Volume 20, Issue 4 (JIAEEE Vol.20 No.4 2023)
Journal of Iranian Association of Electrical and Electronics Engineers 2023, 20(4): 123-132 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Sohrabi M S, Moazzami M. A Hybrid Approach for Probabilistic mid-term Electricity Price Forecasting using deep learning. Journal of Iranian Association of Electrical and Electronics Engineers 2023; 20 (4) :123-132
URL: http://jiaeee.com/article-1-997-en.html
URL: http://jiaeee.com/article-1-997-en.html
Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran
Abstract: (841 Views)
With deregulation of modern power systems, electricity market price forecasting become more and more important in managing electricity market which plays a key role in practical operation of electricity market and smart grids. In this paper, a hybrid approach is proposed for probabilistic mid-term electricity price forecasting. In proposed method, feature matrix is extracted using neighborhood component analysis while the seasonality of observed electricity prices is decomposed. After preparation of training dataset, each subset divided to training and validation subsets. Afterwards, using each training data subset and by utilizing a long short-term memory network configuration with three hidden layers, a prediction model will be trained and will be tested with training and validation data sets. The simulation results show that proposed hybrid method caused a decrease in the point forecasting error. Error reduction results to a decrease in final error of combined model and the best MAPE is related to Winsorized model with value of 9.2009 which shows a reduction in MAPE equal to 9.633 percent compared with the method presented for comparison. The results show that the proposed method for electricity price forecasting is an efficient method and can be used for mid-term probabilistic electricity price forecasting.
Keywords: Neighborhood component analysis, Seasonal decomposition, Probabilistic forecasting, Long short-term memory network, Sequence training, Prediction combination, Probability density function.
Type of Article: Research |
Subject:
Power
Received: 2019/10/9 | Accepted: 2022/12/26 | Published: 2023/08/6
Received: 2019/10/9 | Accepted: 2022/12/26 | Published: 2023/08/6
Extended Abstract [PDF 277 KB] (11 Download)
References
1. [1] M. Shahidehpour, H. Yamin, Z. Li, "Market Operations in Electric Power Systems, Tarbiat modares university, 1384.
2. [2] رحمت الله هوشمند، مجید معظمی، "پیش‌بینی کوتاه مدت قیمت تراکم گرهی در یک سیستم قدرت بزرگ تجدید ساختاریافته با استفاده از شبکه‌های عصبی مصنوعی با بهینه‌سازی آموزش ژنتیکی"، مجله انجمن برق و الکترونیک ایران، سال یازدهم، شماره اول، صفحات 37-48، بهار و تابستان 1393.
3. [3] حمید کریمی، شهرام جدید، "تعیین قیمت بهینه برای برنامه پاسخگویی بار با هدف بهبود همزمان سود مصرف‌کنندگان و ضریب بار شبکه"، مجله انجمن برق و الکترونیک ایران، سال هفدهم، شماره دوم، صفحات 149-159، تابستان 1399.
4. [4] P. Kou, D. Liang, L. Gao and J. Lou, "Probabilistic electricity price forecasting with variational heteroscedastic gaussian process and active learning," Energy Conversion and Management, vol. 89, no. 0, pp. 298-308, 2015. [DOI:10.1016/j.enconman.2014.10.003]
5. [5] N. A. Shrivastava and B. K. Panigrahi, "A hybrid wavelet-ELM based short term price forecasting for electricity markets," Int. J. Elec. Power & Energy. Syst., vol. 55, pp. 41-50, 2014. [DOI:10.1016/j.ijepes.2013.08.023]
6. [6] K. He, Y. Xu, Y. Zou and L. Tang, "Electricity price forecasts using a curvelet denoising based approach," Physica A: Statistical Mechanics and its Applications, vol. 425, pp. 1-9, 2015. [DOI:10.1016/j.physa.2015.01.012]
7. [7] C. Wan, M. Niu, Y. Song and Z. Xu, "Pareto optimal prediction intervals of electricity price," IEEE Trans. Power Syst. in press, 2016. [DOI:10.1109/TPWRS.2016.2550867]
8. [8] P. Gaillard, Y. Goude and R. Nedellec, "Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting," Int. J. Forecast., 2016, in press. [DOI:10.1016/j.ijforecast.2015.12.001]
9. [9] F. Ziel, "Forecasting electricity spot prices using lasso: On capturing the autoregressive intraday structure," IEEE Trans. Power Syst., 2016, in press. [DOI:10.1109/TPWRS.2016.2521545]
10. [10] T. Hong, P. Pinson, S. Fan, H. Zareipour, A. Troccoli and R.J. Hyndman, "Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond," Int.J.Forecast. 2016. [DOI:10.1016/j.ijforecast.2016.02.001]
11. [11] P. Gaillard, Y. Goude and R. Nedellec, "Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting," Int. J. Forecast., 2016, in press. [DOI:10.1016/j.ijforecast.2015.12.001]
12. [12] F. Ziel, "Forecasting electricity spot prices using lasso: On capturing the autoregressive intraday structure," IEEE Trans. Power Syst., 2016, in press. [DOI:10.1109/TPWRS.2016.2521545]
