15435075.2011.621473
Abstract
This paper presents a new method for predicting hourly ambient temperature series for Malaysia using generalized regression neural network (GRNN). MATLAB was used to develop the GRNN using the weather records for Malaysia. The developed model has five inputs and one output. The inputs of the proposed model are hour, day, month, sunshine ratio, and relative humidity, meanwhile ambient temperature is the output. To evaluate the accuracy of the GRNN, three statistical parameters, namely, the mean absolute percentage error (MAPE), mean bias error (MBE), and root mean square error (RMSE) are considered. The GRNN results give an accurate prediction of ambient temperatures for the selected testing months with average values of MAPE, MBE, and RMSE of 2.65%, 4.05%, and 0.347%, respectively. The advantage of the proposed method is that it is able to predict ambient temperature at sites where there is no ambient temperature-measuring instrument installed.Keywords
This publication has 8 references indexed in Scilit:
- Daily means ambient temperature prediction using artificial neural network method: A case study of TurkeyRenewable Energy, 2009
- Hourly temperature forecasting using abductive networksEngineering Applications of Artificial Intelligence, 2004
- Application of neural networks for the prediction of hourly mean surface temperatures in Saudi ArabiaRenewable Energy, 2002
- A new analytical model for temperature predictionsRenewable Energy, 1997
- Elements of Artificial Neural NetworksPublished by MIT Press ,1996
- Time-series analysis of climatic variablesSolar Energy, 1995
- An electronic system for predicting air temperature and wind speed patternsRenewable Energy, 1994
- Prediction of meteorological parametersIl Nuovo Cimento C, 1991