Best-tree wavelet packet transform bidirectional GRU for short-term load forecasting
Pages 13545 - 13577
Abstract
This work proposes the short-term load forecasting (STLF) using a combination of wavelet transform (WT) and bidirectional gated recurrent unit (BGRU). Selection of the best wavelet basis using the Shannon entropy cost function is introduced in this paper. Since entropy is a measure of the average amount of information, Shannon's entropy has been used to select nodes from the wavelet tree that have more information. The best high- and low-frequency features selected by the Shannon entropy are applied to the BGRU for STLF. In addition, a new time coding approach called the cyclical encoding is designed that appropriately models the periods and time patterns in the electrical load time series. The proposed best-tree wavelet packet transform bidirectional gated recurrent unit (BT-WPT-BGRU) method shows superior performance compared to the wavelet transform and neuro-evolutionary algorithm (WT-NEA), wavelet and collaborative representation transforms (WACRT), convolutional and recurrent neural network (CARNN), WT–BGRU, full wavelet packet transform BGRU (FWPT-BGRU), BT-WPT bidirectional LSTM (BT-WPT-BLSTM) and BT-WPT-BGRU (with one-hot encoding). The BT-WPT-BGRU model performs 71.7%, 58.8%, 58.2%, 17.6%, 12.5%, 12.5% and 6.6% better than WT-NEA, WACRT, CARNN, WT-BGRU, FWPT-BGRU, BT-WPT-BGRU (with one-hot encoding) and BT-WPT-BLSTM in terms of the MAPE metric in ISONE dataset, respectively.
References
[1]
Hou H, Liu C, Wang Q, Wu X, Tang J, Shi Y, and Xie C Review of load forecasting based on artificial intelligence methodologies, models, and challenges Electric Power Syst Res 2022 210 108067
[2]
Keshvari R, Imani M, and Parsa Moghaddam M A clustering-based short-term load forecasting using independent component analysis and multi-scale decomposition transform J Supercomput 2022 78 7908-7935
[3]
Papalexopoulos AD and Hesterberg TC A regression-based approach to short-term system load forecasting IEEE Trans Power Syst 1990 5 4 1535-1547
[4]
Jeong D, Park C, and Ko YM Short-term electric load forecasting for buildings using logistic mixture vector autoregressive model with curve registration Appl Energy 2021 282 Part B 116249
[5]
Imani M (2022) Fuzzy-based weighting long short-term memory network for demand forecasting. J Supercomput
[6]
Taylor J Short-term electricity demand forecasting using double seasonal exponential smoothing J Oper Res Soc 2003 54 799-805
[7]
Taylor JW An evaluation of methods for very short-term load forecasting using minute-by-minute British data Int J Forecast 2008 24 4 645-658
[8]
Bracale A, Caramia P, De Falco P, and Hong T A multivariate approach to probabilistic industrial load forecasting Electric Power Syst Res 2020 187 106430
[9]
Cao X, Dong S, Wu Z, Jing Y (2015) a data-driven hybrid optimization model for short-term residential load forecasting. In: IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, pp 283–287
[10]
Din GMU, Marnerides AK (2017) Short term power load forecasting using Deep Neural Networks. In: 2017 International Conference on Computing, Networking and Communications (ICNC), Santa Clara, CA, pp 594–598
[11]
Hoori AO and Motai Y Multicolumn RBF Network IEEE Trans Neural Netw Learn Syst 2018 29 4 766-778
[12]
Yu H, Reiner PD, Xie T, Bartczak T, and Wilamowski BM An incremental design of radial basis function networks IEEE Trans Neural Netw Learn Syst 2014 25 10 1793-1803
[13]
Amarasinghe K, Marino DL, Manic M (2017) Deep neural networks for energy load forecasting. In: 2017 IEEE 26th international symposium on industrial electronics (ISIE), Edinburgh, pp.1483–1488
[14]
Khuntia SR, Rueda JL, and van der Meijden MAMM Forecasting the load of electrical power systems in mid and long-term horizons: a review IET Gener Transm Distrib 2016 10 16 3971-3977
[15]
Li S, Goel L, and Wang P An ensemble approach for short-term load forecasting by extreme learning machine Appl Energy 2016 170 22-29
[16]
Kamruzzaman M, Bhusal N, and Benidris M A convolutional neural network-based approach to composite power system reliability evaluation Int J Electr Power Energy Syst 2022 135 107468
[17]
Shi H, Xu M, and Li R Deep learning for household load forecasting-a novel pooling deep RNN IEEE Trans Smart Grid 2018 9 5 5271-5280
[18]
Imani M (2019) Long short-term memory network and support vector regression for electrical load forecasting. In: 2019 International Conference on Power Generation Systems and Renewable Energy Technologies (PGSRET), Istanbul, Turkey, pp 1–6
[19]
Imani M, Ghassemian H (2019) Sequence to image transform based convolutional neural network for load forecasting. In: 2019 27th Iranian Conference on Electrical Egineering (ICEE), Yazd, Iran, pp 1362–1366
