MULTI-STEP FORWARD FORECASTING OF ELECTRICAL POWER GENERATION IN LIGNITE-FIRED THERMAL POWER PLANT

Abstract

This paper presents multi-step forward forecasting studies using real-time generated electrical power time series. Nonlinear Automatic Regression (NAR) and Autoregressive Integrated Moving Average (ARIMA) models were created and applied to the generator power time series produced in Afşin-Elbistan Thermal B Plant. The data were divided into three categories as raw, 10-moving average and 20-moving average while the number of forwarding steps has been established as 6-step forward, 12-step forward and 20-step forward. Performance results of NAR and ARIMA models were presented with 6 scenarios, and then, the results were compared with tables and graphs. As a result of all studies, it has been observed that the model’s success was greatly affected by moving average and forward steps parameters.

Keywords

• ARIMA
• NAR
• Artificial Neural Network
• Time Series
• Multi-Step Forward Forecast

LİNYİT YAKITLI TERMİK SANTRALDE ELEKTRİK ENERJİSİ ÜRETİMİNİN ÇOK ADIMLI İLERİ TAHMİNİ

Abstract

Bu çalışmada gerçek zamanlı üretilen elektriksel güç zaman serilerinin kullanılmasıyla çok adımlı ileriye dönük tahmin çalışmaları anlatılmaktadır. Doğrusal Olmayan Otoregresif (NAR) ve Otoregresif Hareketli Ortalama (ARIMA) modelleri oluşturulmuş ve Afşin-Elbistan Termik B Santralinde üretilen generatör güç zaman serilerine uygulanmıştır. Veriler ham, 10 hareketli ortalama ve 20 hareketli ortalama olarak üç kategoriye ayrılırken, adım sayısı 6 adım ileri, 12 adım ileri ve 20 adım ileri olarak belirlenmiştir. NAR ve ARIMA modellerinin performans sonuçları 6 senaryo ile oluşturulmuş, ardından sonuçlar tablo ve grafikler ile karşılaştırılmıştır. Tüm çalışmalar sonucunda, hareketli ortalama ve ileri adım sayısı parametrelerinin model başarısını büyük ölçüde etkilediği görülmüştür.

Keywords

• ARIMA
• NAR
• Yapay Sinir Ağları
• Zaman Serisi
• Çok-Adımlı İleri Tahmin

References

1. Abdel-Aal R.E., Elhadidy M.A., Shaahid S.M., 2009. Modeling And Forecasting the Mean Hourly Wind Speed Time Series Using GMDH-Based Abductive Networks, Renewable Energy 34: 1686-1699.
2. Amjady A., Keynia F., Zareipour H. 2010., Short-Term Load Forecast of Microgrids by a New Bilevel Prediction Strategy, IEEE Transactıons on Smart Grid, 1(3):286-294.
3. Bálint R., Fodor A., Magyar A. 2019., Model-Based Power Generation Estimation of Solar Panels Using Weather Forecast for Microgrid Application, Acta Polytechnica Hungarica, 16 (7): 149-165.
4. Bhaskar K. and Sing S. N. 2012., AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network. The Institute of Electrical and Electronics Engineers Transactions on Sustainable Energy, 3(2): 306-315.
5. Bracale A., Carpinelli G., Rizzo R., Russo A. 2014., Advanced Method and Cost-Based Indices for Probabilistic Forecasting the Generation of Renewable Power, 3rd Renewable Power Generation Conference (RPG 2014), 24-25 Sept. 2014, Naples, Italy.
6. Chang W.Y. 2014., A Literature Review of Wind Forecasting Methods, Journal of Power and Energy Engineering, 2:161-168.
7. Hong T., Pinson P., Fan S., Zareipour H., Troccoli, A., Hyndmanc, R. J. 2016., Probabilistic Energy Forecasting: Global Energy Forecasting Competition 2014 and Beyond, International Journal of Forecasting, 32: 896-913.
8. Hossain M.S., Mahmood H. 2020., Short-Term Load Forecasting Using an LSTM Neural Network, 2020 IEEE Power and Energy Conference at Illinois (PECI), 27-28 Feb. 2020 Champaign, IL, USA.

