Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Prediction of Day Ahead Hourly Solar Radiation by Meteorological Forecasting Supported Artificial Neural Network: A Case Study for Trabzon Province

Meteorolojik Tahmin Destekli Yapay Sinir Ağı ile Gün Öncesi Saatlik Güneş Işınımı Kestirimi: Trabzon ili Örneği

How to cite: Çevik S, Çakmak R, Altaş H. Prediction of day ahead hourly solar radiation by meteorological forecasting supported artificial neural network: a case study for trabzon province. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2018; 1(2): 87-92.

Full Text: PDF, in Turkish.

Total number of downloads: 945

Title: Prediction of Day Ahead Hourly Solar Radiation by Meteorological Forecasting Supported Artificial Neural Network: A Case Study for Trabzon Province

Abstract: Electricity generation from renewable energy sources is increased day by day. Accurate estimation of electricity generation from the renewable energy sources which have intermittent and variable characteristics is a requirement to ensure stable operation of the electrical grid. In this study, a multi-layer artificial neural network (ANN) system, which is supported by meteorological forecasting data, has been proposed to predict day ahead hourly solar radiation. In this context, the ANN system which operates by based on cause-effect relationship has been designed. In order to increase accuracy of the solar radiation prediction of the designed ANN, a similar day selection algorithm has been developed. A unique ANN has been constituted for each season by evaluating the seasons within itself. The designed ANN model has been designed, trained and tested in MATLAB simulation environment without using codes of the MATLAB ANN toolbox. Day ahead hourly solar radiation of Trabzon province has been predicted by the proposed ANN. The accuracy of the predictions has been evaluated by the mean absolute percentage error (MAPE), the root means squared error (RMSE), the mean absolute error (MAE) and the correlation coefficient (r) performance measures.

Keywords: Prediction of solar radiation; artificial neural networks; artificial intelligence; forecasting; Trabzon


Başlık: Meteorolojik Tahmin Destekli Yapay Sinir Ağı ile Gün Öncesi Saatlik Güneş Işınımı Kestirimi: Trabzon ili Örneği

Özet: Yenilenebilir enerji kaynaklarından elektrik üretimi her geçen gün artmaktadır. Elektik şebekesinin kararlı bir şekilde çalışmasını sağlamak için kesintili ve değişken karakteristiğe sahip olan yenilenebilir enerji kaynaklarından yapılacak olan üretimin doğru tahmin edilmesi gerekmektedir. Bu çalışmada gün öncesi saatlik güneş radyasyonunu tahmin etmek için meteorolojik tahmin verileri ile desteklenen çok katmanlı yapay sinir ağı (YSA) sistemi önerilmektedir. Bu bağlamda sebep sonuç ilişkisine dayalı olarak çalışan bir YSA sistemi tasarlanmıştır. Tasarlanan yapay sinir ağının yapacağı güneş ışınımı kestiriminin doğruluğunu arttırmak için benzer gün seçim algoritması geliştirilmiştir. Mevsimleri kendi içerisinde değerlendirerek, her mevsim için farklı bir yapay sinir ağı oluşturulmuştur. Tasarlanan YSA modeli, MATLAB benzetim programında MATLAB’ın YSA araç kutusunda bulunan kodlar kullanılmadan tasarlanmış, eğitilmiş ve test edilmiştir. Önerilen YSA sistemi kullanılarak Trabzon ili için gün öncesi saatlik güneş ışınımı tahmini yapılmıştır. Yapılan tahminlerin doğruluğu, ortalama mutlak yüzde hata (OMHY), karesel ortalama hata (KOH), ortalama mutlak hata (OMH) ve korelasyon katsayısı (r) performans ölçütleri ile değerlendirilmiştir.

Anahtar kelimeler: Güneş ışınımı kestirimi; yapay sinir ağları; yapay zeka; tahmin; Trabzon


Bibliography:
  • Farhangi H. The path of the smart grid. IEEE Power and Energy Magazine 2010; 8(1): 18-28.
  • Cakmak C, Altas IH. Scheduling of domestic shiftable loads via Cuckoo search optimization algorithm. In 2016 4th International Istanbul Smart Grid Congress and Fair (ICSG), 2016, Istanbul, Turkey, pp. 1-4.
  • Wan C, Zhao J, Song Y, Xu Z, Lin J, Hu Z. Photovoltaic and solar power forecasting for smart grid energy management. CSEE Journal of Power and Energy Systems 2015; 1(4): 38-46.
  • Liu J, Fang W, Zhang X, Yang C. An improved photovoltaic power forecasting model with the assistance of aerosol index data. IEEE Transactions on Sustainable Energy 2015; 6(2): 434-442.
  • Watetakarn S, Premrudeepreechacharn S. Forecasting of solar irradiance for solar power plants by artificial neural network. In 2015 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA), November 3-6, 2015, Bangkok, Thailand, pp. 1-5.
  • Grimaccia F, Mussetta M, Zich RE. Advanced predictive models towards PV energy integration in smart grid. 2012 IEEE International Conference on Fuzzy Systems, June 10-15, 2012, Brisbane, QLD, Australia, pp. 1-6.
  • Hocaoglu FO, Serttas F. A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting. Renewable Energy 2017; 108: 635-643.
  • Akarslan E, Hocaoflu FO. A novel adaptive approach for hourly solar radiation forecasting. Renewable Energy 2016; 87(1): 628-633.
  • Li Z, Zang C, Zeng P, Yu H, Li H. Day-ahead hourly photovoltaic generation forecasting using extreme learning machine. In 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), June 8-12, 2015, Shenyang, China, pp. 779-783.
  • Ferrari S, Lazzaroni M, Piuri V, Salman A, Cristaldi L, Faifer M. Computational intelligence models for solar radiation. In 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), May 9-13, 2013, Minneapolis, MN, USA, pp. 757-762.
  • Yang X, Jiang F, Liu H. Short term solar radiation prediction based on SVM with similar data. In 2nd IET Renewable Power Generation Conference (RPG 2013), September 9-11, 2013, Beijing, China, pp. 1-4.
  • Baharin KA, Rahman HA, Hassan MY, Gan CK. Hourly irradiance forecasting in Malaysia using support vector machine,” 2014 IEEE Conference on Energy Conversion (CENCON), October 13-14, 2014, Johor Bahru, Malaysia, pp. 185-190.
  • Ding M, Wang L, Bi R. An ANN-based approach for forecasting the power output of photovoltaic system. Procedia Environmental Sciences 2011; 11(C): 1308-1315.
  • Ceylan O, Starke M, Irminger P, Ollis B, Tomsovic K. A regression based hourly day ahead solar irradiance forecasting model by Labview using cloud cover data. In 9th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, 2015, pp. 406-410.
  • Huang CM, Chen SJ, Yang SP. One-day-ahead hourly forecasting for photovoltaic power generation using an intelligent method with weather-based forecasting models. IET Generation, Transmission & Distribution 2015; 9(14): 1874-1882.
  • Yan X, Abbes D, Francois B. Solar radiation forecasting using artificial neural network for local power reserve. In 2014 International Conference on Electrical Sciences and Technologies in Maghreb (CISTEM), Tunis, 2014, pp. 1-6.
  • CAMS radiation service. Retrieved from http://www.soda-pro.com/web-services/radiation/cams-radiation-service
  • Merra-2 meteorological re-analysis. Retrieved from http://www.soda-pro.com/web-services/meteo-data/merra
  • Lewis CD. Industrial and Business Forecasting Methods. Butterworths Publishing, London, 1982.
  • Cakmak R, Altas IH. Solar energy potential of eastern black sea region of Turkey: A case study for Trabzon province. In 2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO), December 1-3, 2016, Bursa, Turkey, pp. 86-90.
  • Yavuz S, Deveci M. The effect of statistical normalization techniques on the performance of artificial neural network. Erciyes University Journal of Faculty of Economics and Administrative Sciences 2012; 40: 167-187.