13. [13] Y. Yang, Y. Dong, Y. Chen and C. Li, "Intelligent optimized combined model based on GARCH and SVM for forecasting electricity price of New South Wales, Australia," in Abstr. Appl. Anal., vol. 2014, Article ID 504064, 2014. [DOI:10.1155/2014/504064]
14. [14] X. Yan and N. A. Chowdhury, "Mid-term electricity market clearing price forecasting: A multiple SVM approach," Int. J. Elec. Power, vol. 58, pp. 206-214, 2014. [DOI:10.1016/j.ijepes.2014.01.023]
15. [15] R. Weron, "Electricity price forecasting: A review of the state-of-the-art with a look into the future," Int.J.Forecast., vol. 30, no. 4, pp. 1030-1081 2014. [DOI:10.1016/j.ijforecast.2014.08.008]
16. [16] Osorio, G. J., Matis, J.C.O., Catalao, J.P.S., "Electricity prices forecasting by a hybrid evolutionary-adaptive methodology," Energy Conversion and Management, Vol.80, pp. 363-373, April. 2014. [DOI:10.1016/j.enconman.2014.01.063]
17. [17] Feijoo, F., Silva, W., K..Das, T., "A computationally efficient electricity price forecasting model for realtime energy market,", Energy Conversion and Management, Vol.113, pp. 27-35, April. 2016. [DOI:10.1016/j.enconman.2016.01.043]
18. [18] Hossam, M., El-Hawary, M., " Hourly Electricity Price Forecasting for the Next Month Using Multilayer Neural Network," IEEE Canadian journal of electrical and computer engineering, vol.39, pp. 283-291, December. 2016. [DOI:10.1109/CJECE.2016.2586939]
19. [19] Y.H. Chen, W.C. Hong, W. Shen, N.N. Huang, "Electric Load Forecasting Based on a Least Squares Support Vector Machine with Fuzzy Time Series and Global Harmony Search Algorithm,", MDPI energies, Vol. 9, No. 2, January 2016. [DOI:10.3390/en9020070]
20. [20] W. Guo, Z. Zhao, "A Novel Hybrid BND-FOA-LSSVM Model for Electricity Price Forecasting,", MDPI Information, Vol. 8, No. 4, September 2017. [DOI:10.3390/info8040120]
21. [21] P.H. Kuo, C.J. Huang, "An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks,", MDPI Sustainability, Vol. 10, No. 4, April 2018. [DOI:10.3390/su10041280]
22. [22] M. Rafiei, T. Niknam, M. Khooban, "Probabilistic Forecasting of Hourly Electricity Price by Generalization of ELM for Usage in Improved Wavelet Neural Network," IEEE Trans. Industrial Informatics., Vol. 13, No. 1, pp. 71-79, Feb. 2017. [DOI:10.1109/TII.2016.2585378]
23. [23] R. Tahmasebifar, M. Sheikh-El-Eslami, R. Kheirollahi, "Point and interval forecasting of real-time and day-ahead electricity prices by a novel hybrid approach," IET Generation, Transmission & Distribution, Vol. 11, No. 9, pp. 2173-2183, June. 2017. [DOI:10.1049/iet-gtd.2016.1396]
24. [24] B. Uniejewski, R. Weron and F. Ziel, "Variance Stabilizing Transformations for Electricity Spot Price Forecasting," IEEE Trans. Power Syst., Vol. 33, No. 2, pp. 2219-2229, March. 2018. [DOI:10.1109/TPWRS.2017.2734563]
25. [25] A. Bello, D. W. Bunn, J. Reneses, A. Muñoz, "Medium-Term Probabilistic Forecasting of Electricity Prices: a Hybrid Approach," IEEE Trans. Power Syst., Vol. 32, No. 1, pp. 334-343, Jan. 2017. [DOI:10.1109/TPWRS.2016.2552983]
26. [26] L. L. Jiang, G. Hu, "Day-Ahead Price Forecasting for Electricity Market using Long-Short Term Memory Recurrent Neural Network", 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, 18-21 Nov. 2018. [DOI:10.1109/ICARCV.2018.8581235]
27. [27] L. Penga, S. Liub, R. Liu, L. Wang, "Effective long short-term memory with differential evolution algorithm for electricity price prediction", Elsevier Energy, Vol. 162, pp. 1301-1314, 1 November 2018. [DOI:10.1016/j.energy.2018.05.052]
28. [28] S. Mujeeb, N. Javaid , M. Ilahi, Z. Wadud, F. Ishmanov, M. K. Afzal, "Deep Long Short-Term Memory: A New Price and Load Forecasting Scheme for Big Data in Smart Cities", MDPI Sustainability, Vol. 11, No. 4, February 2019. [DOI:10.3390/su11040987]
29. [29] Yang, W., K. Wang, W. Zuo. "Neighborhood Component Feature Selection for High-Dimensional Data." Journal of Computers. Vol. 7, Number 1, January, 2012. [DOI:10.4304/jcp.7.1.161-168]
30. [30] Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735-1780. [DOI:10.1162/neco.1997.9.8.1735]
31. [31] K. B. Sahay and M. M. Tripathi, "Day ahead hourly load and price forecast in ISO New England market using ANN," in Proc. Annu. IEEE India Conf. (INDICON), Dec. 2013, pp. 1-6. [DOI:10.1109/INDCON.2013.6725869]
32. [32] Escribano, Alvaro, Pena, Juan Ignacio, Villaplana, Pablo. "Modeling Electricity Prices: International Evidence." Universidad Carloes III de Madrid, Working Paper 02-27, 2002. [DOI:10.2139/ssrn.299360]
33. [33] Lucia, Julio J., Schwartz, Eduaro. "Electricity Prices and Power Derivatives: Evidence from the Nordic Power Exchange." Review of Derivatives Research. Vol. 5, Issue 1, pp 5-50, 2002. [DOI:10.1023/A:1013846631785]
34. [34] The Australian Energy Market Operator (AEMO). [Online]. Available: http://www.aemo.com.au/Electricity/Planning/ Forecasting (2015).
Send email to the article author
| Rights and permissions | |
 |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |
