A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping

Hanshen Li, Yuan Zhu, Takayuki Furuzuki, Zhe Li

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

3 Citations (Scopus)

Abstract

As a routine within the planning and operation of the electrical power system, Short-term load forecasting (STLF) is an essential issue in energy fields. Its prediction accuracy and precision specifically have an effect on the basic safety, stability and economic efficiency of the power system. Moreover, the actual forecasting result also has an impact on operations such as startup and shutdown of the power units, power switching, equipment maintenance, etc. Nonlinear Autoregressive models with Exogenous Input (NARX) Neural Network has been utilized for STLF and proved its effectiveness. This paper proposes a localized Bayesian-Regularization NARX Neural Network model combined with Self-Organizing Mapping (SOM). SOM Neural Network is utilized to extract the meteorological distribution and K-means is utilized to cluster the data. Assessment results depending on half-hourly Australian Grid data and Meteorological data demonstrate that the enhanced model can provide a higher accuracy prediction, which could bring additional economic benefits and extensive social advantages.

Original languageEnglish
Title of host publication2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages749-754
Number of pages6
ISBN (Electronic)9781509051571
DOIs
Publication statusPublished - 2017 Jul 25
Event3rd IEEE International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017 - Kaohsiung, Taiwan, Province of China
Duration: 2017 Jun 32017 Jun 7

Other

Other3rd IEEE International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017
CountryTaiwan, Province of China
CityKaohsiung
Period17/6/317/6/7

Fingerprint

Short-term Load Forecasting
Self-organizing
Neural Network Model
Power System
Economics
Neural Networks
Neural networks
Data Grid
Prediction
Start-up
K-means
Autoregressive Model
Nonlinear Model
Forecasting
Regularization
High Accuracy
Maintenance
Safety
Planning
Unit

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Control and Optimization

Cite this

Li, H., Zhu, Y., Furuzuki, T., & Li, Z. (2017). A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping. In 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017 (pp. 749-754). [7992133] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IFEEC.2017.7992133

A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping. / Li, Hanshen; Zhu, Yuan; Furuzuki, Takayuki; Li, Zhe.

2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 749-754 7992133.

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

Li, H, Zhu, Y, Furuzuki, T & Li, Z 2017, A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping. in 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017., 7992133, Institute of Electrical and Electronics Engineers Inc., pp. 749-754, 3rd IEEE International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017, Kaohsiung, Taiwan, Province of China, 17/6/3. https://doi.org/10.1109/IFEEC.2017.7992133
Li H, Zhu Y, Furuzuki T, Li Z. A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping. In 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 749-754. 7992133 https://doi.org/10.1109/IFEEC.2017.7992133
Li, Hanshen ; Zhu, Yuan ; Furuzuki, Takayuki ; Li, Zhe. / A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping. 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 749-754
@inproceedings{bd58f750fe82451daadee2a5b6333ac9,
title = "A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping",
abstract = "As a routine within the planning and operation of the electrical power system, Short-term load forecasting (STLF) is an essential issue in energy fields. Its prediction accuracy and precision specifically have an effect on the basic safety, stability and economic efficiency of the power system. Moreover, the actual forecasting result also has an impact on operations such as startup and shutdown of the power units, power switching, equipment maintenance, etc. Nonlinear Autoregressive models with Exogenous Input (NARX) Neural Network has been utilized for STLF and proved its effectiveness. This paper proposes a localized Bayesian-Regularization NARX Neural Network model combined with Self-Organizing Mapping (SOM). SOM Neural Network is utilized to extract the meteorological distribution and K-means is utilized to cluster the data. Assessment results depending on half-hourly Australian Grid data and Meteorological data demonstrate that the enhanced model can provide a higher accuracy prediction, which could bring additional economic benefits and extensive social advantages.",
author = "Hanshen Li and Yuan Zhu and Takayuki Furuzuki and Zhe Li",
year = "2017",
month = "7",
day = "25",
doi = "10.1109/IFEEC.2017.7992133",
language = "English",
pages = "749--754",
booktitle = "2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A localized NARX Neural Network model for Short-term load forecasting based upon Self-Organizing Mapping

AU - Li, Hanshen

AU - Zhu, Yuan

AU - Furuzuki, Takayuki

AU - Li, Zhe

PY - 2017/7/25

Y1 - 2017/7/25

N2 - As a routine within the planning and operation of the electrical power system, Short-term load forecasting (STLF) is an essential issue in energy fields. Its prediction accuracy and precision specifically have an effect on the basic safety, stability and economic efficiency of the power system. Moreover, the actual forecasting result also has an impact on operations such as startup and shutdown of the power units, power switching, equipment maintenance, etc. Nonlinear Autoregressive models with Exogenous Input (NARX) Neural Network has been utilized for STLF and proved its effectiveness. This paper proposes a localized Bayesian-Regularization NARX Neural Network model combined with Self-Organizing Mapping (SOM). SOM Neural Network is utilized to extract the meteorological distribution and K-means is utilized to cluster the data. Assessment results depending on half-hourly Australian Grid data and Meteorological data demonstrate that the enhanced model can provide a higher accuracy prediction, which could bring additional economic benefits and extensive social advantages.

AB - As a routine within the planning and operation of the electrical power system, Short-term load forecasting (STLF) is an essential issue in energy fields. Its prediction accuracy and precision specifically have an effect on the basic safety, stability and economic efficiency of the power system. Moreover, the actual forecasting result also has an impact on operations such as startup and shutdown of the power units, power switching, equipment maintenance, etc. Nonlinear Autoregressive models with Exogenous Input (NARX) Neural Network has been utilized for STLF and proved its effectiveness. This paper proposes a localized Bayesian-Regularization NARX Neural Network model combined with Self-Organizing Mapping (SOM). SOM Neural Network is utilized to extract the meteorological distribution and K-means is utilized to cluster the data. Assessment results depending on half-hourly Australian Grid data and Meteorological data demonstrate that the enhanced model can provide a higher accuracy prediction, which could bring additional economic benefits and extensive social advantages.

UR - http://www.scopus.com/inward/record.url?scp=85034055232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034055232&partnerID=8YFLogxK

U2 - 10.1109/IFEEC.2017.7992133

DO - 10.1109/IFEEC.2017.7992133

M3 - Conference contribution

SP - 749

EP - 754

BT - 2017 IEEE 3rd International Future Energy Electronics Conference and ECCE Asia, IFEEC - ECCE Asia 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -