在能源行業中，數據分析對於電力系統的日常運營和規劃至關重要。在新興的智能電網中，能源管理面臨的一個關鍵挑戰是在電力供應（例如：可再生能源發電）和需求（例如：服務區域的負載需求）方面的不確定性。對各種類型能源數據的準確預測對智能電網技術發展和將可再生能源有效整合到現有電網中至為關鍵。因此，此論文提出了一種包括分解算法和深度學習模型的混合方法，可應用於能源市場預測。我們的研究主要有三個方向：1）新混合模型的開發，2）數據分解和固有模態函數（IMF）確定方法，以及3）時間滑動窗口方法的應用。將可再生能源整合到電網中改變了負載模式，增加了數據變異性，為能源預測帶來了新的挑戰。因此，我們在這項研究中引入了一種創新的混合方法，用於預測各種能源數據集。結果顯示，本研究中的方法在公共能源市場數據集中的預測能力優於其他預測方法。使用滑動窗口方法，每個IMF均由我們提出的方法建模，以獲得預測序列。然後，這些序列被總和並重新歸一化以獲得最終的預測值。為了評估我們模型的泛化能力和穩健性，使用了各種能源數據類型，從非可再生到可再生再到電價。在實驗中，所提出方法的平均絕對百分比誤差在所有預測期內均小於1％，R2在92.6％到99.8％的範圍內，顯示在這些時期具有顯著的準確性。為了評估我們提出模型的可靠性，使用蒙特卡羅隨機關閉神經元方法進行不確定性量化，有助於制定強健的風險管理策略。

In the power industry, data analytics is crucial for the daily operation and planning of power systems. A key challenge in energy management within the emerging smart grid is the uncertainty in power supply, such as renewable energy generation, and in demand, like load demand from service areas. For the development of smart grid technology and efficient integration of renewable energy into existing grids, accurate prediction of various energy data types is essential. Therefore, In this paper, we propose a hybrid approach that includes decomposition algorithms and deep learning models; it can be applied to energy market forecasting. Our research has three main directions: 1) development of new hybrid models, 2) data decomposition and intrinsic mode functions (IMFs) determination methods, and 3) application of time-sliding window methods. Integrating renewable energy into the grid changes load patterns, increasing data variability and creating new challenges for energy forecasting. Therefore, we introduce in this study an innovative hybrid approach to forecasting various energy datasets. The results show that the prediction ability of the method in this study is better than other prediction methods in the public energy market data set. Using the sliding window method, each IMF is modeled with our proposed approach to yield a predicted sequence. The series sequences are then added and renormalized to derive the final predicted values. To evaluate the generalization and robust capability of our model different energy data types are used ranging from nonrenewable to renewable to electricity price. In experiments, the MAPEs of the proposed method are less than 1%, across all forecast periods, and the R^2 range from 92.6% to 99.8%, it shows remarkable accuracy in these periods. To evaluate our proposed model’s reliability, uncertainty quantification is done using the Monte Carlo dropout approach to help in robust risk management strategies.

[1] R.Irle. Global EV Sales for 2022 H1, https://www.ev-volumes.com/; 2022 [ accessed 06 January 2023].
[2] International Energy Agency. European Union 2020 Energy Policy Review, Paris; IEA/OECD Publications: Paris, France, 2020; p. 310.
[3] Zhao GY, Liu ZY, He Y, Cao HJ, Guo YB. Energy consumption in machining: classification, prediction, and reduction strategy. Energy 2017;133:142–57. https://doi.org/10.1016/j.energy.2017.05.110.
[4] Zhang Y, Guo H, Sun M, Liu S, Forrest J. A novel grey Lotka–Volterra model driven by the mechanism of competition and cooperation for energy consumption forecasting. Energy 2023;264:126154. https://doi.org/10.1016/j.energy.2022.126154.
[4] Perçuku A, Minkovska D, Stoyanova L. Big data and time series use in short term load forecasting in power transmission system. Procedia Comput Sci 2018;141:167–74.
[5] Nasab MA, Zand M, Dashtaki AA, Azimi Nasab M, Padmanaban S, Blaabjerg F, et al. Uncertainty compensation with coordinated control of EVs and DER systems in smart grids. Sol Energy 2023;263:111920. https://doi.org/10.1016/j.solener.2023.111920.
[6] Wang J, Han L, Zhang X, Wang Y, Zhang S. Electrical load forecasting based on variable T-distribution and dual attention mechanism. Energy 2023;283:128569. https://doi.org/10.1016/j.energy.2023.128569.
[7] Jedrzejewski A, Lago J, Marcjasz G, Weron R. Electricity price forecasting: The dawn of machine learning. IEEE Power Energy Mag 2022;20:24–31. https://doi.org/10.1109/MPE.2022.3150809.
[8] Wu B, Wang L, Zeng Y-R. Interpretable wind speed prediction with multivariate time series and temporal fusion transformers. Energy 2022;252:123990. https://doi.org/10.1016/j.energy.2022.123990.
[9 ] Wu L, Zhang Y. Attention-based encoder-decoder networks for state of charge estimation of lithium-ion battery. Energy 2023:126665.
[10] Hu Y, Xiao F. Network self attention for forecasting time series. Appl Soft Comput 2022;124:109092.
[11] Lee CT, Hashim H, Ho CS, Fan Y Van, Klemeš JJ. Sustaining the low-carbon emission development in Asia and beyond: Sustainable energy, water, transportation and low-carbon emission technology. J Clean Prod 2017;146:1–13. https://doi.org/10.1016/j.jclepro.2016.11.144.
[12] Ikram M. Models for predicting non-renewable energy competing with renewable source for sustainable energy development: Case of Asia and oceania region. Glob J Flex Syst Manag 2021;22:133–60. https://doi.org/10.1007/s40171-021-00285-7.
[13] Zhang J, Cui M, Hodge B-M, Florita A, Freedman J. Ramp forecasting performance from improved short-term wind power forecasting over multiple spatial and temporal scales. Energy 2017;122:528–41. https://doi.org/10.1016/j.energy.2017.01.104.
[14] National Infrastructure Commission et al. Smart power (national infrastructure commission report). National Infrastructure Commission, 2016.
[15] Farmanbar M, Parham K, Arild Ø, Rong C. A Widespread review of smart grids towards smart cities. Energies 2019;12:4484. https://doi.org/10.3390/en12234484.
[16] Aslam S, Herodotou H, Mohsin SM, Javaid N, Ashraf N, Aslam S. A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids. Renew Sustain Energy Rev 2021;144:110992. https://doi.org/10.1016/j.rser.2021.110992.
[17] Commentaries on the M3-Competition, October-December 2001.
[18] Bunn, D. & Farmer, E. D. Comparative models for electrical load forecasting. Working paper, 1985.
[19] Li H, Liu H, Ji H, Zhang S, Li P. Ultra-short-term load demand forecast model framework based on deep learning. Energies 2020;13:4900. https://doi.org/10.3390/en13184900.
[20] Ahmad T, Zhang D, Huang C. Methodological framework for short-and medium-term energy, solar and wind power forecasting with stochastic-based machine learning approach to monetary and energy policy applications. Energy 2021;231:120911. https://doi.org/10.1016/j.energy.2021.120911.
[21] Borunda M, Rodríguez-Vázquez K, Garduno-Ramirez R, de la Cruz-Soto J, Antunez-Estrada J, Jaramillo OA. Long-term estimation of wind power by probabilistic forecast using genetic programming. Energies 2020;13:1885. https://doi.org/10.3390/en13081885.
[22] Bui DM, Le PD, Cao MT, Pham TT, Pham DA. Accuracy improvement of various short-term load forecasting models by a novel and unified statistical data-filtering method. Int J Green Energy 2020;17:382–406. https://doi.org/10.1080/15435075.2020.1761810.
