Research Article
Rüzgar Hızı Verilerinin Modellenmesinde İki ve Çok Boyutlu Filtrelerin Performaslarının Karşılaştırılması
Abstract
Teknolojinin gelişimi, devam eden nüfus artışı gibi nedenler enerji ihtiyacının sürekli artmasına neden olmaktadır. Bununla beraber tükenen fosil yakıtlar, hem farklı kaynaklardan enerji üretimini zorunlu kılmış, hem de sürdürülebilir kaynaklardan enerji üretimini zorunlu hale getirilmiştir. Rüzgardan enerji üreten sistemler hem sürdürülebilir hem de çevre dostu olmaları sebebi ile yaygın kullanım alanına sahiptir. Bir rüzgar türbiniden üretilecek enerji o bölgedeki rüzgar hızı ile doğrudan bağlantılıdır. Bu çalışmada, Doğrusal Tahmin Filtreleri tasarlanarak, Afyon Kocatepe Üniversitesi kampüs alanına tesis edilmiş bir meteoroloji istasyonundan 10 dakikalık periyotlarda toplanan ortalama rüzgar hızı verilerinin başarılı bir şekilde modellenmesi hedeflenmiştir. Çalışmada hem iki boyutlu hem de çok boyutlu doğrusal tahmin filtreleri tasarlanmıştır. Gerçekleştirilen çalışmada kısa dönem rüzgar hızı verilerinin tahmini amacıyla geçmişte ölçülmüş; rüzgar hızı, rüzgar hızı-sıcaklık ve rüzgar hızı-sıcaklık-basınç verilerini kullanan farklı doğrusal tahmin filtreleri tasarlarnmıştır. Filtrelerden elde edilen sonuçlar gözönüne alınarak, hem doğrusal tahmin filtrelerinin kısa dönem rüzgar hızı modellemesindeki başarısı incelenmiş, hem de iki boyut ve çok boyutlu doğrusal tahmin filtrelerinin başarısı birbirleri ile karşılaştırılmıştır. Elde edilen sonuçlar hem iki boyutlu hem de çok boyutlu doğrusal tahmin filtrelerin kısa dönem rüzgar hızı modellemedeki başarısını ortaya koymuştur.
References
- Akarslan E., Hocaoglu F.O., Edizkan R. "A novel M-D (multi-dimensional) linear prediction filter approach for hourly solar radiation forecasting". Energy 73, 978–986, 2014.
- Akarslan E., Hocaoglu F.O. "An application of MDLPF models for solar radiation forecasting". International Journal of Smart Grid and Clean Energy 4(4), 299-304, 2015.
- Akarslan E., Hocaoglu F.O., Edizkan R. " Novel short term solar irradiance forecasting models". Renewable Energy 123, 58–66, 2018.
- Akarslan E., and Hocaoglu F.O. “A Novel Method Based on Similarity for Hourly Solar Irradiance Forecasting.” Renewable Energy 112, 337-346, 2017.
- Qinkai H., Hao Z., Hu T., and Chu F. “Non-Parametric Models for Joint Probabilistic Distributions of Wind Speed and Direction Data.” Renewable Energy 126 (October): 1032–42, 2018.
- Hocaoğlu, F.O., Gerek O.N., and Kurban M. “Hourly Solar Radiation Forecasting Using Optimal Coefficient 2-D Linear Filters and Feed-Forward Neural Networks.” Solar Energy 82 (8): 714–26, 2008.
- Seckin K., Altan A., Sarac Z., and Hacioglu R. “Prediction of Wind Speed with Non-Linear Autoregressive (NAR) Neural Networks.” In 2017 25th Signal Processing and Communications Applications Conference (SIU), 1–4. IEEE, 2017.
- Bayram K., Recebli̇ Z., Özkaymak M. “Stokastik Modellerle Rüzgar Hızı Tahmini; Karabük Örneği.” Accessed September 22, 2018. http://www.isites.info/PastConferences/ISITES2014/ISITES2014/papers/A12-ISITES2014ID128.pdf.