9. Hu J., Wang J., Zeng G. 2013., A Hybrid Forecasting Approach Applied to Wind Speed Time Series, Renewable Energy, 60:185-194.
10. Jeong G., Park S., Hwang G. 2020., Time Series Forecasting Based Day-Ahead Energy Trading in Microgrids: Mathematical Analysis and Simulation, IEEE Access, 10.1109/ACCESS.2020.2985258, 8(20): 63885-63900.
11. Kerem A., Kirbas İ., Saygın A. 2016., Performance Analysis of Time Series Forecasting Models for Short Term Wind Speed Prediction, International Conference on Engineering and Natural Sciences (ICENS), 24-28 May 2016, Sarajevo, Bosnia-Herzegovina.
12. Kerem A., Kırbaş İ. 2019., Doğrusal Olmayan Otoregresif Ağ (NAR) Modelinin Gerçek Zamanlı Rüzgar Hızı Zaman Serilerine Uygulanması, International Symposium on Advanced Engineering Technologies (ISADET), 02-04 May, Kahramanmaraş, Turkey.
13. Kırbaş I., Kerem A. 2016., Short-Term Wind Speed Prediction Based on Artificial Neural Network Models, Measurement and Control, 49 (6) 183-190.
14. Kırbaş İ. 2018., İstatistiksel Metotlar ve Yapay Sinir Ağları Kullanarak Kısa Dönem Çok Adımlı Rüzgâr Hızı Tahmini, Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 22(1): 24-38.
15. Liu H., Tian H., Pan D., Li Y. 2013., Forecasting Models for Wind Speed Using Wavelet, Wavelet Packet, Time Series and Artificial Neural Networks, Applied Energy, 107:191-208.
16. Liu S., Zhang L., Zou B. 2020., Study on Electricity Market Price Forecasting With Large-Scale Wind Power Based on LSTM, 6th International Conference on Dependable Systems and Their Applications (DSA), 3-6 Jan. 2020, Harbin, China.
17. Mao Y. and Shaoshuai W. 2016., A Review of Wind Power Forecasting & Prediction. Probabilistic Methods Applied to Power Systems (PMAPS), 2016 International Conference, Beijing, China.
18. Niu D., Shi H., Li J., Wei Y. 2010., Research on Short-Term Power Load Time Series Forecasting Model Based on BP Neural Network, 2nd International Conference on Advanced Computer Control, 27-29 March 2010, Shenyang, China.
19. Obradovic Z., Tomsovic, K. 1999., Time Series Methods for Forecasting Electricity Market Pricing, IEEE Power Engineering Society Summer Meeting, Conference Proceedings (Cat. No.99CH36364), 18-22 July 1999, Edmonton, Alta, Canada.
20. Rahman M.N., Esmailpour A. 2015., An Efficient Electricity Generation Forecasting System Using Artificial Neural Network Approach With Big Data, 2015 IEEE First International Conference on Big Data Computing Service and Applications, 213-217.
21. Sahu M. K., Sahoo B., Khatoi M., Behera S. 2019., Short-Term Wind And PV Generation Forecasting of Time-Series Using ANN, International Conference on Intelligent Computing and Control Systems (ICCS), 15-17 May 2019, Madurai, India.
22. Sevüktekin M., Çınar M. 2017., Ekonometrik Zaman Serileri Analizi: Eviews Uygulamalı, Dora Yayıncılık, 1- 667.
23. Sfetsos A. 2000., A Comparison of Various Forecasting Techniques Applied to Mean Hourly Wind Speed Time Series, Renewable Energy, 21: 23-35
24. Shi J., Guo J., Zheng S. 2012., Evaluation of Hybrid Forecasting Approaches for Wind Speed and Power Generation Time Series, Renewable and Sustainable Energy Reviews,16: 3471-3480.
25. Taylor J.W., McSharry P.E., Buizza R. 2009., Wind Power Density Forecasting using Ensemble Predictions and Time Series Models, IEEE Transactions on Energy Conversion, 24(3): 775-782.
26. Türkiye Elektrik Yatırımları 2020 Yılı Ocak Ayı Özet Raporu, Enerji İşleri Genel Müdürlüğü Yatırımlar Dairesi Başkanlığı, Ocak 2020, 1-4, Ankara, Turkey
27. Yuan-Kang W., Jing-Shan H. 2007., A Literature Review of Wind Forecasting Technology in The World, 2007 IEEE Lausanne Power Tech, 1-5 July 2007, Lausanne, Switzerland.