An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting

A preliminary case study

Moslem Yousefi, Danial Hooshyar, Milad Yousefi, Weria Khaksar, Khairul Salleh Mohamed Sahari, Firas Basim Ismail

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

7 Citations (Scopus)

Abstract

Given the importance of an accurate wind speed forecasting for efficient utilization of wind farms, and the volatile nature of wind speed data including its non-linear and uncertain nature, the wind speed forecasting has remained an active field of research. In this study, the non-linearity of wind speed is tackled using artificial neural network and its uncertainty by wavelet transform. To avoid trial-and-error process for selection the ANN structure, the results of auto correlation factor (ACF) and partial auto correlation factor (PACF) on the historical wind speed data are employed. Instead of forecasting the time series directly, a set of better-behaved components of the data is achieved by decomposing the data using wavelet transform and are forecasted separately using a feedforward neural network. Finally, using an inverse wavelet transform, the future time series is reconstructed and the wind speed could be forecasted. The historical hourly wind speed from ABEI weather station in Idaho, United States is used for assessing the performance of the proposed algorithm. This data set is merely selected due to its availability. The data is divided to three parts of 50%, 25% and 25% for training, testing and validation respectively. The testing part of data set will be merely used for assessing the performance of the neural network which guarantees that only unseen data is used to evaluate the forecasting performance of the network. On the other hand, validation data could be used for parameter-setting of the network if required. The results shows that using wavelet transform can enhance the forecasting accuracy when it is compared with a regular neural network prediction algorithm.

Original languageEnglish
Title of host publicationProceedings - 2015 International Conference on Science in Information Technology
Subtitle of host publicationBig Data Spectrum for Future Information Economy, ICSITech 2015
EditorsYana Hendriana, Andri Pranolo, Adhi Prahara, Dewi Pramudi Ismi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages95-99
Number of pages5
ISBN (Electronic)9781479983865
DOIs
Publication statusPublished - 16 Feb 2016
EventInternational Conference on Science in Information Technology, ICSITech 2015 - Yogyakarta, Indonesia
Duration: 27 Oct 201528 Oct 2015

Other

OtherInternational Conference on Science in Information Technology, ICSITech 2015
CountryIndonesia
CityYogyakarta
Period27/10/1528/10/15

Fingerprint

neural network
Wavelet transforms
Neural networks
Autocorrelation
Time series
time series
Inverse transforms
performance
Feedforward neural networks
Testing
Farms
guarantee
Availability
farm
utilization
uncertainty

All Science Journal Classification (ASJC) codes

  • Education
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems

Cite this

Yousefi, M., Hooshyar, D., Yousefi, M., Khaksar, W., Mohamed Sahari, K. S., & Ismail, F. B. (2016). An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study. In Y. Hendriana, A. Pranolo, A. Prahara, & D. P. Ismi (Eds.), Proceedings - 2015 International Conference on Science in Information Technology: Big Data Spectrum for Future Information Economy, ICSITech 2015 (pp. 95-99). [7407784] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSITech.2015.7407784
Yousefi, Moslem ; Hooshyar, Danial ; Yousefi, Milad ; Khaksar, Weria ; Mohamed Sahari, Khairul Salleh ; Ismail, Firas Basim. / An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting : A preliminary case study. Proceedings - 2015 International Conference on Science in Information Technology: Big Data Spectrum for Future Information Economy, ICSITech 2015. editor / Yana Hendriana ; Andri Pranolo ; Adhi Prahara ; Dewi Pramudi Ismi. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 95-99
@inproceedings{a528a2897a7f4671b334c88c28aa860a,
title = "An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study",
abstract = "Given the importance of an accurate wind speed forecasting for efficient utilization of wind farms, and the volatile nature of wind speed data including its non-linear and uncertain nature, the wind speed forecasting has remained an active field of research. In this study, the non-linearity of wind speed is tackled using artificial neural network and its uncertainty by wavelet transform. To avoid trial-and-error process for selection the ANN structure, the results of auto correlation factor (ACF) and partial auto correlation factor (PACF) on the historical wind speed data are employed. Instead of forecasting the time series directly, a set of better-behaved components of the data is achieved by decomposing the data using wavelet transform and are forecasted separately using a feedforward neural network. Finally, using an inverse wavelet transform, the future time series is reconstructed and the wind speed could be forecasted. The historical hourly wind speed from ABEI weather station in Idaho, United States is used for assessing the performance of the proposed algorithm. This data set is merely selected due to its availability. The data is divided to three parts of 50{\%}, 25{\%} and 25{\%} for training, testing and validation respectively. The testing part of data set will be merely used for assessing the performance of the neural network which guarantees that only unseen data is used to evaluate the forecasting performance of the network. On the other hand, validation data could be used for parameter-setting of the network if required. The results shows that using wavelet transform can enhance the forecasting accuracy when it is compared with a regular neural network prediction algorithm.",
author = "Moslem Yousefi and Danial Hooshyar and Milad Yousefi and Weria Khaksar and {Mohamed Sahari}, {Khairul Salleh} and Ismail, {Firas Basim}",
year = "2016",
month = "2",
day = "16",
doi = "10.1109/ICSITech.2015.7407784",
language = "English",
pages = "95--99",
editor = "Yana Hendriana and Andri Pranolo and Adhi Prahara and Ismi, {Dewi Pramudi}",
booktitle = "Proceedings - 2015 International Conference on Science in Information Technology",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Yousefi, M, Hooshyar, D, Yousefi, M, Khaksar, W, Mohamed Sahari, KS & Ismail, FB 2016, An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study. in Y Hendriana, A Pranolo, A Prahara & DP Ismi (eds), Proceedings - 2015 International Conference on Science in Information Technology: Big Data Spectrum for Future Information Economy, ICSITech 2015., 7407784, Institute of Electrical and Electronics Engineers Inc., pp. 95-99, International Conference on Science in Information Technology, ICSITech 2015, Yogyakarta, Indonesia, 27/10/15. https://doi.org/10.1109/ICSITech.2015.7407784

An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting : A preliminary case study. / Yousefi, Moslem; Hooshyar, Danial; Yousefi, Milad; Khaksar, Weria; Mohamed Sahari, Khairul Salleh; Ismail, Firas Basim.

Proceedings - 2015 International Conference on Science in Information Technology: Big Data Spectrum for Future Information Economy, ICSITech 2015. ed. / Yana Hendriana; Andri Pranolo; Adhi Prahara; Dewi Pramudi Ismi. Institute of Electrical and Electronics Engineers Inc., 2016. p. 95-99 7407784.

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

TY - GEN

T1 - An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting

T2 - A preliminary case study

AU - Yousefi, Moslem

AU - Hooshyar, Danial

AU - Yousefi, Milad

AU - Khaksar, Weria

AU - Mohamed Sahari, Khairul Salleh

AU - Ismail, Firas Basim

PY - 2016/2/16

Y1 - 2016/2/16

N2 - Given the importance of an accurate wind speed forecasting for efficient utilization of wind farms, and the volatile nature of wind speed data including its non-linear and uncertain nature, the wind speed forecasting has remained an active field of research. In this study, the non-linearity of wind speed is tackled using artificial neural network and its uncertainty by wavelet transform. To avoid trial-and-error process for selection the ANN structure, the results of auto correlation factor (ACF) and partial auto correlation factor (PACF) on the historical wind speed data are employed. Instead of forecasting the time series directly, a set of better-behaved components of the data is achieved by decomposing the data using wavelet transform and are forecasted separately using a feedforward neural network. Finally, using an inverse wavelet transform, the future time series is reconstructed and the wind speed could be forecasted. The historical hourly wind speed from ABEI weather station in Idaho, United States is used for assessing the performance of the proposed algorithm. This data set is merely selected due to its availability. The data is divided to three parts of 50%, 25% and 25% for training, testing and validation respectively. The testing part of data set will be merely used for assessing the performance of the neural network which guarantees that only unseen data is used to evaluate the forecasting performance of the network. On the other hand, validation data could be used for parameter-setting of the network if required. The results shows that using wavelet transform can enhance the forecasting accuracy when it is compared with a regular neural network prediction algorithm.

AB - Given the importance of an accurate wind speed forecasting for efficient utilization of wind farms, and the volatile nature of wind speed data including its non-linear and uncertain nature, the wind speed forecasting has remained an active field of research. In this study, the non-linearity of wind speed is tackled using artificial neural network and its uncertainty by wavelet transform. To avoid trial-and-error process for selection the ANN structure, the results of auto correlation factor (ACF) and partial auto correlation factor (PACF) on the historical wind speed data are employed. Instead of forecasting the time series directly, a set of better-behaved components of the data is achieved by decomposing the data using wavelet transform and are forecasted separately using a feedforward neural network. Finally, using an inverse wavelet transform, the future time series is reconstructed and the wind speed could be forecasted. The historical hourly wind speed from ABEI weather station in Idaho, United States is used for assessing the performance of the proposed algorithm. This data set is merely selected due to its availability. The data is divided to three parts of 50%, 25% and 25% for training, testing and validation respectively. The testing part of data set will be merely used for assessing the performance of the neural network which guarantees that only unseen data is used to evaluate the forecasting performance of the network. On the other hand, validation data could be used for parameter-setting of the network if required. The results shows that using wavelet transform can enhance the forecasting accuracy when it is compared with a regular neural network prediction algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84966508437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966508437&partnerID=8YFLogxK

U2 - 10.1109/ICSITech.2015.7407784

DO - 10.1109/ICSITech.2015.7407784

M3 - Conference contribution

SP - 95

EP - 99

BT - Proceedings - 2015 International Conference on Science in Information Technology

A2 - Hendriana, Yana

A2 - Pranolo, Andri

A2 - Prahara, Adhi

A2 - Ismi, Dewi Pramudi

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Yousefi M, Hooshyar D, Yousefi M, Khaksar W, Mohamed Sahari KS, Ismail FB. An artificial neural network hybrid with wavelet transform for short-term wind speed forecasting: A preliminary case study. In Hendriana Y, Pranolo A, Prahara A, Ismi DP, editors, Proceedings - 2015 International Conference on Science in Information Technology: Big Data Spectrum for Future Information Economy, ICSITech 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 95-99. 7407784 https://doi.org/10.1109/ICSITech.2015.7407784