- Hui l., Mi X., and Li Y. “An Experimental Investigation of Three New Hybrid Wind Speed Forecasting Models Using Multi-Decomposing Strategy and ELM Algorithm.” Renewable Energy 123 (August): 694–705. 2018.
- Angeliki L., Howell S., Johnson P., and Duck P. “Stochastic Wind Speed Modelling for Estimation of Expected Wind Power Output.” Applied Energy 228 (October): 1328–40, 2018.
- Jinrui M., Fouladirad M., and Grall A. “Flexible Wind Speed Generation Model: Markov Chain with an Embedded Diffusion Process.” Energy 164 (December): 316–28, 2018.
- Masseran N. “Integrated Approach for the Determination of an Accurate Wind-Speed Distribution Model.” Energy Conversion and Management 173 (October): 56–64, 2018.
- Nascimento C., do H., Lucio P.S., Verçosa Leal Junior J.B., and Marques de Carvalho P.C. “A Hybrid Model Based on Time Series Models and Neural Network for Forecasting Wind Speed in the Brazilian Northeast Region.” Sustainable Energy Technologies and Assessments 28 (August): 65–72, 2018.
- Nastos, P.T., Paliatsos A.G., Koukouletsos K.V., Larissi I.K., and Moustris K.P. “Artificial Neural Networks Modeling for Forecasting the Maximum Daily Total Precipitation at Athens, Greece.” Atmospheric Research 144 (July): 141–50, 2014.
- Pobočíková I., Sedliačková Z., and Michalková M. “Application of Four Probability Distributions for Wind Speed Modeling.” Procedia Engineering 192 (January): 713–18, 2017.
- Tan Z., Zhang H., Xu J., Wang J., Yu C., and Zhang J. “Photovoltaic Power Generation in China: Development Potential, Benefits of Energy Conservation and Emission Reduction.” Journal of Energy Engineering 138 (2): 73–86, 2012.
- Yilmaz V., and Çelik H.E. “Rüzgar Hızı Dağılımının Tahmin Edilmesi İçin İstatistiksel Bir Yaklaşım: Gelibolu Bölgesi Örneği.” Vol. 9. 2008. http://openaccess.dogus.edu.tr/bitstream/handle/11376/399/yılmaz.pdf?sequence=1&isAllowed=y.
Comparison of Performance of Two and Multi-Dimensional Linear Prediction Filters for Modeling Wind Speed Data
Abstract
The reasons such as; development on the technology, continuing increase in population etc. has caused continues increase on the demand of energy. Nevertheless, depleted fossil fuels have forced the
production of energy from different sources as well as the generation of energy from sustainable sources. Wind energy generation systems are both sustainable and environmentally friendly and are an
important source of production. The energy to be generated from a wind turbine is directly related to the wind speed in that region. In this study, it is aimed to model the average wind speed data collected
in ten minutes period from a meteorological station at the campus area of Afyon Kocatepe University of Turkey, successfully by designing linear prediction filters. Both two-dimensional and multidimensional linear prediction filters are used in the study. In this study, for the aim of prediction of short term wind speed data measured; wind speed, wind speed-temperature and wind speedtemperature-pressure data are employed and different filter templates have been built. Considering the results obtained from the filters, both the success of linear prediction filters on short-term wind speed modeling has been investigated and the successes of two-dimensional and multidimensional linear prediction filters have been compared. The results indicated that both the two-dimensional and the multi-dimensional linear prediction filters have been successful in modeling short-term wind speeds.
References
- Akarslan E., Hocaoglu F.O., Edizkan R. "A novel M-D (multi-dimensional) linear prediction filter approach for hourly solar radiation forecasting". Energy 73, 978–986, 2014.
- Akarslan E., Hocaoglu F.O. "An application of MDLPF models for solar radiation forecasting". International Journal of Smart Grid and Clean Energy 4(4), 299-304, 2015.
