Research Article
BibTex RIS Cite

İstatistiksel metotlar ve yapay sinir ağları kullanarak kısa dönem çok adımlı rüzgâr hızı tahmini

Year 2018, Volume: 22 Issue: 1, 24 - 38, 01.02.2018
https://doi.org/10.16984/saufenbilder.305224

Abstract

Bu çalışmada TÜBİTAK T60 ulusal gözlem evi
meteoroloji istasyonunun 2016 yılı nisan ayı içerisinde yaptığı gözlem
sonuçları PHP programlama dili kullanılarak web sitesi üzerinden derlenmiştir.
Elde edilen rüzgâr hızı verileri istatistiksel ve yapay sinir ağı metotları
kullanılarak incelenmiş ve meydana getirilen zaman serisi üzerinden ileriye
yönelik rüzgâr hızı kestirimlerinde bulunulmuştur. Yapılan hesaplamalar ve
gerçek veriler ile kıyaslamalar sonucunda incelenen ARIMA modelleri ve yapay
sinir ağları arasında belirgin bir hata oranı farkı görülmüştür. Literatürde
yer alan rüzgâr hızı tahmin çalışmaları genellikle sadece tek adım tahmin
başarısı üzerinde yoğunlaşırken, önerilen çalışmada sık kullanılan tahmin
metotlarının ileriye dönük 12 adım seviyesinde ayrıntılı değerlendirilmeleri
gerçekleştirilmiştir.

