Afyonkarahisar bölgesi şartlarında bulut hareketlerinin gökyüzü sınıfları tabanlı tahmini

Year 2022, , 68 - 76, 14.01.2022

Ardan Hüseyin Eşlik , Emre Akarslan , Fatih Onur Hocaoğlu

https://doi.org/10.28948/ngumuh.872533

Abstract

Güneş enerjisinin kesikli ve değişken yapıda olması verimli kullanımını oldukça zorlaştırmaktadır. Bu kesiklilik ve değişkenliğin oluşmasındaki en büyük etmen bulut hareketleridir. Gerçekleştirilen çalışmada, bulutların takibi ve hareketlerinin tahmini için akış tabanlı bir algoritmanın performansı Afyonkarahisar bölgesi şartlarında araştırılmıştır. Bu amaç doğrultusunda Afyon Kocatepe Üniversitesi Mühendislik Fakültesine bir dijital kamera yerleştirilmiş ve belirli aralıklarla gökyüzü görüntüleri kaydedilmiştir. Elde edilen görüntüler üzerinde bulut ve gökyüzü sınıflandırmaları gerçekleştirilmiştir. Bulutların takibinin gerçekleştirilebilmesi için takibe en uygun köşe noktaları Shi-Tomasi algoritması kullanılarak belirlenmiştir. Bulunan köşe noktaları Lucas-Kanade optik akış algoritması kullanılarak sıralı görüntüler üzerinde takip edilmiş ve doğrusal regresyon yardımıyla bulutların hareket yön ve hız bilgilerine ulaşılmıştır. Son olarak, ilgili hareket yön ve hız bilgilerinin kullanılmasıyla 340 saniye zaman ufku için 20 saniye çözünürlüğünde bulut hareketleri tahmin edilmiştir. Çalışmada kullanılan veri seti için %5.88’lik hata performansı ile tahminler gerçekleştirilmiştir. Yöntem, bulut hareketi tahmininde yüksek potansiyele sahip olduğunu göstermiştir.

Keywords

Bulut Hareketi Takibi, Bulut Hareketi Tahmini, Shi-Tomasi Algoritması, Lucas-Kanade Optik Akış, Güneş Enerjisi

Supporting Institution

Afyon Kocatepe Üniversitesi Bilimsel Araştırma Projeleri Birimi

Project Number

20.FENBİL.25

Thanks

Bu çalışma, Afyon Kocatepe Üniversitesi Bilimsel Araştırma Projeleri birimi tarafından 20.FENBİL.25 no’lu proje kapsamında desteklenmiştir. Desteklerinden dolayı Afyon Kocatepe Üniversitesi Bilimsel Araştırma Projeleri birimine teşekkür ederiz.

Sky Class Based Prediction of Cloud Movements in Afyonkarahisar Region Conditions

Abstract

The intermittent and variable nature of solar energy makes its efficient use very difficult. The biggest factor in this intermittency and variability is cloud movements. In the study, the performance of a flow-based algorithm for tracking and predicting the movements of clouds was investigated under the conditions of the Afyonkarahisar region. For this purpose, a digital camera was installed in Afyon Kocatepe University Engineering Faculty and sky images were recorded at regular intervals. Cloud and sky classifications were made on the images obtained. In order to follow the clouds, the most suitable corner points for tracking were determined using the Shi-Tomasi algorithm. The corner points found were followed on sequential images using the Lucas-Kanade optical flow algorithm and the motion direction and speed information of the clouds were obtained with the help of linear regression. Finally, using the relevant motion direction and velocity information, cloud motions with a resolution of 20 seconds for a time horizon of 340 seconds are estimated. For the data set used in the study, estimates were made with an error performance of 5.88%. The method has shown that it has a high potential in cloud motion prediction.

Keywords

Cloud Motion Tracking, Cloud Motion Prediction, Shi-Tomasi Algorithm, Lucas-Kanade Optical Flow, Solar Energy

Project Number

20.FENBİL.25

References

• V. Kostylev and A. Pavlovski, Solar power forecasting performance–towards industry standards. 1st international workshop on the integration of solar power into power systems,pp.1-8, Aarhus, Denmark, 2011.
• L. Bird, M. Milligan and D. Lew, Integrating variable renewable energy: challenges and solutions. National Renewable Energy Laboratory (NREL), Golden Colorado, United States, Technical Report NREL/TP-6A20-60451, 2013. https://doi.org/10.2172/1097911
• L. M. Aguiar, B. Pereira, P. Lauret, F. Díaz and M. David, Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting. Renew. Energy, 97, 599–610, 2016. https://doi.org/10.1016/j.renene.2016.06. 018
• H. M. Diagne, P. Lauret and M. David, Solar irradiation forecasting: state-of-the-art and proposition for future developments for small-scale insular grids. WREF 2012-World Renewable Energy Forum, May 2012.
• J. Alonso-Montesinos and F. J. Batlles, The use of a sky camera for solar radiation estimation based on digital image processing. Energy, 90, 377–386, 2015. https://doi.or g /10.1016/j.energy.2015.07.028
• C. W. Chow, B. Urquhart, M. Lave, A. Dominguez, J. Kleissl, J. Shields and B. Washom, Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed. Solar Energy, 85 (11), 2881–2893, December, 2011. https://doi.org/10.1016/j.solener. 2011.08 .025
• M. Cervantes, H. Krishnaswami, W. Richardson, and R. Vega, Utilization of low cost, sky-imaging technology for ırradiance forecasting of distributed solar generation. 2016 IEEE Green Technologies Conference (GreenTech), pp. 142–146, Kansas City, United States, 2016. https: //doi.org/10.1109/GreenTech.2016.33
• P. Wood-Bradley, J. Zapata and J. Pye, Cloud tracking with optical flow for short-term solar forecasting. Proceedings of the 50th Conference of the Australian Solar Energy Society, Melbourne, 2012.
• R. Chauvin, J. Nou, S. Thil, A. Traoré and S. Grieu, Cloud detection methodology based on a sky-imaging system. Energy Procedia, 69, 1970–1980, 2015. https://doi .org/10.1016/j.egypro.2015.03.198
• J. Alonso, A. Ternero, F. J. Batlles, G. López, J. Rodríguez and J. I. Burgaleta, Prediction of cloudiness in short time periods using techniques of remote sensing and image processing. Energy Procedia, 49, 2280–2289, 2014. https://doi.org/10.1016/j.egy pro.2014.03.241
• F. J. Batlles, J. Alonso and G. López, Cloud cover forecasting from METEOSAT data. Energy Procedia, 57, 1317–1326, 2014. https://doi.org/10.1016/j. egypro.2014.10 .122
• J. A. Leese, C. S. Novak and V. Ray Taylor, The determination of cloud pattern motions from geosynchronous satellite image data. Pattern Recognit, 2(4), 279–292, December 1970. https://doi.org/10.1016/0031-32 03(70)90018-X
• R. Chauvin, J. Nou, S. Thil and S. Grieu, Cloud motion estimation using a sky imager. AIP Conference Proceedings, 1734(1), 150003, 2016. https://doi.org/10.10 63/1.4949235
• J. Alonso and F. J. Batlles, Short and medium-term clou diness forecasting using remote sensing techniques and sky camera imagery. Energy, 73, 890–897, 2014. https://doi .org/10.1016/j.energy.2014. 06.101
• B. Lucas and T. Kanade, An iterative image registration technique with an application to stereo vision. Proceedings DARPA Image Understanding Workshop, pp. 121-130, April 1981.
• P. Tuominen and M. Tuononen, Cloud detection and movement estimation based on sky camera images using neural networks and the Lucas-Kanade method. AIP Conference Proceedings, 1850(1), 140020, 2017. https://doi. org/ 10.1063/1.4984528
• H. I. Ben Idder and N. Laachfoubi, Cloud motion estimation in satellite image sequences by tracking skeleton critical points using lucas-kanade method. 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), pp. 178–183, 2016. https://doi.org/ 10.1109/CGi V.2016.42
• S. Dev, F. M. Savoy, Y. H. Lee and S. Winkler, Short-term prediction of localized cloud motion using ground-based sky imagers. IEEE Region 10 Annual International Conference, Proceedings/TENCON, 0, 2563-2566, 2017. https://doi.org/ 10.1109/TEN CON.2016.78484 99
• J. Du, Q. Min, P. Zhang, J. Guo, J. Yang and B. Yin, Short-term solar irradiance forecasts using sky images and radiative transfer model. Energies, 11(5), 1107, May 2018. https://doi.org/10.3390/ en11051107
• G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library, O’Reilly Media Inc, 2008.
• A. Heinle, A. Macke and A. Srivastav, Automatic cloud classification of whole sky images. Atmospheric Measurement Techniques, 3(3), 557–567, 2010. https://doi. org/ 10.5194/amt-3-557-2010
• H. Huang, J. Xu, Z. Peng, S. Yoo, D. Yu, D. Huang and H. Qin, Cloud motion estimation for short term solar irradiation prediction. 2013 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 696–701, 2013. https: //doi.org/ 10.1109/SmartGridComm. 2013.66880 40
• J. Shi and C. Tomasi, Good features to track. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 593–600, 1994. https://doi.org/ 10.1109/CVPR.1994. 3237 94
• C. Harris and M. Stephens, A combined corner and edge detector. Alvey vision conference, 15(50), pp. 10-5244, 1988.
• J.L. Barron, D.J. Fleet and S.S. Beauchemin, Performance of optical flow techniques. International journal of computer vision, 12(1), 43–77,1994. https://doi.org/10.10 07/BF 01420984
• A. S. Keçeli ve A. Kaya, Optik akış görüntüsü ve bi-lstm ile şiddet içeren hareketlerin sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi,14, 204–208, 2018. https://doi.org/10.31590/ejosat.460257
• Z. El Jaouhari, Y. Zaz and L. Masmoudi, Cloud tracking from whole-sky ground-based images. 3rd International Renewable and Sustainable Energy Conference (IRSEC), pp. 1-5, 2015. https://doi.org/ 10. 1109/IRSEC.20 15.7455105