A deep learning model for electricity demand forecasting based on a tropical data

• Autorzy: Adewuyi Saheed A. , Aina Segun , Oluwaranti Adeniran I.

Identyfikatory

DOI

10.23743/acs-2020-01

• Języki publikacji: EN

Abstrakty

EN

Electricity demand forecasting is a term used for prediction of users’ consumption on the grid ahead of actual demand. It is very important to all power stakeholders across levels. The power players employ electricity demand forecasting for sundry purposes. Moreover, the government’s policy on its market deregulation has greatly amplified its essence. Despite numerous studies on the subject using certain classical approaches, there exists an opportunity for exploration of more sophisticated methods such as the deep learning (DL) techniques. Successful researches about DL applications to computer vision, speech recognition, and acoustic computing problems are motivation. However, such researches are not sufficiently exploited for electricity demand forecasting using DL methods. In this paper, we considered specific DL techniques (LSTM, CNN, and MLP) to short-term load forecasting problems, using tropical institutional data obtained from a Transmission Company. We also test how accurate are predictions across the techniques. Our results relatively revealed models appropriateness for the problem.

Słowa kluczowe

EN

Electricity Demand Forecasting; STLF; deep learning techniques; LSTM; CNN; MLP

PL

prognozowanie zapotrzebowania na energię elektryczną; STLF; techniki głębokiego uczenia; LSTM; CNN; MLP

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2020
• Tom: Vol. 16, no 1
• Strony: 5--17
• Opis fizyczny: Bibliogr. 29 poz., fig.

Twórcy

autor

Adewuyi Saheed A.

• 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, Nigeria

autor

Oluwaranti Adeniran I.

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

Bibliografia

• [1] Adewuyi, S., Aina, S., Uzunuigbe, M., Lawal, A., & Oluwaranti, A. (2019). An Overview of Deep Learning Techniques for Short-Term Electricity Load Forecasting. Applied Computer Science, 15(4), 75–92. doi: 10.23743/acs-2019-31
• [2] Agrawal, R. K., Muchahary, F., & Tripathi, M. M. (2018). Long term load forecasting with hourly predictions based on long-short-term-memory networks. In 2018 IEEE Texas Power and Energy Conference (TPEC) (pp. 1–6). College Station, TX.
• [3] Bengio, Y. (2009). Learning deep architectures for AI. Foundation and Trends in Machine Learning, 2(1), 1–127.
• [4] Bouktif, S., Ali, F., Ali, O., & Mohamed, A. S. (2018). Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11, 1636–1656.
• [5] Brownlee, J. (2018). Deep learning for time series forecasting: Predicting the future with MLPs, CNNs and LSTMs in Python. V1.2 ed. M. L. Mastery.
• [6] Chengdong, L., Zixiang, D., Dongbin, Z., Jianqiang, Y., & Guiqing, Z. (2017). Building energy Con-sumption prediction: An extreme deep learning approach. Energies, 10(10), 1525–1545.
• [7] 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.
• [8] Deng, L., & Yu, D. (2013). Deep learning: Methods and Applications. Foundations and Trends in Signal Processing, 7(3-4), 197–387.
• [9] 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 (pp. 269–285). Boston, MA.
• [10] Gamboa, J. (2017). Deep learning for time-series Analysis. arXiv: 1701.01887[cs. LG].
• [11] Ghullam, M. U., & Angelos, K. M. (2017). Short-term power load forecasting using deep neural networks. ICNC, 10(1109), 594–598.
• [12] Hamedmoghadam, H., Joorabloo, N., & Jalili, M. (2018). Australia's long-term electricity demand forecasting using deep neural networks, arXiv:1801.02148 [cs.NE].
• [13] Hernandez, L., Baladron, C., Aquiar, J. M., Calavia, L., Carro, B., Sánchez-Esguevillas, A., Cook, D. J., Chinarro, D., & Gomez, J. (2012). A study of relationship between weather variables and electric power demand inside a smart grid/ smart world. MDPI Sensors, 22(9), 11571–11591. doi:10.3390/s120911571
• [14] Hernandez, L., Baladron, C., Aquiar, J. M., Calavia, L., Carro, B., Sánchez-Esguevillas, A., Cook, D. J., Chinarro, D., & Gomez, J. (2013). Short-term load forecasting for micro-grids based on artificial neural networks. MDPI Sensors, 6(3), 1385–1408.
• [15] Hernandez, L., Baladron, C., Aquiar, J. M., Calavia, L., Carro, B., Sánchez-Esguevillas, A., Perez, F., Fernández, A., & Lloret, J. (2014). Artificial neural network for short-term load forecasting in distribution systems. MDPI Energies, 7(3), 1576–1598.
• [16] Hosein, S., & Hosein, P. (2017). Load forecasting using deep neural networks. In Proceedings of the Power and Energy Society Conference on Innovative Smart Grid Technologies (pp. 1–5). IEEE.
• [17] Hussein, A. (2018). Deep Learning Based Approaches for Imitation Learning (Doctoral dissertation). Robert Gordon University, Aberden, Scotland.
• [18] International Energy Agency (IEA) Publications and data (n.n.). Retrieved August 12, 2018 from https://www.iea.org
• [19] Kuo, P., & Huang, C. (2018). A high-precision artificial neural networks model for short-term energy load management. Energy, 11(1), 213– 226.
• [20] Momani, M. A. (2013). Factors Affecting Electricity Demand in Jordan. Energy and Power Engineering, 5, 50–58.
• [21] Ronald, J. W., & Jing, P. (1990). An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories. Neural Computation, 2, 490–501.
• [22] Sarabjit, S., & Rupinderjit, S. (2013). ARIMA Based Short Term Load Forecasting for Punjab Region. IJSR, 4(6), 1919–1822.
• [23] Schmidhuber, J., & Sepp, H. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
• [24] Seunghyoung, R., Hongseok, K., & Jaekoo, N. (2017). Deep neural network based demand side short term load forecasting. Energies MDPI, 10(1), 3–23.
• [25] Stuart, R., & Norvig, P. (2013). Artificial Intelligence A modern Approach. Second ed. Prentice Hall.
• [26] Sutskever, I. (2013). Training Rucurrent Neural Net-works (Doctoral dissertation). Computer Science, University of Toronto, Toronto.
• [27] Swalin, A. (2018). How to Handle Missing Data. Towards Data Science. https://towardsdatascience.com/how-to-handle-missing-data-8646b18db0d4 on 18/01/19.
• [28] Wan, H. (2014). Deep Neural Network Based Load Forecast. Computer Modelling and New Technologies, 18(3), 258–262.
• [29] Yi, Y., Jie, W., Yanhua, C., & Caihong, L. (2013). A New Strategy for Short-Term Load Forecasting. Hindawi, 2013, 208964. doi:10.1155/2013/208964

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).