[23] Li J, Luo Y, Wei S. Long-term electricity consumption forecasting method based on system dynamics under the carbon-neutral target. Energy 2022;244:122572. https://doi.org/10.1016/j.energy.2021.122572.
[24] Gao R, Duru O. Parsimonious fuzzy time series modelling. Expert Syst Appl 2020;156:113447. https://doi.org/10.1016/j.eswa.2020.113447.
[25] Kim JH, Lee BS, Kim CH. A Study on the development of long-term hybrid electrical load forecasting model based on MLP and statistics using massive actual data considering field applications. Electr Power Syst Res 2023;221:109415. https://doi.org/10.1016/j.epsr.2023.109415.
[26] Heidarpanah M, Hooshyaripor F, Fazeli M. Daily electricity price forecasting using artificial intelligence models in the Iranian electricity market. Energy 2023;263:126011. https://doi.org/10.1016/j.energy.2022.126011.
[27] Ying C, Wang W, Yu J, Li Q, Yu D, Liu J. Deep learning for renewable energy forecasting: A taxonomy, and systematic literature review. J Clean Prod 2023;384:135414. https://doi.org/10.1016/j.jclepro.2022.135414.
[28] Alcántara A, Galván IM, Aler R. Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks. Eng Appl Artif Intell 2022;114:105128. https://doi.org/10.1016/j.engappai.2022.105128.
[29] Gomez W, Wang F-K, Lo S-C. A hybrid approach based machine learning models in electricity markets. Energy 2024;289:129988. https://doi.org/10.1016/j.energy.2023.129988.
[30] Li S, Goel L, Wang P. An ensemble approach for short-term load forecasting by extreme learning machine. Appl Energy 2016;170:22–9. https://doi.org/10.1016/j.apenergy.2016.02.114.
[31] Dash SK, Patel D. Short-term electric load forecasting using extreme learning machine - A case study of Indian power market. 2015 IEEE Power, Commun. Inf. Technol. Conf., IEEE; 2015, p. 961–6. https://doi.org/10.1109/PCITC.2015.7438135.
[32] Bhinge R, Park J, Law KH, Dornfeld DA, Helu M, Rachuri S. Toward a generalized energy prediction model for machine tools. J Manuf Sci Eng 2017;139. https://doi.org/10.1115/1.4034933.
[33] Li M, Yang Y, He Z, Guo X, Zhang R, Huang B. A wind speed forecasting model based on multi-objective algorithm and interpretability learning. Energy 2023;269:126778. https://doi.org/10.1016/j.energy.2023.126778.
[34] Mounir N, Ouadi H, Jrhilifa I. Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system. Energy Build 2023;288:113022. https://doi.org/10.1016/j.enbuild.2023.113022.
[35] Guermoui M, Gairaa K, Ferkous K, Santos DS de O, Arrif T, Belaid A. Potential assessment of the TVF-EMD algorithm in forecasting hourly global solar radiation: Review and case studies. J Clean Prod 2023;385:135680. https://doi.org/10.1016/j.jclepro.2022.135680.
[36] Radovanovic A, Nesti T, Chen B. A holistic approach to forecasting wholesale energy Market prices. IEEE Trans Power Syst 2019;34:4317–28. https://doi.org/10.1109/TPWRS.2019.2921611.
[37] Zhang Y, Guo H, Sun M, Liu S, Forrest J. A novel grey Lotka–Volterra model driven by the mechanism of competition and cooperation for energy consumption forecasting. Energy 2023;264:126154. https://doi.org/10.1016/j.energy.2022.126154.
[38] Aksan F, Suresh V, Janik P, Sikorski T. Load forecasting for the laser metal processing industry using VMD and hybrid deep learning models. Energies 2023;16:5381. https://doi.org/10.3390/en16145381.
[39] Lahouar A, Slama JBH. Day-ahead load forecast using random forest and expert input selection. Energy Convers Manag 2015;103:1040–51.
