ISSN: 2225-8329
Open access
Economic and industry growth increases the demand for electricity, forecasting electricity loads is critical for distribution and production of electricity. However, the former forecasting models have three shortcomings: (1) Most of the models use single input feature for forecasting and the forecasting performances of those models are not good enough; (2) Past forecasting methods have used EMD (empirical mode decomposition) method to decompose raw time series data containing noise to improve prediction performance, however EMD method can not handle mode mixing problem; and (3) The recurrent neural network encounters the problem of gradient disappearance or explosion when learning the time series of long-term dependencies. Therefore, proposed model uses autoregressive method and use the EEMD (ensemble empirical mode decomposition) algorithm (which can overcome the mode mixing problem) for time series data decomposition. Further, values produced by moving averages are as input attributes of proposed model to improve forecasting performance. Finally, long-short term memory neural networks (which can solve the shortcomings of recurrent neural networks) are used to build predictive models to enhance electricity loads forecasting model. In the last step of this study, practical electricity loads datasets will be collected to validate the proposed model. Experimental results show that proposed model can improve the accuracy of prediction.
An, X., Jiang, D., Zhao, M., Liu, C. (2012) Short-term prediction of wind power using EMD and chaotic theory, Commun. Nonlinear Sci. Numer. Simul. 17 1036-1042.
Bayer, F. M., Bayer, D. M., Pumi, G. (2017) Kumaraswamy autoregressive moving average models for double bounded environmenttal data, Journal of Hydrology, 555, 385-396,
Bayer, J., Simon. (2015) Learning Sequence Representations, Technische Universitt Mnchen.
Bollerslev, T. (1986) Generalized autoregressive conditional heteroscedasticity. Journal of Econometrics. 31 307-327.
Box, G., Jenkins, G. (1976) Time series analysis: Forecasting and control, San Francisco: Holden-Day.
Caruana, R., A. Niculescu-Mizil, Crew, G., Ksikes, A., (2004) Ensemble selection from libraries of models, International conference on machine learning,
Chang, B. R. (2008) Resolving the forecasting problems of overshoot and volatility clustering using ANFIS coupling nonlinear heteroscedasticity with quantum tuning. Fuzzy Sets and Systems, 159(23) 3183-3200.
Chen, J., Wang, Y. L. (2018) A Resource Demand Prediction Method Based on EEMD in Cloud Computing, Procedia Computer Science, 131, 116-123
Chen, K. L., Yeh, C. C., Lu, T. (2012) Forecasting the output of Taiwan’s integrated circuit (IC) industry using empirical mode decomposition and support vector machines, Int. J. Phys. Sci. 3 (78) 5460-5467.
Engle, R. F. (1982) Autoregressive conditional heteroscedasticity with estimator of the variance of United Kingdom inflation. Econometrica. 50(4) 987-1008.
Fan, S., Mao, C., Chen, L. (2005) Peak load forecasting using the selforganizing map. “Advances in Neural Network”-ISNN 2005. Springer. Part III. 640-9
Feng, F., Zhu, D., Jiang, P., Jiang, H. (2010) GA-EMD-SVR condition prediction for a certain diesel engine, 2010 Progn. Syst. Heal. Manag. Conf. PHM ‘10,
Friedrich, L., Armstrong, P., Afshari, A. (2014)Mid-term forecasting of urban electricity load to isolate air-conditioning impact, “Energy and Buildings”, 80, September, 72-80,
Fu, C. (2010). Forecasting exchange rate with EMD-based Support Vector Regression, in: 2010 Int. Conf. Manag. Serv. Sci. MASS,
Hippert, H. S., Pedreira, C. E., Castro, R. (2001) Neural networks for short-term load forecasting: a review and evaluation. “IEEE Trans Power Syst”, 16, 44-55,
Hochreiter, S., Schmidhuber, J. (1997) Long short-term memory, Neural Comput. 9 (8) 1735–1780.
Hsu, C. C., Chen, C. Y. (2003) Regional load forecasting in Taiwan- applications of artificial neural networks. “Energ Convers Manage”, 44: 1941-9
Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q. (1998)The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis, in: Proceedings of the royal society of London series a-mathematical physical and engineering sciences, series A, 454 903-995.
Huarng, K. H. (2001) Effective lengths of intervals to improve forecasting in fuzzy time series, Fuzzy Sets and Systems. 123 155-162.
