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

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

doi:10.1109/isie.2012.6237191

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

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

School of Computing, Engineering and Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Citations (Scopus)

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.

Original language	English
Title of host publication	2012 IEEE International Symposium on Industrial Electronics
Place of Publication	Piscataway, NJ
Publisher	IEEE
ISBN (Print)	9781467301589
DOIs	https://doi.org/10.1109/isie.2012.6237191
Publication status	Published - 12 Jul 2012

Access to Document

10.1109/isie.2012.6237191

Cite this

@inproceedings{725c0f878798410dbd31ab4ec2ce40f4,

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

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.",

author = "Awan, {Shahid M.} and Khan, {Zubair A.} and M. Aslam and Waqar Mahmood and Affan Ahsan",

year = "2012",

month = jul,

day = "12",

doi = "10.1109/isie.2012.6237191",

language = "English",

isbn = "9781467301589",

booktitle = "2012 IEEE International Symposium on Industrial Electronics",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Application of NARX based FFNN, SVR and ANN Fitting models for long term industrial load forecasting and their comparison

AU - Awan, Shahid M.

AU - Khan, Zubair A.

AU - Aslam, M.

AU - Mahmood, Waqar

AU - Ahsan, Affan

PY - 2012/7/12

Y1 - 2012/7/12

N2 - 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.

AB - 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.

U2 - 10.1109/isie.2012.6237191

DO - 10.1109/isie.2012.6237191

M3 - Conference contribution

SN - 9781467301589

BT - 2012 IEEE International Symposium on Industrial Electronics

PB - IEEE

CY - Piscataway, NJ

ER -

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

Abstract

Access to Document

Fingerprint

Cite this