[40] Wang Y, Sun S, Chen X, Zeng X, Kong Y, Chen J, et al. Short-term load forecasting of industrial customers based on SVMD and XGBoost. Int J Electr Power Energy Syst 2021;129:106830.
[41] Dai Y, Zhao P. A hybrid load forecasting model based on support vector machinewith intelligent methods for feature selection and parameter optimization. Appl Energy 2020;279:115332.
[42] Hao Y, Yang W, Yin K. Novel wind speed forecasting model based on a deep learning combined strategy in urban energy systems. Expert Syst Appl 2023;219:119636. https://doi.org/10.1016/j.eswa.2023.119636.
[43] Fan G-F, Zhang L-Z, Yu M, Hong W-C, Dong S-Q. Applications of random forest in multivariable response surface for short-term load forecasting. Int J Electr Power Energy Syst 2022;139:108073. https://doi.org/10.1016/j.ijepes.2022.108073.
[43] Shi H, Xu M, Li R. Deep learning for household load forecasting—A novel pooling deep RNN. IEEE Trans Smart Grid 2018;9:5271–80. https://doi.org/10.1109/TSG.2017.2686012.
[44] Fazlipour Z, Mashhour E, Joorabian M. A deep model for short-term load forecasting applying a stacked autoencoder based on LSTM supported by a multi-stage attention mechanism. Appl Energy 2022;327:120063. https://doi.org/10.1016/j.apenergy.2022.120063.
[45] Qin C-X, Qu D. Towards understanding attention-based speech recognition models. IEEE Access 2020;8:24358–69. https://doi.org/10.1109/ACCESS.2020.2970758.
[46] Meng Z, Xie Y, Sun J. Short-term load forecasting using neural attention model based on EMD. Electr Eng 2021. https://doi.org/10.1007/s00202-021-01420-4.
[47] Meng Z, Xie Y, Sun J. Short-term load forecasting using neural attention model based on EMD. Electr Eng 2021. https://doi.org/10.1007/s00202-021-01420-4.
[48] Zhang S, Chen Y, Xiao J, Zhang W, Feng R. Hybrid wind speed forecasting model based on multivariate data secondary decomposition approach and deep learning algorithm with attention mechanism. Renew Energy 2021;174:688–704. https://doi.org/10.1016/j.renene.2021.04.091.
[49] Huang C, Shen Y, Chen Y, Chen H. A novel hybrid deep neural network model for short‐term electricity price forecasting. Int J Energy Res 2021;45:2511–32. https://doi.org/10.1002/er.5945.
[50] Zhou M, Zhu Z, Hu F, Bian K, Lai W, Hu T. Short‐term commercial load forecasting based on peak‐valley features with the TSA‐ELM model. Energy Sci Eng 2022;10:2622–36. https://doi.org/10.1002/ese3.1203.
[51] Zhang M, Guo H, Sun M, Liu S, Forrest J. A novel flexible grey multivariable model and its application in forecasting energy consumption in China. Energy 2022;239:122441. https://doi.org/10.1016/j.energy.2021.122441.
[52] Li L-L, Wen S-Y, Tseng M-L, Wang C-S. Renewable energy prediction: A novel short-term prediction model of photovoltaic output power. J Clean Prod 2019;228:359–75. https://doi.org/10.1016/j.jclepro.2019.04.331.
[53] Gomez W, Wang F-K, Amogne ZE. Electricity load and price forecasting using a hybrid method based bidirectional long short-term memory with attention mechanism model. Int J Energy Res 2023;2023:1–18. https://doi.org/10.1155/2023/3815063.
[54] Daubechies I, Lu J, Wu HT. Synchrosqueezed wavelet transforms: An empirical mode decomposition-like tool. Appl Comput Harmon Anal. 2011;30(2):243–261. https://doi.org/10.1016/j.acha.2010.08.002.

[55] Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc London Ser A Math Phys Eng Sci 1998;454:903–95. https://doi.org/10.1098/rspa.1998.0193.
