An overview of deep learning techniques for short-term electricity load forecasting

• Autorzy: Adewuyi Saheed , Aina Segun , Uzunuigbe Moses , Lawal Aderonke , Oluwaranti Adeniran

Identyfikatory

DOI

10.23743/acs-2019-31

• Języki publikacji: EN

Abstrakty

EN

This paper presents an overview of some Deep Learning (DL) techniques applicable to forecasting electricity consumptions, especially in the short-term horizon. The paper introduced key parts of four DL architectures including the RNN, LSTM, CNN and SAE, which are recently adopted in implementing Short-term (electricity) Load Forecasting problems. It further presented a model approach for solving such problems. The eventual implication of the study is to present an insightful direction about concepts of the DL methods for forecasting electricity loads in the short-term period, especially to a potential researcher in quest of solving similar problems.

Słowa kluczowe

EN

Short-term Load Forecasting; deep learning architectures; RNN; LSTM; CNN; SAE

PL

prognozowanie obciążenia krótkoterminowego; architektura głębokiego uczenia; RNN; LSTM; CNN; SAE

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2019
• Tom: Vol. 15, no 4
• Strony: 75--92
• Opis fizyczny: Bibliogr. 24 poz., fig.

Twórcy

autor

Adewuyi Saheed

• Osun State University, Department of Information and Communication Technology, Osogbo, Osun State, Nigeria

autor

Aina Segun

• Obafemi Awolowo University, Department of Computer Science and Engineering, Ile-Ife, Osun State, Niger

autor

Uzunuigbe Moses

• Transmission Company of Nigeria, 132/33 kV, Ajebandele, Ile Ife, Osun State, Nigeria

autor

Lawal Aderonke

• Obafemi Awolowo University, Department of Computer Science and Engineering, Ile-Ife, Osun State, Nigeria

autor

Oluwaranti Adeniran

• Obafemi Awolowo University, Department of Computer Science and Engineering, Ile-Ife, Osun State, Nigeria

Bibliografia

• [1] Bengio, Y. (2009). Learning deep architectures for AI. Foundation and Trends in Machine Learning, 2(1), 1–127.
• [2] Brownlee, J. (Ed.) (2018). Deep learning for time series forecasting: Predicting the future with MLPs, CNNs and LSTMs in Python. Machine learning mastery.
• [3] Chengdong, L., Zixiang, D., Dongbin, Z., Jianqiang, Y., & Guiqing, Z. (2017). Building energy consu-mption prediction: An extreme deep learning approach. Energies, 10(10), 1525–1545.
• [4] Deng, L. (2013). A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, 3(2). doi:10.1017/ATSIP
• [5] Deng, L., & Yu, D. (2013). Deep learning: methods and applications. Foundations and Trends in Signal Processing, 7(3-4), 197–387.
• [6] Feinberg, E. A., & Genethliou, D. (2005). Load forecasting. In J. H. Chow, F.F. Wu, & J. Momoh (Eds.), Applied Mathematics for Restructured Electric Power Systems. Power Electronics and Power Systems. Springer, Boston, MA.
• [7] Gamboa, J. (2017). Deep learning for time-series analysis. arXiv: 1701.01887.
• [8] Ghullam, M. U., & Angelos, K. M. (2017). Short term power load forecasting using deep neural networks. ICNC, 10(1109), 594–598, 7876196.
• [9] Hamedmoghadam, H., Joorabloo, N., & Jalili, M. (2018). Australia's long-term electricity demand forecasting using deep neural networks. arXiv: preprint arXiv:1801.02148.
• [10] Hussein, A. (2018). Deep Learning Based Approaches for Imitation Learning (doctoral dissertation). Robert Gordon University Aberdeen, Scotland.
• [11] Hussein, S., & Hussein, P. (2017). Load forecasting using deep neural networks. In 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT). IEEE. doi:10.1109/ISGT.2017.8085971
• [12] Kuo, P., & Huang, C. (2018). A high-precision artificial neural networks model for short-term energy load management. Energy, 11(1), 213–226.
• [13] Luis, H., Carlos, B., Javier, M. A., Lorena, C., Belen, C., Antonio, S., Diane, J. C., David, C., & Jorge, G. (2012). A study of relationship between weather variables and electric power demand inside a smart grid/ smart world. MDPI Sensors, 22(9), 11571–11591.
• [14] Luis, H., Carlos, B., Javier, M. A., Lorena, C., Belen, C., Antonio, S., Diane, J. C., David, C., & Jorge, G. (2013). Short-term load forecasting for micro-grids based on artificial neural networks, MDPI Sensors, 6(3), 1385–1408.
• [15] Luis, H., Carlos, B., Javier, M. A., Lorena, C., Belen, C., Antonio, S., & Jaime, L. (2014). Artificial neural network for short-term load forecasting in distribution systems, MDPI, 7(3), 1576–1598.
• [16] Merkel, G. D., Povinelli, R. J., & Brown, R. H. (2017). Deep neural network regression for short-term load forecasting of natural gas. Report: Marquette University.
• [17] Nor, H. M., Rahaini, M. S., & Siti, H. H. A. (2018). ARIMA with Regression Model in Modelling electricity load demand, Journal of Telecommunication, Electronic and Computer Engineering, 8(12), 113–116.
• [18] Rahul, K. A., Frankle, M., & Madan, M. T. (2018). Long term load forecasting with hourly predictions based on long-short-term-memory networks. In 2018 IEEE Texas Power and Energy Conference (TPEC). IEEE. doi:10.1109/TPEC.2018.8312088
• [19] Sarabjit, S., & Rupinderjit, S. (2013). ARIMA Based Short Term Load Forecasting for Punjab Region. IJSR, 4(6), 1919–1822.
• [20] Schmidhuber, J., & Sepp, H. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
• [21] Seunghoung, R., Hongseok, K., & Jaekoo, N. (2017). Deep neural network based demand side short term load forecasting. Energies MDPI, 10(1), 3–23.
• [22] Swalin, A. (2019). How to handle missing data. Towards Data Science. Retrieved from https://towardsdatascience.com/how-tohandle-missing-data-8646b18db on 18/01/2019.
• [23] Wan, H. (2014). Deep neural network based load forecast. Computer Modelling and New Technologies, 18(3), 258–262.
• [24] Yi, Y., Jie, W., Yanhua, C., & Caihong L. (2013). A new strategy for short-term load forecasting. Hindawi.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).