References

  • [1] A. Kerem, I. Kirbas, and A. Saygın, “Performance Analysis of Time Series Forecasting Models for Short Term Wind Speed Prediction,” presented at the International Conference on Engineering and Natural Sciences (ICENS), 2016, pp. 2733–2739. [2] İ. Kırbaş and A. Kerem, “Short-Term Wind Speed Prediction Based on Artificial Neural Network Models,” Meas. Control, vol. 49, no. 6, Jul. 2016. [3] M. Narayana, G. Putrus, M. Jovanovic, and P. S. Leung, “Predictive control of wind turbines by considering wind speed forecasting techniques,” in 2009 44th International Universities Power Engineering Conference (UPEC), 2009, pp. 1–4. [4] Z. D. Grève et al., “Impact of the geographical correlation between wind speed time series on reliability indices in power system studies,” in 2016 IEEE International Energy Conference (ENERGYCON), 2016, pp. 1–6. [5] M. Lydia and S. S. Kumar, “A comprehensive overview on wind power forecasting,” in 2010 Conference Proceedings IPEC, 2010, pp. 268–273. [6] J. Zhong, Y. Hou, and F. F. Wu, “Wind power forecasting and integration to power grids,” presented at the The 2010 International Conference on Green Circuits and Systems (ICGCS), Shanghai, China, 2010, pp. 555–560. [7] M. Khanna, N. K. Srinath, and J. K. Mendiratta, “Feature Extraction of Time Series Data for Wind Speed Power Generation,” in 2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016, pp. 169–173. [8] D. R. Chandra, M. S. Kumari, and M. Sydulu, “A detailed literature review on wind forecasting,” in Power, Energy and Control (ICPEC), 2013 International Conference on, 2013, pp. 630–634. [9] S. S. Soman, H. Zareipour, O. Malik, and P. Mandal, “A review of wind power and wind speed forecasting methods with different time horizons,” in North American Power Symposium 2010, NAPS 2010, 2010. [10] D. R. Chandra, M. S. Kumari, and M. Sydulu, “A detailed literature review on wind forecasting,” in Power, Energy and Control (ICPEC), 2013 International Conference on, 2013, pp. 630–634. [11] M. Bhaskar, A. Jain, and N. V. Srinath, “Wind speed forecasting: Present status,” in 2010 International Conference on Power System Technology, 2010, pp. 1–6. [12] “TÜBİTAK Ulusal Gözlem Evi,” TÜBİTAK Ulusal Gözlem Evi, 2017. [Online]. Available: http://tug.tubitak.gov.tr/tr/teleskoplar/t60-0. [Accessed: 03-Mar-2017]. [13] U. Firat, S. N. Engin, M. Saraclar, and A. B. Ertuzun, “Wind Speed Forecasting Based on Second Order Blind Identification and Autoregressive Model,” in Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on, 2010, pp. 686–691. [14] S. Rajagopalan and S. Santoso, “Wind power forecasting and error analysis using the autoregressive moving average modeling,” in 2009 IEEE Power Energy Society General Meeting, 2009, pp. 1–6. [15] K. Yunus, T. Thiringer, and P. Chen, “ARIMA-Based Frequency-Decomposed Modeling of Wind Speed Time Series,” IEEE Trans. Power Syst., vol. 31, no. 4, pp. 2546–2556, Jul. 2016. [16] I. Khandelwal, R. Adhikari, and G. Verma, “Time Series Forecasting Using Hybrid ARIMA and ANN Models Based on DWT Decomposition,” Procedia Comput. Sci., vol. 48, pp. 173–179, 2015. [17] H. Vergil and F. Özkan, “Döviz kurları öngörüsünde satınalma gücü paritesi ve ARIMA modelleri: Trkiye Örneği,” İMKB Derg., vol. 9, no. 35, pp. 41–55, 1997. [18] A. M. Foley, P. G. Leahy, and E. J. McKeogh, “Wind power forecasting & prediction methods,” in 2010 9th International Conference on Environment and Electrical Engineering, 2010, pp. 61–64. [19] J. C. Palomares-Salas, J. J. G. de la Rosa, J. G. Ramiro, J. Melgar, A. Aguera, and A. Moreno, “ARIMA vs. Neural networks for wind speed forecasting,” in 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 2009, pp. 129–133. [20] O. Kaynar, S. Taştan, and F. Demirkoparan, “Yapay Sinir Ağları ile Doğalgaz Tüketim Tahmini,” Atatürk Üniversitesi İİBF Derg., no. 10. Ekonometri ve İstatistik Sempozyumu Özel Sayısı, pp. 463–474, 2011. [21] O. Kaynar and S. Taştan, “Zaman serisi analizinde MLP yapay sinir ağları ve ARIMA modelinin karşılaştırılması,” Erciyes Üniversitesi Iktis. Ve İdari Bilim. Fakültesi Derg., no. 33, pp. 161–172, 2009. [22] E. İslamoğlu, “Aralık Değerli Zaman Serilerinde Kullanılan Modelleme Teknikleri,” EÜFBED Fen Bilim. Enstitüsü Derg., vol. 8, no. 2, pp. 178–193, 2015. [23] R. Ak, O. Fink, and E. Zio, “Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction,” IEEE Trans. Neural Netw. Learn. Syst., vol. 27, no. 8, pp. 1734–1747, Aug. 2016. [24] İ. Kırbaş, “Short‐Term Multı‐Step Wind Speed Prediction Using Statistical Methods And Artificial Neural Networks,” presented at the International Science and Technology Conference, 2016, vol. 1, p. 1064.

Short-term multi-step wind speed prediction using statistical methods and artificial neural networks

Year 2018, Volume: 22 Issue: 1, 24 - 38, 01.02.2018
https://doi.org/10.16984/saufenbilder.305224

Abstract

The results of the observations made by TUBITAK
T60 national observation house meteorological station in April, 2016 were
compiled on this website using the PHP programming language. Obtained wind
speed data were analysed using statistical and artificial neural network
methods and predicted wind speed predictions over the time series brought to
the field. There is a significant difference in error rates between the ARIMA
models and the artificial neural networks examined as a result of comparisons
with the calculated calculations and actual data. While the wind speed
estimation studies in the literature generally focus only on single step
prediction success, detailed evaluation of commonly used estimation methods at
the prospective 12 step level has been carried out.

References

  • [1] A. Kerem, I. Kirbas, and A. Saygın, “Performance Analysis of Time Series Forecasting Models for Short Term Wind Speed Prediction,” presented at the International Conference on Engineering and Natural Sciences (ICENS), 2016, pp. 2733–2739. [2] İ. Kırbaş and A. Kerem, “Short-Term Wind Speed Prediction Based on Artificial Neural Network Models,” Meas. Control, vol. 49, no. 6, Jul. 2016. [3] M. Narayana, G. Putrus, M. Jovanovic, and P. S. Leung, “Predictive control of wind turbines by considering wind speed forecasting techniques,” in 2009 44th International Universities Power Engineering Conference (UPEC), 2009, pp. 1–4. [4] Z. D. Grève et al., “Impact of the geographical correlation between wind speed time series on reliability indices in power system studies,” in 2016 IEEE International Energy Conference (ENERGYCON), 2016, pp. 1–6. [5] M. Lydia and S. S. Kumar, “A comprehensive overview on wind power forecasting,” in 2010 Conference Proceedings IPEC, 2010, pp. 268–273. [6] J. Zhong, Y. Hou, and F. F. Wu, “Wind power forecasting and integration to power grids,” presented at the The 2010 International Conference on Green Circuits and Systems (ICGCS), Shanghai, China, 2010, pp. 555–560. [7] M. Khanna, N. K. Srinath, and J. K. Mendiratta, “Feature Extraction of Time Series Data for Wind Speed Power Generation,” in 2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016, pp. 169–173. [8] D. R. Chandra, M. S. Kumari, and M. Sydulu, “A detailed literature review on wind forecasting,” in Power, Energy and Control (ICPEC), 2013 International Conference on, 2013, pp. 630–634. [9] S. S. Soman, H. Zareipour, O. Malik, and P. Mandal, “A review of wind power and wind speed forecasting methods with different time horizons,” in North American Power Symposium 2010, NAPS 2010, 2010. [10] D. R. Chandra, M. S. Kumari, and M. Sydulu, “A detailed literature review on wind forecasting,” in Power, Energy and Control (ICPEC), 2013 International Conference on, 2013, pp. 630–634. [11] M. Bhaskar, A. Jain, and N. V. Srinath, “Wind speed forecasting: Present status,” in 2010 International Conference on Power System Technology, 2010, pp. 1–6. [12] “TÜBİTAK Ulusal Gözlem Evi,” TÜBİTAK Ulusal Gözlem Evi, 2017. [Online]. Available: http://tug.tubitak.gov.tr/tr/teleskoplar/t60-0. [Accessed: 03-Mar-2017]. [13] U. Firat, S. N. Engin, M. Saraclar, and A. B. Ertuzun, “Wind Speed Forecasting Based on Second Order Blind Identification and Autoregressive Model,” in Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on, 2010, pp. 686–691. [14] S. Rajagopalan and S. Santoso, “Wind power forecasting and error analysis using the autoregressive moving average modeling,” in 2009 IEEE Power Energy Society General Meeting, 2009, pp. 1–6. [15] K. Yunus, T. Thiringer, and P. Chen, “ARIMA-Based Frequency-Decomposed Modeling of Wind Speed Time Series,” IEEE Trans. Power Syst., vol. 31, no. 4, pp. 2546–2556, Jul. 2016. [16] I. Khandelwal, R. Adhikari, and G. Verma, “Time Series Forecasting Using Hybrid ARIMA and ANN Models Based on DWT Decomposition,” Procedia Comput. Sci., vol. 48, pp. 173–179, 2015. [17] H. Vergil and F. Özkan, “Döviz kurları öngörüsünde satınalma gücü paritesi ve ARIMA modelleri: Trkiye Örneği,” İMKB Derg., vol. 9, no. 35, pp. 41–55, 1997. [18] A. M. Foley, P. G. Leahy, and E. J. McKeogh, “Wind power forecasting & prediction methods,” in 2010 9th International Conference on Environment and Electrical Engineering, 2010, pp. 61–64. [19] J. C. Palomares-Salas, J. J. G. de la Rosa, J. G. Ramiro, J. Melgar, A. Aguera, and A. Moreno, “ARIMA vs. Neural networks for wind speed forecasting,” in 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 2009, pp. 129–133. [20] O. Kaynar, S. Taştan, and F. Demirkoparan, “Yapay Sinir Ağları ile Doğalgaz Tüketim Tahmini,” Atatürk Üniversitesi İİBF Derg., no. 10. Ekonometri ve İstatistik Sempozyumu Özel Sayısı, pp. 463–474, 2011. [21] O. Kaynar and S. Taştan, “Zaman serisi analizinde MLP yapay sinir ağları ve ARIMA modelinin karşılaştırılması,” Erciyes Üniversitesi Iktis. Ve İdari Bilim. Fakültesi Derg., no. 33, pp. 161–172, 2009. [22] E. İslamoğlu, “Aralık Değerli Zaman Serilerinde Kullanılan Modelleme Teknikleri,” EÜFBED Fen Bilim. Enstitüsü Derg., vol. 8, no. 2, pp. 178–193, 2015. [23] R. Ak, O. Fink, and E. Zio, “Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction,” IEEE Trans. Neural Netw. Learn. Syst., vol. 27, no. 8, pp. 1734–1747, Aug. 2016. [24] İ. Kırbaş, “Short‐Term Multı‐Step Wind Speed Prediction Using Statistical Methods And Artificial Neural Networks,” presented at the International Science and Technology Conference, 2016, vol. 1, p. 1064.
There are 1 citations in total.

