ABSTRACT
Load forecasting has always played a particularly important role in the power industry. In this article, we proposed a hybrid model based on Ensemble Empirical Mode Decomposition (EEMD) and Bidirectional Long Short-Term memory (Bi-LSTM). The original time series of load demand was decomposed into several sub-series called Intrinsic Mode Functions (IMFs) using the EEMD method. Then each IMF was divided into training, validation and testing datasets, and predicted using Bi-LSTM. Finally, the forecasting of the load demand would be obtained by composing the predictions of all IMFs. This model was applied to forecast the electrical demand in Hanoi using the data in 2018. The data was first decomposed based on Seasonal-Trend decomposition using the LOESS (STL) method to find down if there was a seasonal characteristic or not. Then 2 cases were analyzed, forecasting the load with and without considering the seasons. The performance of the proposed model in both cases were compared with other traditional models. The results showed that the proposed approach outperformed the other methods with minimal mean absolute percentage error (MAPE) of just over 2% when considering the whole year data as one time series. Meanwhile, the results of the seasonal division are slightly better in 3 seasons and more biased in the summer due to more variability.
- Aasim, S.N. Singh, and Abheejeet Mohapatra. 2021. Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM model. Appl. Soft Comput. 111, (November 2021), 107730. DOI: https://doi.org/10.1016/j.asoc.2021.107730Google ScholarDigital Library
- Jie Du, Yingying Cheng, Quan Zhou, Jiaming Zhang, Xiaoyong Zhang, and Gang Li. 2020. Power Load Forecasting Using BiLSTM-Attention. IOP Conf. Ser. Earth Environ. Sci. 440, (March 2020), 032115. DOI: https://doi.org/10.1088/1755-1315/440/3/032115Google ScholarCross Ref
- Grzegorz Dudek. 2016. Pattern-based local linear regression models for short-term load forecasting. Electr. Power Syst. Res. 130, (January 2016), 139–147. DOI: https://doi.org/10.1016/j.epsr.2015.09.001Google ScholarCross Ref
- Hosein Eskandari, Maryam Imani, and Mohsen Parsa Moghaddam. 2021. Convolutional and recurrent neural network based model for short-term load forecasting. Electr. Power Syst. Res. 195, (June 2021), 107173. DOI: https://doi.org/10.1016/j.epsr.2021.107173Google ScholarCross Ref
- Guo-Feng Fan, Li-Ling Peng, Wei-Chiang Hong, and Fan Sun. 2016. Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing 173, (January 2016), 958–970. DOI: https://doi.org/10.1016/j.neucom.2015.08.051Google ScholarDigital Library
- M. Ghofrani, M. Ghayekhloo, A. Arabali, and A. Ghayekhloo. 2015. A hybrid short-term load forecasting with a new input selection framework. Energy 81, (March 2015), 777–786. DOI: https://doi.org/10.1016/j.energy.2015.01.028Google ScholarCross Ref
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Comput. 9, 8 (November 1997),1735–1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735Google ScholarDigital Library
- Rui Hu, Shiping Wen, Zhigang Zeng, and Tingwen Huang. 2017. A short-term power load forecasting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm. Neurocomputing 221, (January 2017), 24–31. DOI: https://doi.org/10.1016/j.neucom.2016.09.027Google ScholarDigital Library
- Norden E. Huang, Zheng Shen, Steven R. Long, Manli C. Wu, Hsing H. Shih, Quanan Zheng, Nai-Chyuan Yen, Chi Chao Tung, and Henry H. Liu. 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. Ser. Math. Phys. Eng. Sci. 454, 1971 (March 1998), 903–995. DOI: https://doi.org/10.1098/rspa.1998.0193Google ScholarCross Ref
- K.U. Jaseena and Binsu C. Kovoor. 2021. Decomposition-based hybrid wind speed forecasting model using deep bidirectional LSTM networks. Energy Convers. Manag. 234, (April 2021), 113944. DOI: https://doi.org/10.1016/j.enconman.2021.113944Google ScholarCross Ref
- Chen Li. 2021. A fuzzy theory-based machine learning method for workdays and weekends short-term load forecasting. Energy Build. 245, (August 2021), 111072. DOI: https://doi.org/10.1016/j.enbuild.2021.111072Google ScholarCross Ref
- Muhammad Mansoor, Francesco Grimaccia, Sonia Leva, and Marco Mussetta. 2021. Comparison of echo state network and feed-forward neural networks in electrical load forecasting for demand response programs. Math. Comput. Simul. 184, (June 2021), 282–293. DOI: https://doi.org/10.1016/j.matcom.2020.07.011Google ScholarCross Ref
- Gholamreza Memarzadeh and Farshid Keynia. 2021. Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm. Electr. Power Syst. Res. 192, (March 2021), 106995. DOI: https://doi.org/10.1016/j.epsr.2020.106995Google ScholarCross Ref
- M. Moazzami, A. Khodabakhshian, and R. Hooshmand. 2013. A new hybrid day-ahead peak load forecasting method for Iran's National Grid. Appl. Energy 101, (January 2013), 489–501. DOI: https://doi.org/10.1016/j.apenergy.2012.06.009Google ScholarCross Ref
