Application of NARX based FFNN, SVR and ANN Fitting models for long term industrial load forecasting and their comparison

Author

Awan, Shahid M. ; Khan, Zubair A. ; Aslam, M. ; Mahmood, Waqar ; Ahsan, Affan

Author_Institution

Al-Khawarizmi Inst. of Comput. Sci., Univ. of Eng. & Technol., Lahore, Pakistan

fYear

2012

fDate

28-31 May 2012

Firstpage

803

Lastpage

807

Abstract

Accurate load forecasting is essential for energy planning and load management. This paper presents long term industrial load forecasting (LTLF) using Nonlinear Autoregressive Exogenous model (NARX) based Feed-Forward Neural Network (FFNN) method, Support Vector Regression (SVR) and Neural Network models. It is applied to data sets obtained from National Transmission and Dispatch Company (NTDC) of Pakistan, ranging from 1970 to 2010. Several influencing load factors are examined. Comparison of results obtained by all three techniques is presented which portray a high acceptable accuracy with 2.09% Mean absolute percentage error (MAPE) on monthly and yearly demand estimation for industrial sector.

Keywords

feedforward neural nets; load forecasting; load management; power engineering computing; regression analysis; support vector machines; ANN fitting models; LTLF; MAPE; NARX based FFNN application; NTDC; National Transmission and Dispatch Company; Pakistan; SVR fitting models; energy planning; feedforward neural network method; load factors; load management; long term industrial load forecasting; mean absolute percentage error; nonlinear autoregressive exogenous model; support vector regression; Artificial neural networks; Biological system modeling; Load forecasting; Load modeling; Predictive models; Support vector machines; Neural nonlinear systems; modelling; nonlinear estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics (ISIE), 2012 IEEE International Symposium on

Conference_Location

Hangzhou

ISSN

2163-5137

Print_ISBN

978-1-4673-0159-6

Electronic_ISBN

2163-5137

Type

conf

DOI

10.1109/ISIE.2012.6237191

Filename

6237191