Details

Subjects Computer Software
Journal Section Research Articles
Authors

İsmail Kırbaş 0000-0002-1206-8294

Publication Date February 1, 2018
Submission Date April 10, 2017
Acceptance Date August 1, 2017
Published in Issue Year 2018 Volume: 22 Issue: 1

Cite

APA Kırbaş, İ. (2018). Short-term multi-step wind speed prediction using statistical methods and artificial neural networks. Sakarya University Journal of Science, 22(1), 24-38. https://doi.org/10.16984/saufenbilder.305224
AMA Kırbaş İ. Short-term multi-step wind speed prediction using statistical methods and artificial neural networks. SAUJS. February 2018;22(1):24-38. doi:10.16984/saufenbilder.305224
Chicago Kırbaş, İsmail. “Short-Term Multi-Step Wind Speed Prediction Using Statistical Methods and Artificial Neural Networks”. Sakarya University Journal of Science 22, no. 1 (February 2018): 24-38. https://doi.org/10.16984/saufenbilder.305224.
EndNote Kırbaş İ (February 1, 2018) Short-term multi-step wind speed prediction using statistical methods and artificial neural networks. Sakarya University Journal of Science 22 1 24–38.
IEEE İ. Kırbaş, “Short-term multi-step wind speed prediction using statistical methods and artificial neural networks”, SAUJS, vol. 22, no. 1, pp. 24–38, 2018, doi: 10.16984/saufenbilder.305224.
ISNAD Kırbaş, İsmail. “Short-Term Multi-Step Wind Speed Prediction Using Statistical Methods and Artificial Neural Networks”. Sakarya University Journal of Science 22/1 (February 2018), 24-38. https://doi.org/10.16984/saufenbilder.305224.
JAMA Kırbaş İ. Short-term multi-step wind speed prediction using statistical methods and artificial neural networks. SAUJS. 2018;22:24–38.
MLA Kırbaş, İsmail. “Short-Term Multi-Step Wind Speed Prediction Using Statistical Methods and Artificial Neural Networks”. Sakarya University Journal of Science, vol. 22, no. 1, 2018, pp. 24-38, doi:10.16984/saufenbilder.305224.
Vancouver Kırbaş İ. Short-term multi-step wind speed prediction using statistical methods and artificial neural networks. SAUJS. 2018;22(1):24-38.