skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs

Abstract

Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. Finally, the New England electrical load data are used tomore » train and validate the forecast prediction.« less

Authors:
ORCiD logo [1];  [1]
  1. Univ. of Miami, Coral Gables, FL (United States)
Publication Date:
Research Org.:
Univ. of Miami, Coral Gables, FL (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE)
OSTI Identifier:
1347528
Grant/Contract Number:  
EE0005545
Resource Type:
Accepted Manuscript
Journal Name:
Energies (Basel)
Additional Journal Information:
Journal Name: Energies (Basel); Journal Volume: 10; Journal Issue: 1; Journal ID: ISSN 1996-1073
Publisher:
MDPI AG
Country of Publication:
United States
Language:
English
Subject:
30 DIRECT ENERGY CONVERSION; short-term load forecasting; nonlinear autoregressive exogenous input; artificial neural networks; closed-loop forecasting

Citation Formats

Buitrago, Jaime, and Asfour, Shihab. Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs. United States: N. p., 2017. Web. doi:10.3390/en10010040.
Buitrago, Jaime, & Asfour, Shihab. Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs. United States. doi:10.3390/en10010040.
Buitrago, Jaime, and Asfour, Shihab. Sun . "Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs". United States. doi:10.3390/en10010040. https://www.osti.gov/servlets/purl/1347528.
@article{osti_1347528,
title = {Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs},
author = {Buitrago, Jaime and Asfour, Shihab},
abstractNote = {Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. Finally, the New England electrical load data are used to train and validate the forecast prediction.},
doi = {10.3390/en10010040},
journal = {Energies (Basel)},
number = 1,
volume = 10,
place = {United States},
year = {2017},
month = {1}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Effect of temperature on short term load forecasting using an integrated ANN
journal, November 2004


Techniques of applying wavelet transform into combined model for short-term load forecasting
journal, April 2006

  • Nengling, Tai; Stenzel, Jürgen; Hongxiao, Wu
  • Electric Power Systems Research, Vol. 76, Issue 6-7
  • DOI: 10.1016/j.epsr.2005.07.003

Neural networks for short-term load forecasting: a review and evaluation
journal, January 2001

  • Hippert, H. S.; Pedreira, C. E.; Souza, R. C.
  • IEEE Transactions on Power Systems, Vol. 16, Issue 1
  • DOI: 10.1109/59.910780

Electric load forecasting methods: Tools for decision making
journal, December 2009

  • Hahn, Heiko; Meyer-Nieberg, Silja; Pickl, Stefan
  • European Journal of Operational Research, Vol. 199, Issue 3
  • DOI: 10.1016/j.ejor.2009.01.062

Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher
journal, June 2003


Forecasting with artificial neural networks:
journal, March 1998


A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings
journal, October 2015


A hybrid short-term load forecasting with a new data preprocessing framework
journal, February 2015


Univariate modeling and forecasting of monthly energy demand time series using abductive and neural networks
journal, May 2008


Cascaded artificial neural networks for short-term load forecasting
journal, January 1997

  • AlFuhaid, A. S.; El-Sayed, M. A.; Mahmoud, M. S.
  • IEEE Transactions on Power Systems, Vol. 12, Issue 4
  • DOI: 10.1109/59.627852

Autoregressive with Exogenous Variables and Neural Network Short-Term Load Forecast Models for Residential Low Voltage Distribution Networks
journal, April 2014

  • Bennett, Christopher; Stewart, Rodney; Lu, Junwei
  • Energies, Vol. 7, Issue 5
  • DOI: 10.3390/en7052938

An efficient approach for short term load forecasting using artificial neural networks
journal, October 2006

  • Kandil, Nahi; Wamkeue, René; Saad, Maarouf
  • International Journal of Electrical Power & Energy Systems, Vol. 28, Issue 8
  • DOI: 10.1016/j.ijepes.2006.02.014

Very short-term load forecasting using artificial neural networks
journal, January 2000

  • Charytoniuk, W.; Chen, M. -S.
  • IEEE Transactions on Power Systems, Vol. 15, Issue 1
  • DOI: 10.1109/59.852131

Short-Term Load Forecasting for Microgrids Based on Artificial Neural Networks
journal, March 2013

  • Hernandez, Luis; Baladrón, Carlos; Aguiar, Javier
  • Energies, Vol. 6, Issue 3
  • DOI: 10.3390/en6031385

Improved Short-Term Load Forecasting Based on Two-Stage Predictions with Artificial Neural Networks in a Microgrid Environment
journal, August 2013

  • Hernández, Luis; Baladrón, Carlos; Aguiar, Javier
  • Energies, Vol. 6, Issue 9
  • DOI: 10.3390/en6094489

Short-term load forecasting based on artificial neural networks parallel implementation
journal, October 2002


ANNSTLF-a neural-network-based electric load forecasting system
journal, July 1997

  • Khotanzad, A.; Afkhami-Rohani, R.
  • IEEE Transactions on Neural Networks, Vol. 8, Issue 4
  • DOI: 10.1109/72.595881

Short-term load forecasting using neural networks
journal, April 1995


Next hour load forecast in medium voltage electricity distribution
journal, September 2008

  • Jorge Santos, P.; Gomes Martins, A.; Pires, A. J.
  • International Journal of Energy Sector Management, Vol. 2, Issue 3
  • DOI: 10.1108/17506220810892964

On the use of reactive power as an endogenous variable in short-term load forecasting
journal, January 2003