Koprinska, I., Rana, M., Agelidis, V. G. (2015) Correlation and instance based feature selection for electricity load forecasting, “Knowledge-Based Systems”, 82, 29-40,
Lai, M. C., Yeh, C. C. (2013) A hybrid model by empirical mode decomposition and support vector regression for tourist arrivals forecasting, J. Test. Eval. 41.
Song, Q., Chissom, B. S. (1993)Forecasting enrollments with fuzzy time series Part I, Fuzzy Sets and Systems. 54 1-10.
Sutskever, I. (2012) Training recurrent neural networks, University of Toronto, Ph.d. thesis .
Tang, L., Lv, H., Yu, L. (2017) An EEMD-based multi-scale fuzzy entropy approach for complexity analysis in clean energy markets, Appl. Soft Comput. 56 124-133.
Tian, Y., Zhang, K., Li, J., Lin, X., Yang, B. (2018) LSTM-based traffic flow prediction with missing data, Neurocomputing, 318 (27), 297-305
Vincent, H. T., Hu S.-L. J., Hou, Z. (1999) Damage detection using empirical mode decomposition method and a comparison with wavelet analysis, in: Proceedings of the second international workshop on structural health monitoring, Stanford 891-900.
Wang, W., Chen, Q., Yan, D., Geng, D. (2019) A novel comprehensive evaluation method of the draft tube pressure pulsation of Francis turbine based on EEMD and information entropy, Mechanical Systems and Signal Processing, 116(1), 772-786
Wang, J., Peng, B., Zhang, X. (2018) Using a stacked residual LSTM model for sentiment intensity prediction, Neurocomputing, 322 (17), 93-101
Wei, L. Y. (2013) A GA-weighted ANFIS model based on multiple stock market volatility causality for TAIEX forecasting , Applied Soft Computing, 13 911-920
Wei, L.Y. (2016) A hybrid ANFIS model based on empirical mode decomposition for stock time series forecasting, Applied Soft Computing, 368-376
Wu, Z., Huang, N. E. (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method, Adv. Adapt. Data Anal. 1 (01) 1–41.
Xu, J., Tan, X., He, G., Liu, Y. (2019) Disentangling the drivers of carbon prices in China's ETS pilots - An EEMD approach Technological Forecasting and Social Change, 139 , 1-9
Yang, Y., Chen, Y., Wang, Y., Li, C., Li, L. (2016) Modelling a combined method based on ANFIS and neural network improved by DE algorithm: A case study for short-term electricity demand forecasting, “Applied Soft Computing”, Vol. 49, pp 663-675,
Yu, D. J., Cheng, J. S., Yang, Y. (2005) Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings, Mech. Syst. Signal Process. 19 (2) 259-270.
Yu, Z., Liu, G., Liu, Q., Deng, J. (2018)Spatio-temporal convolutional features with nested LSTM for facial expression recognition, Neurocomputing, 317 (23), 50-57
Zhang, C., Z. Ni, Ni, L., J. Li, Zhou, L. (2016)Asymmetric multifractal detrending moving average analysis in time series of PM2.5 concentration, Physica A: Statistical Mechanics and its Applications, 457, (1), 322-330,
Zhao, X. J., Mao, Chen, L. (2019)Speech emotion recognition using deep 1D & 2D CNN LSTM networks, Biomedical Signal Processing and Control, 47, 312-323
Zhu, X., Li, Lixiang, Liu, Jing., Li, Ziyi, Niu, X. (2018)Image captioning with triple-attention and stack parallel LSTM, Neurocomputing, 319 (30), 55-65
(Wei, 2024)
Wei, L.-Y. (2024). Fusion AR-EEMD and Moving Average Model based on Long-Short Term Memory Network for Forecasting Electricity Loads. International Journal of Academic Research in Accounting Finance and Management Sciences, 14(1), 81–96.
Copyright: © 2024 The Author(s)
Published by HRMARS (www.hrmars.com)
This article is published under the Creative Commons Attribution (CC BY 4.0) license. Anyone may reproduce, distribute, translate and create derivative works of this article (for both commercial and non-commercial purposes), subject to full attribution to the original publication and authors. The full terms of this license may be seen at: http://creativecommons.org/licences/by/4.0/legalcode