Accurate electricity load forecasting with artificial neural networks

Daniel Ortiz-Arroyo; Morten K. Skov; Quang Huynh

doi:10.1109/CIMCA.2005.1631248

Accurate electricity load forecasting with artificial neural networks

Daniel Ortiz-Arroyo^*, Morten K. Skov, Quang Huynh

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

20 Citations (Scopus)

Abstract

In this paper we present a simple yet accurate model to forecast electricity load with Artificial Neural Networks (ANNs). We analyze the problem domain and choose the most adequate set of attributes in our model. To obtain the best performance in prediction, we follow an experimental approach analyzing the entire ANN design space and applying different training strategies. We found that when little data is available, applying this approach is critical to obtain the best results. Our experiments also show that a simple ANN-based prediction model appropriately tuned can outperform other more complex models. Our feed-forward ANN-based model obtained 29% improvement in prediction accuracy when compared to the best results presented in the 2001 EUNITE competition.

Original language	English
Title of host publication	Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet
Number of pages	6
Volume	1
Publication date	1 Dec 2005
Pages	94-99
Article number	1631248
ISBN (Print)	0769525040, 9780769525044
DOIs	https://doi.org/10.1109/CIMCA.2005.1631248
Publication status	Published - 1 Dec 2005
Event	International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005 - Vienna, Austria Duration: 28 Nov 2005 → 30 Nov 2005

Conference

Conference	International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005
Country/Territory	Austria
City	Vienna
Period	28/11/2005 → 30/11/2005
Sponsor	IEEE Computational Intelligence Society, European Society for Fuzzy Logic and Technology, EUFLAT, European Neural Networks Society, ENNS, International Association for Fuzzy Set in Management and, Japan Society for Fuzzy Theory and Intelligent Informatics

Access to Document

10.1109/CIMCA.2005.1631248

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Ortiz-Arroyo, D., Skov, M. K., & Huynh, Q. (2005). Accurate electricity load forecasting with artificial neural networks. In Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet (Vol. 1, pp. 94-99). Article 1631248 https://doi.org/10.1109/CIMCA.2005.1631248

@inproceedings{1f7f1b267fa64157b1da031e7506ecc8,

title = "Accurate electricity load forecasting with artificial neural networks",

abstract = "In this paper we present a simple yet accurate model to forecast electricity load with Artificial Neural Networks (ANNs). We analyze the problem domain and choose the most adequate set of attributes in our model. To obtain the best performance in prediction, we follow an experimental approach analyzing the entire ANN design space and applying different training strategies. We found that when little data is available, applying this approach is critical to obtain the best results. Our experiments also show that a simple ANN-based prediction model appropriately tuned can outperform other more complex models. Our feed-forward ANN-based model obtained 29% improvement in prediction accuracy when compared to the best results presented in the 2001 EUNITE competition.",

author = "Daniel Ortiz-Arroyo and Skov, {Morten K.} and Quang Huynh",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/CIMCA.2005.1631248",

language = "English",

isbn = "0769525040",

volume = "1",

pages = "94--99",

booktitle = "Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet",

note = "International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005 ; Conference date: 28-11-2005 Through 30-11-2005",

}

Ortiz-Arroyo, D, Skov, MK & Huynh, Q 2005, Accurate electricity load forecasting with artificial neural networks. in Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. vol. 1, 1631248, pp. 94-99, International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005, Vienna, Austria, 28/11/2005. https://doi.org/10.1109/CIMCA.2005.1631248

Accurate electricity load forecasting with artificial neural networks. / Ortiz-Arroyo, Daniel; Skov, Morten K.; Huynh, Quang.
Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. Vol. 1 2005. p. 94-99 1631248.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Accurate electricity load forecasting with artificial neural networks

AU - Ortiz-Arroyo, Daniel

AU - Skov, Morten K.

AU - Huynh, Quang

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper we present a simple yet accurate model to forecast electricity load with Artificial Neural Networks (ANNs). We analyze the problem domain and choose the most adequate set of attributes in our model. To obtain the best performance in prediction, we follow an experimental approach analyzing the entire ANN design space and applying different training strategies. We found that when little data is available, applying this approach is critical to obtain the best results. Our experiments also show that a simple ANN-based prediction model appropriately tuned can outperform other more complex models. Our feed-forward ANN-based model obtained 29% improvement in prediction accuracy when compared to the best results presented in the 2001 EUNITE competition.

AB - In this paper we present a simple yet accurate model to forecast electricity load with Artificial Neural Networks (ANNs). We analyze the problem domain and choose the most adequate set of attributes in our model. To obtain the best performance in prediction, we follow an experimental approach analyzing the entire ANN design space and applying different training strategies. We found that when little data is available, applying this approach is critical to obtain the best results. Our experiments also show that a simple ANN-based prediction model appropriately tuned can outperform other more complex models. Our feed-forward ANN-based model obtained 29% improvement in prediction accuracy when compared to the best results presented in the 2001 EUNITE competition.

UR - http://www.scopus.com/inward/record.url?scp=33847236265&partnerID=8YFLogxK

U2 - 10.1109/CIMCA.2005.1631248

DO - 10.1109/CIMCA.2005.1631248

M3 - Article in proceeding

AN - SCOPUS:33847236265

SN - 0769525040

SN - 9780769525044

VL - 1

SP - 94

EP - 99

BT - Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet

T2 - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005

Y2 - 28 November 2005 through 30 November 2005

ER -

Ortiz-Arroyo D, Skov MK, Huynh Q. Accurate electricity load forecasting with artificial neural networks. In Proceedings - International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on Intelligent Agents, Web Technologies and Internet. Vol. 1. 2005. p. 94-99. 1631248 doi: 10.1109/CIMCA.2005.1631248

Accurate electricity load forecasting with artificial neural networks

Abstract

Conference

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this