  • Santos, P. Jorge; Martins, A. Gomes; Pires, A. J.
  • International Journal of Energy Research, Vol. 27, Issue 5
  • DOI: 10.1002/er.892

Input space to neural network based load forecasters
journal, October 2008

  • Alves da Silva, Alexandre P.; Ferreira, Vitor H.; Velasquez, Roberto M. G.
  • International Journal of Forecasting, Vol. 24, Issue 4
  • DOI: 10.1016/j.ijforecast.2008.07.006

Toward Estimating Autonomous Neural Network-Based Electric Load Forecasters
journal, November 2007

  • Ferreira, Vitor Hugo; da Silva, Alexandre P. Alves
  • IEEE Transactions on Power Systems, Vol. 22, Issue 4
  • DOI: 10.1109/TPWRS.2007.908438

Designing the input vector to ANN-based models for short-term load forecast in electricity distribution systems
journal, May 2007

  • Santos, P. J.; Martins, A. G.; Pires, A. J.
  • International Journal of Electrical Power & Energy Systems, Vol. 29, Issue 4
  • DOI: 10.1016/j.ijepes.2006.09.002

Hour-ahead demand forecasting in smart grid using support vector regression (SVR): HOURLY DEMAND FORECASTING IN SMART GRID
journal, September 2013

  • Fattaheian-Dehkordi, Sajjad; Fereidunian, Alireza; Gholami-Dehkordi, Hamid
  • International Transactions on Electrical Energy Systems, Vol. 24, Issue 12
  • DOI: 10.1002/etep.1791

Short Term Load Forecasting Using Artificial Neural Networks for the West of Iran
journal, December 2007


Artificial neural networks for short-term load forecasting in microgrids environment
journal, October 2014


Design of artificial neural networks for short-term load forecasting. Part 2: Multilayer feedforward networks for peak load and valley load forecasting
journal, January 1991

  • Hsu, Yuan-Yih; Yang, Chien-Chuen
  • IEE Proceedings C Generation, Transmission and Distribution, Vol. 138, Issue 5
  • DOI: 10.1049/ip-c.1991.0052

Design of artificial neural networks for short-term load forecasting. Part 1: Self-organising feature maps for day type identification
journal, January 1991

  • Hsu, Yuan-Yih; Yang, Chien-Chuen
  • IEE Proceedings C Generation, Transmission and Distribution, Vol. 138, Issue 5
  • DOI: 10.1049/ip-c.1991.0051

Global model for short-term load forecasting using artificial neural networks
journal, January 2002

  • Marin, F. J.; Garcia-Lagos, F.; Joya, G.
  • IEE Proceedings - Generation, Transmission and Distribution, Vol. 149, Issue 2
  • DOI: 10.1049/ip-gtd:20020224

Application of Artificial Neural Networks and Fuzzy logic Methods for Short Term Load Forecasting
journal, January 2012


Interval Type-2 Fuzzy Logic Systems for Load Forecasting: A Comparative Study
journal, August 2012

  • Khosravi, Abbas; Nahavandi, Saeid; Creighton, Doug
  • IEEE Transactions on Power Systems, Vol. 27, Issue 3
  • DOI: 10.1109/TPWRS.2011.2181981

Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems
journal, January 1995

  • Kwang-Ho Kim,
  • IEEE Transactions on Power Systems, Vol. 10, Issue 3
  • DOI: 10.1109/59.466492

Modelling self-optimised short term load forecasting for medium voltage loads using tunning fuzzy systems and Artificial Neural Networks
journal, December 2015


Evolving artificial neural networks for short term load forecasting
journal, December 1998


Implementation of hybrid short-term load forecasting system with analysis of temperature sensitivities
journal, October 2007


A new short-term load forecasting approach using self-organizing fuzzy ARMAX models
journal, January 1998

  • Hong-Tzer Yang,
  • IEEE Transactions on Power Systems, Vol. 13, Issue 1
  • DOI: 10.1109/59.651639

A hierarchical neural model in short-term load forecasting
journal, September 2004

  • Carpinteiro, Otavio A. S.; Reis, Agnaldo J. R.; da Silva, Alexandre P. A.
  • Applied Soft Computing, Vol. 4, Issue 4
  • DOI: 10.1016/j.asoc.2004.02.005

Electric load Pattern Classification Using Parameter Estimation, Clustering and Artificial Neural Networks
journal, January 2015


Application of SOM neural networks to short-term load forecasting: The Spanish electricity market case study
journal, October 2012


A hybrid artificial neural network—differential dynamic programming approach for short-term hydro scheduling
journal, May 1995


Simulation of Compressor Transient Behavior Through Recurrent Neural Network Models
journal, February 2005


Numerical bounds to assure initial local stability of NARX multilayer perceptrons and radial basis functions
journal, December 2008


    Works referencing / citing this record:

    Risk Evaluation of Distribution Networks Considering Residential Load Forecasting with Stochastic Modeling of Electric Vehicles
    journal, May 2019

    • Habib, Salman; Khan, Muhammad Mansoor; Abbas, Farukh
    • Energy Technology, Vol. 7, Issue 7
    • DOI: 10.1002/ente.201900191

    Risk Evaluation of Distribution Networks Considering Residential Load Forecasting with Stochastic Modeling of Electric Vehicles
    journal, May 2019

    • Habib, Salman; Khan, Muhammad Mansoor; Abbas, Farukh
    • Energy Technology, Vol. 7, Issue 7
    • DOI: 10.1002/ente.201900191