- Shahzad Muzaffar and Afshin Afshari. 2019. Short-Term Load Forecasts Using LSTM Networks. Energy Procedia 158, (February 2019), 2922–2927. DOI: https://doi.org/10.1016/j.egypro.2019.01.952Google ScholarCross Ref
- S.Sp. Pappas, L. Ekonomou, D.Ch. Karamousantas, G.E. Chatzarakis, S.K. Katsikas, and P. Liatsis. 2008. Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models. Energy 33, 9 (September 2008), 1353–1360. DOI: https://doi.org/10.1016/j.energy.2008.05.008Google ScholarCross Ref
- Xueheng Qiu, Ye Ren, Ponnuthurai Nagaratnam Suganthan, and Gehan A.J. Amaratunga. 2017. Empirical Mode Decomposition based ensemble deep learning for load demand time series forecasting. Appl. Soft Comput. 54, (May 2017), 246–255. DOI: https://doi.org/10.1016/j.asoc.2017.01.015Google ScholarDigital Library
- Srinivasa Rao Rallapalli and Sajal Ghosh. 2012. Forecasting monthly peak demand of electricity in India—A critique. Energy Policy 45, (June 2012), 516–520. DOI: https://doi.org/10.1016/j.enpol.2012.02.064Google ScholarCross Ref
- Mao Tan, Siping Yuan, Shuaihu Li, Yongxin Su, Hui Li, and Feng He. 2020. Ultra-Short-Term Industrial Power Demand Forecasting Using LSTM Based Hybrid Ensemble Learning. IEEE Trans. Power Syst. 35, 4 (July 2020), 2937–2948. DOI: https://doi.org/10.1109/TPWRS.2019.2963109Google ScholarCross Ref
- María E. Torres, Marcelo A. Colominas, Gastón Schlotthauer, and Patrick Flandrin. 2011. A complete ensemble empirical mode decomposition with adaptive noise. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4144–4147. DOI: https://doi.org/10.1109/ICASSP.2011.5947265Google ScholarCross Ref
- Deyun Wang, Chenqiang Yue, and Adnen ElAmraoui. 2021. Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy. Chaos Solitons Fractals 152, (November 2021), 111453. DOI: https://doi.org/10.1016/j.chaos.2021.111453Google ScholarCross Ref
- Jie Wu, Jianzhou Wang, Haiyan Lu, Yao Dong, and Xiaoxiao Lu. 2013. Short term load forecasting technique based on the seasonal exponential adjustment method and the regression model. Energy Convers. Manag. 70, (June 2013), 1–9. DOI: https://doi.org/10.1016/j.enconman.2013.02.010Google ScholarCross Ref
- Zhaohua Wu and Norden E. Huang. 2009. ENSEMBLE EMPIRICAL MODE DECOMPOSITION: A NOISE-ASSISTED DATA ANALYSIS METHOD. Adv. Adapt. Data Anal. 01, 01 (January 2009), 1–41. DOI: https://doi.org/10.1142/S1793536909000047Google ScholarCross Ref
- Youlong Yang, Jinxing Che, Chengzhi Deng, and Li Li. 2019. Sequential grid approach based support vector regression for short-term electric load forecasting. Appl. Energy 238, (March 2019), 1010–1021 DOI: https://doi.org/10.1016/j.apenergy.2019.01.127Google ScholarCross Ref
- Haixiang Zang, Ruiqi Xu, Lilin Cheng, Tao Ding, Ling Liu, Zhinong Wei, and Guoqiang Sun. 2021. Residential load forecasting based on LSTM fusing self-attention mechanism with pooling. Energy 229, (August 2021), 120682. DOI: https://doi.org/10.1016/j.energy.2021.120682Google ScholarCross Ref
- Zichen Zhang and Wei-Chiang Hong. 2021. Application of variational mode decomposition and chaotic grey wolf optimizer with support vector regression for forecasting electric loads. Knowl.-Based Syst. 228, (September 2021), 107297. DOI: https://doi.org/10.1016/j.knosys.2021.107297Google ScholarDigital Library
- Hyperbolic Tangent Function - an overview ScienceDirect Topics. Retrieved October 26, 2021 from https://www.sciencedirect.com/topics/engineering/hyperbolic-tangent-functionGoogle Scholar
- Sigmoid Function - an overview | ScienceDirect Topics. Retrieved October 26, 2021 from https://www.sciencedirect.com/topics/engineering/sigmoid-functionGoogle Scholar
Recommendations
Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM model
AbstractElectrical load forecasting is an integral tool used by the grid operator to operate the smart power network. The information related to the electrical load is a prerequisite towards the effective and optimal operation of the power ...
Highlights- A new Repeated WT based SVM (RWT-SVM) model is proposed for the forecasting of the day-ahead electrical load.
A hybrid short-term traffic flow forecasting model based on time series multifractal characteristics
Short-term traffic flow forecasting is a key problem in the area of intelligent transportation systems (ITS). Timely and accurate traffic state prediction is also the prerequisite of realizing proactive traffic control and dynamic traffic assignment ...
A Comparative of a New Hybrid Based on Neural Networks and SARIMA Models for Time Series Forecasting
Multi-disciplinary Trends in Artificial IntelligenceAbstractIn this paper, we present a new hybrid forecasting model using decomposition method with SARIMA model and Artificial Neural Network (ANN). The proposed model has combined linear and non-linear models such as decomposition method with SARIMA model ...
Comments