Journal of Energy Management and Technology

Journal of Energy Management and Technology

Electricity price and load demand forecasting using an adaptive hybrid BiLSTM model based on wavelet transform technique and Pareto optimization: an application in the smart cities

Document Type : Original Article

Authors
Mohammad Asadpour 1
Nazila Pourhaji 1
Ali Ahmadian 2
1 Faculty Of Electrical And Computer Engineering, University Of Tabriz, 29 Bahman Blvd, Tabriz, Iran
2 Department of Electrical Engineering, University of Bonab, Bonab 5551761167
10.22109/jemt.2023.414599.1467
Abstract
Accurate forecasting of electricity price and load demand is an essential requirement for managing energy production and consumption in a smart city. In this paper, an adaptive hybrid model is presented for accurate short-term forecasting of electricity price and load demand based on wavelet transform (WT) decomposition, mutual information (MI) and interaction gain (IG) feature selection methods, and Pareto optimization technique with BiLSTM network called WT-MI-IG-BiLSTM. In this model, first, the electricity price and load demand signals are decomposed using the WT technique. Then, the variables that have the most excellent effect on the prediction are selected by the MI and IG feature selection method. In the forecasting stage, prediction is made with the BiLSTM network, and the combination of networks prediction vectors provides the final prediction result. PJM electricity market price and load demand data sets in 2006 and 2018 and five error metrics including RMSE, MAE, MAPE, Variance, and R-Squared are used to evaluate the model. To demonstrate the high capability of the WT-MI-IG-BiLSTM model, the proposed model has been compared with the MI-IG-BiLSTM, WT-MI-IG-LSTM, and MI-IG-LSTM models. Based on the obtained results, the proposed WT-MI-IG-BiLSTM model compared to the MI-IG-BiLSTM model, which is the best benchmark model, has 17-18.16% improvement in accuracy of electricity price forecasting and 21.8% in accuracy of electricity load forecasting. Finally, the Pareto optimization algorithm has implemented on the model, and a set of optimal models with optimal accuracy and execution time has presented in the Pareto front chart.
Keywords
Wavelet transform
Mutual information
Interaction gain
LSTM
BiLSTM