- Akarslan E., Hocaoglu F.O., Edizkan R. " Novel short term solar irradiance forecasting models". Renewable Energy 123, 58–66, 2018.
- Akarslan E., and Hocaoglu F.O. “A Novel Method Based on Similarity for Hourly Solar Irradiance Forecasting.” Renewable Energy 112, 337-346, 2017.
- Qinkai H., Hao Z., Hu T., and Chu F. “Non-Parametric Models for Joint Probabilistic Distributions of Wind Speed and Direction Data.” Renewable Energy 126 (October): 1032–42, 2018.
- Hocaoğlu, F.O., Gerek O.N., and Kurban M. “Hourly Solar Radiation Forecasting Using Optimal Coefficient 2-D Linear Filters and Feed-Forward Neural Networks.” Solar Energy 82 (8): 714–26, 2008.
- Seckin K., Altan A., Sarac Z., and Hacioglu R. “Prediction of Wind Speed with Non-Linear Autoregressive (NAR) Neural Networks.” In 2017 25th Signal Processing and Communications Applications Conference (SIU), 1–4. IEEE, 2017.
- Bayram K., Recebli̇ Z., Özkaymak M. “Stokastik Modellerle Rüzgar Hızı Tahmini; Karabük Örneği.” Accessed September 22, 2018. http://www.isites.info/PastConferences/ISITES2014/ISITES2014/papers/A12-ISITES2014ID128.pdf.
- Hui l., Mi X., and Li Y. “An Experimental Investigation of Three New Hybrid Wind Speed Forecasting Models Using Multi-Decomposing Strategy and ELM Algorithm.” Renewable Energy 123 (August): 694–705. 2018.
- Angeliki L., Howell S., Johnson P., and Duck P. “Stochastic Wind Speed Modelling for Estimation of Expected Wind Power Output.” Applied Energy 228 (October): 1328–40, 2018.
- Jinrui M., Fouladirad M., and Grall A. “Flexible Wind Speed Generation Model: Markov Chain with an Embedded Diffusion Process.” Energy 164 (December): 316–28, 2018.
- Masseran N. “Integrated Approach for the Determination of an Accurate Wind-Speed Distribution Model.” Energy Conversion and Management 173 (October): 56–64, 2018.
- Nascimento C., do H., Lucio P.S., Verçosa Leal Junior J.B., and Marques de Carvalho P.C. “A Hybrid Model Based on Time Series Models and Neural Network for Forecasting Wind Speed in the Brazilian Northeast Region.” Sustainable Energy Technologies and Assessments 28 (August): 65–72, 2018.
- Nastos, P.T., Paliatsos A.G., Koukouletsos K.V., Larissi I.K., and Moustris K.P. “Artificial Neural Networks Modeling for Forecasting the Maximum Daily Total Precipitation at Athens, Greece.” Atmospheric Research 144 (July): 141–50, 2014.
- Pobočíková I., Sedliačková Z., and Michalková M. “Application of Four Probability Distributions for Wind Speed Modeling.” Procedia Engineering 192 (January): 713–18, 2017.
- Tan Z., Zhang H., Xu J., Wang J., Yu C., and Zhang J. “Photovoltaic Power Generation in China: Development Potential, Benefits of Energy Conservation and Emission Reduction.” Journal of Energy Engineering 138 (2): 73–86, 2012.
- Yilmaz V., and Çelik H.E. “Rüzgar Hızı Dağılımının Tahmin Edilmesi İçin İstatistiksel Bir Yaklaşım: Gelibolu Bölgesi Örneği.” Vol. 9. 2008. http://openaccess.dogus.edu.tr/bitstream/handle/11376/399/yılmaz.pdf?sequence=1&isAllowed=y.
There are 17 citations in total.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Articles |
| Authors | |
| Publication Date | May 28, 2019 |
| Submission Date | October 1, 2018 |
| Published in Issue | Year 2019 Volume: 19 Issue: 1 |