[56] Wu Z, Huang NE. Esemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 2009;1:1–41. https://doi.org/10.1142/S1793536909000047.
[57] Lei Y, He Z, Zi Y. Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mech Syst Signal Process 2009;23:1327–38. https://doi.org/10.1016/j.ymssp.2008.11.005.
[58] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997;9:1735–80. https://doi.org/10.1162/neco.1997.9.8.1735.
[59] Wu K, Wu J, Feng L, Yang B, Liang R, Yang S, et al. An attention‐based CNN‐LSTM‐BiLSTM model for short‐term electric load forecasting in integrated energy system. Int Trans Electr Energy Syst 2021;31. https://doi.org/10.1002/2050-7038.12637.
[60] Atef S, Eltawil AB. Assessment of stacked unidirectional and bidirectional long short-term memory networks for electricity load forecasting. Electr Power Syst Res 2020;187:106489. https://doi.org/10.1016/j.epsr.2020.106489.
[59] Wu K, Wu J, Feng L, Yang B, Liang R, Yang S, et al. An attention‐based CNN‐LSTM‐BiLSTM</scp> model for short‐term electric load forecasting in integrated energy system. Int Trans Electr Energy Syst 2021;31. https://doi.org/10.1002/2050-7038.12637.
[60] Vapnik VN. The nature of statistical learning theory. New York, NY: Springer New York; 2000. https://doi.org/10.1007/978-1-4757-3264-1.
[61] Liu H, Mi X, Li Y, Duan Z, Xu Y. Smart wind speed deep learning based multi-step forecasting model using singular spectrum analysis, convolutional gated recurrent unit network and support vector regression. Renew Energy 2019;143:842–54. https://doi.org/10.1016/j.renene.2019.05.039.
[62] Campodonico Avendano IA, Dadras Javan F, Najafi B, Moazami A, Rinaldi F. Assessing the impact of employing machine learning-based baseline load prediction pipelines with sliding-window training scheme on offered flexibility estimation for different building categories. Energy Build 2023;294:113217. https://doi.org/10.1016/j.enbuild.2023.113217.
[63] Zhen L, Zhang L, Yang T, Zhang G, Li Q, Ouyang H. Simultaneous prediction for multiple source–loads based sliding time window and convolutional neural network. Energy Reports 2022;8:6110–25. https://doi.org/10.1016/j.egyr.2022.04.041.
[64] J. Snoek, H. Larochelle, R. Adams, Practical Bayesian optimization of machine learning algorithms, Adv. Neural Inf. Process. Syst. 4 (2012) 2951–2959.
[65] Shahriari B, Swersky K, Wang Z, Adams RP, de Freitas N. Taking the Human Out of the Loop: A Review of Bayesian Optimization. Proc IEEE 2016;104:148–75. https://doi.org/10.1109/JPROC.2015.2494218.
[66] Injadat M, Salo F, Nassif AB, Essex A, Shami A. Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection. 2018 IEEE Glob. Commun. Conf., IEEE; 2018, p. 1–6. https://doi.org/10.1109/GLOCOM.2018.8647714.
[67] Stojković M, Kostić S, Plavšić J, Prohaska S. A joint stochastic-deterministic approach for long-term and short-term modelling of monthly flow rates. J Hydrol 2017;544:555–66. https://doi.org/10.1016/j.jhydrol.2016.11.025.
[68] Diebold FX. Comparing predictive accuracy, twenty years later: A personal perspective on the use and abuse of Diebold–Mariano tests. J Bus Econ Stat 2015;33:1–1. https://doi.org/10.1080/07350015.2014.983236.
[69] Samuels JD, Sekkel RM. Model Confidence Sets and forecast combination. Int J Forecast 2017;33:48–60. https://doi.org/10.1016/j.ijforecast.2016.07.004.
[70] https://github.com/JackAndCole/short-term-wind-speed-forecasting/tree/main/data
[71] https://www.dropbox.com/sh/1dczb673bx9kxzl/AABII5ePMWdFhAk-dEcRGS1La?dl=0