Subjects

1. de Guimarães JCF, Severo EA, Felix Júnior LA, da Costa WPLB, Salmoria FT. Governance and quality of life in smart
cities: Towards sustainable development goals. J Clean Prod. 2020 Apr 20;253.
2. Silva BN, Khan M, Han K. Towards sustainable smart cities: A review of trends, architectures, components, and open
challenges in smart cities. Vol. 38, Sustainable Cities and Society. Elsevier Ltd; 2018. p. 697–713.
3. Mujeeb S, Javaid N, Ilahi M, Wadud Z, Ishmanov F, Afzal MK. Deep long short-term memory: A new price and load
forecasting scheme for big data in smart cities. Sustainability (Switzerland). 2019 Feb 14;11(4).
4. Elattar EE, Goulermas J, Wu QH. Electric load forecasting based on locally weighted support vector regression. IEEE
Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews. 2010 Jul;40(4):438–47.
5. Kumar S, Hussain L, Banarjee S, Reza M, Tech B, Students Y. Energy Load Forecasting using Deep Learning Approach-
LSTM and GRU in Spark Cluster.
6. Tschora L, Pierre E, Plantevit M, Robardet C. Electricity price forecasting on the day-ahead market using machine
learning. Appl Energy. 2022 May 1;313.
7. Kong X, Li C, Wang C, Zhang Y, Zhang J. Short-term electrical load forecasting based on error correction using dynamic
mode decomposition. Appl Energy. 2020 Mar 1;261.
8. Weron R. Electricity price forecasting: A review of the state-of-the-art with a look into the future. Vol. 30, International
Journal of Forecasting. Elsevier B.V.; 2014. p. 1030–81.
9. Soliman A hady S, AI-Kandari AM. Electrical load forecasting: modeling and model construction. ELSEVIER; 2010.
10. Zhao Z, Wang C, Nokleby M, Miller CJ. Improving Short Term Electricity Price Forecasting Using Day-Ahead LMP
with ARIMA Models. 2017.
11. Martínez-Alvarez F, Troncoso A, Riquelme JJ, Jesu´s J, Aguilar-Ruiz S. Energy Time Series Forecasting Based on
Pattern Sequence Similarity. 2010.
12. Moradi M, Weng Y, Lai YC. Defending Smart Electrical Power Grids against Cyberattacks with Deep Q -Learning .
PRX Energy. 2022 Nov 28;1(3).
13. Razavi SE, Moradi MA, Shamaghdari S, Menhaj MB. Adaptive optimal control of unknown discrete-time linear sys-
tems with guaranteed prescribed degree of stability using reinforcement learning. Int J Dyn Control. 2022 Jun
1;10(3):870–8.
14. Peng L, Liu S, Liu R, Wang L. Effective long short-term memory with differential evolution algorithm for electricity
price prediction. Energy. 2018 Nov 1;162:1301–14.
15. XY Zhang, S Kuenzel, N Colombo, C Watkins. Short-Term Load Forecasting Method based on. 2021;
16. Jahangir H, Tayarani H, Gougheri SS, Golkar MA, Ahmadian A, Elkamel A. Deep Learning-Based Forecasting Ap-
proach in Smart Grids with Microclustering and Bidirectional LSTM Network. IEEE Transactions on Industrial
Electronics. 2021 Sep 1;68(9):8298–309.
17. Tian C, Hao Y, Hu J. A novel wind speed forecasting system based on hybrid data preprocessing and multi-objective
optimization. Appl Energy. 2018 Dec 1;231:301–19.
18. Shayeghi H, Ghasemi A, Moradzadeh M, Nooshyar M. Simultaneous day-ahead forecasting of electricity price and
load in smart grids. Energy Convers Manag. 2015 May 1;95:371–84.
19. Zhang CY, Chen CLP, Gan M, Chen L. Predictive Deep Boltzmann Machine for Multiperiod Wind Speed Forecast-
ing. IEEE Trans Sustain Energy. 2015 Oct 1;6(4):1416–25.
20. Zhang Y, Li C, Li L. Wavelet transform and Kernel-based extreme learning machine for electricity price forecasting.
Energy Systems. 2018 Feb 1;9(1):113–34.
21. Branco NW, Cavalca MSM, Stefenon SF, Leithardt VRQ. Wavelet LSTM for Fault Forecasting in Electrical Power
Grids. Sensors. 2022 Nov 1;22(21).
22. Xiang J, Qiu Z, Hao Q, Cao H. Multi-time scale wind speed prediction based on WT-bi-LSTM. 2020; Available from:
https://doi.org/10.1051/matecconf/202030
23. Su H, Zio E, Zhang J, Xu M, Li X, Zhang Z. A hybrid hourly natural gas demand forecasting method based
on the integration of wavelet transform and enhanced Deep-RNN model. 2019;178:585–97. Available from:
https://hal.archives-ouvertes.fr/hal-02428545
24. Zainab A, Syed D, Ghrayeb A, Abu-Rub H, Refaat SS, Houchati M, et al. A multiprocessing-based sensitivity
analysis of machine learning algorithms for load forecasting of electric power distribution system. IEEE Access.
2021;9:31684–94.
25. Ahmad A, Javaid N, Mateen A, Awais M, Khan ZA. Short-Term load forecasting in smart grids: An intelligent modu-
lar approach. Energies (Basel). 2019 Jan 1;12(1).
26. Preniqi V, Mishra BK, Thakker D, Feigl E, Mokryani G, Abdullatif A, et al. Comparative Study of Shortterm Elec-
tricity Price Forecasting Models to Optimise Battery Consumption. In: 2020 International Conferences on Inter-
net of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical
and Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics) [Internet]. IEEE; 2020. p. 342–9. Available from: https://ieeexplore.ieee.org/document/9291599/
27. Bouktif S, Fiaz A, Ouni A, Serhani MA. Optimal deep learning LSTM model for electric load forecasting using feature
selection and genetic algorithm: Comparison with machine learning approaches. Energies (Basel). 2018;11(7).
28. Chang Z, Zhang Y, Chen W. Electricity price prediction based on hybrid model of adam optimized LSTM neural
network and wavelet transform. Energy. 2019 Nov 15;187.
29. SK Aggarwal, LM Saini, A Kumar. Electricity Price Forecasting in Ontario Electricity Market Using Wavelet Transform
in Artificial Neural Network Based Model. 2008;
30. da Rocha Reis AJ, Alves da Silva AP. Feature extraction via multiresolution analysis for short-term load fore-
casting. IEEE Transactions on Power Systems. 2005 Feb;20(1):189–98.
31. Memarzadeh G, Keynia F. Short-term electricity load and price forecasting by a new optimal LSTM-NN based predic-
tion algorithm. Electric Power Systems Research. 2021 Mar 1;192.
32. Amjady N, Keynia F. Day-ahead price forecasting of electricity markets by mutual information technique and cascaded
neuro-evolutionary algorithm. IEEE Transactions on Power Systems. 2009;24(1):306–18.
33. Kwak N, Choi CH. Input Feature Selection by Mutual Information Based on Parzen Window. 2002.
34. Liu H, Mi X  wei, Li Y fei. Wind speed forecasting method based on deep learning strategy using empirical wavelet
transform, long short term memory neural network and Elman neural network. Energy Convers Manag. 2018 Jan
15;156:498–514.
35. Meng A, Wang P, Zhai G, Zeng C, Chen S, Yang X, et al. Electricity price forecasting with high penetration of renew-
able energy using attention-based LSTM network trained by crisscross optimization. Energy. 2022 Sep 1;254.
36. Zhou S, Zhou L, Mao M, Tai HM, Wan Y. An Optimized Heterogeneous Structure LSTM Network for Electricity Price
Forecasting. IEEE Access. 2019;7:108161–73.
37. Toubeau JF, Bottieau J, Vallee F, de Greve Z. Deep Learning Based Multivariate Probabilistic Forecasting for Short-Term
Scheduling in Power Markets. IEEE Transactions on Power Systems. 2019 Mar 1;34(2):1203–15.
38. Huang CG, Huang HZ, Li YF. A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions.
IEEE Transactions on Industrial Electronics. 2019 Nov 1;66(11):8792–802.
39. Tong W, Li L, Zhou X, Hamilton A, Zhang K. Deep learning PM2.5 concentrations with bidirectional LSTM RNN. Air
Qual Atmos Health. 2019 Apr 2;12(4):411–23.
40. Navon A, Shamsian A, Chechik G, Fetaya E. Learning the Pareto Front with Hypernetworks. 2020 Oct 8; Available
from: http://arxiv.org/abs/2010.04104
41. Horn D, Bischl B. Multi-objective parameter configuration of machine learning algorithms using model-based opti-
mization. 2016.
Journal of Energy Management and Technology
Volume 8, Issue 3
Summer 2024
Pages 178-195

  • Receive Date 02 September 2023
  • Revise Date 01 October 2023
  • Accept Date 24 October 2023