[20]
Shafiei Chafi Z, Afrakhte H (2021) Short-term load forecasting using neural network and particle swarm optimization (PSO) algorithm. Mathematical Problems in Engineering, vol. 2021
[21]
Kong Z, Zhang C, Lv H, Xiong F, and Fu Z Multimodal feature extraction and fusion deep neural networks for short-term load forecasting IEEE Access 2020 8 185373-185383
[22]
Alhussein M, Aurangzeb K, and Haider SI Hybrid CNN-LSTM model for short-term individual household load forecasting IEEE Access 2020 8 180544-180557
[23]
Gao Y, Fang Y, Dong H, and Kong Y A multifactorial framework for short-term load forecasting system as well as the jinan's case study IEEE Access 2020 8 203086-203096
[24]
Guo W, Che L, Shahidehpour M, Wan X (2021) Machine-learning based methods in short-term load forecasting. Electric J 34(1), Article ID 106884
[25]
Aly HHH (2020) A proposed intelligent short-term load forecasting hybrid models of ANN, WNN and KF based on clustering techniques for smart grid. Electr Power Syst Res 182, Article ID 106191
[26]
Saroha S, Zurek-Mortka M, Szymanski JR, Shekher V, and Singla P Forecasting of market clearing volume using wavelet packet-based neural networks with tracking signals Energies 2021 14 19 6065
[27]
Singla P, Duhan M, and Saroha S A hybrid solar irradiance forecasting using full wavelet packet decomposition and bi-directional long short-term memory (BiLSTM) Arab J Sci Eng 2022 47 14185-14211
[28]
Chen Y, Luh PB, Guan C, Zhao Y, Michel LD, Coolbeth MA, Friedland PB, and Rourke SJ Short-term load forecasting: similar day-based wavelet neural network IEEE Trans Power Syst 2010 25 322-330
[29]
Vautrin D, Artusi X, Lucas M-F, and Farina D A novel criterion of wavelet packet best basis selection for signal classification with application to brain-computer interfaces IEEE Trans Biomed Eng 2009 56 2734-2738
[30]
Saito N, Coifman RR (1997) Local discriminant bases, In: Proceedings of the SPIE wavelet applications in signal and image processing.
[31]
Mallat SG A theory for multiresolution signal decomposition: the wavelet representation IEEE Trans Pattern Anal Mach Intell 1989 11 674-693
[32]
Kováˇc S, Conok GM, Halenár I, and Važan P Comparison of heat demand prediction using wavelet analysis and neural network for a district heating network Energies 2021 14 1545
[33]
Coifman RR and Wickerhauser MV Entropy-based algorithms for best basis selection IEEE Trans Inf Theory 1992 38 713-718
[34]
Hochreiter S, Bengio Y, Frasconi P, Schmidhuber J (2001) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies
[35]
Graves A (2013) Generating sequences with recurrent neural networks." arXiv preprint arXiv:1308.0850
[36]
Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv preprint arXiv:1412.3555
[37]
Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self- normalizing neural networks, Adv Neural Inf Processi Syst, 972–981
[38]
Deihimi A and Showkati H Application of echo state networks in short-term electric load forecasting Energy 2012 39 327-340
[39]
Reis AJR and da Silva APA Feature extraction via multiresolution analysis for short-term load forecasting IEEE Trans Power Syst 2005 20 189-198
[40]
Amjady N and Keynia F Short-term load forecasting of power systems by combination of wavelet transform and neuro-evolutionary algorithm Energy 2009 34 46-57
[41]
Ceperic E, Ceperic V, and Baric A A strategy for short-term load forecasting by support vector regression machines IEEE Trans Power Syst 2013 28 4356-4364
[42]
Hu Z, Bao Y, and Xiong T Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression Appl Soft Comput 2014 25 15-25
[43]
Imani M, Ghassemian H (2019) Residential load forecasting using wavelet and collaborative representation transforms. Appl Energy, 253
[44]
Eskandari H, Imani M, Moghaddam MP (2021) Convolutional and recurrent neural network based model for short-term load forecasting. Electr Power Syst Res 195, Article ID 107173
[45]
Guan C, Luh PB, Michel LD, Wang Y, and Friedland PB Very short-term load forecasting: wavelet neural networks with data pre-filtering IEEE Trans Power Syst 2013 28 30-41
[46]
Shamsollahi P, Cheung KW, Chen Q, Germain EH (2001) A neural network based very short term load forecaster for the interim ISO New England electricity market system. In: 22nd IEEE PES International Conference on Power Industry. Computer Applications, pp 217–222
[47]
Li S, Wang P, and Goel L Short-term load forecasting by wavelet transform and evolutionary extreme learning machine Electric Power Syst Res 2015 122 96-103
Recommendations
Short-term load forecasting using lifting scheme and ARIMA models
Research highlights Short-term load forecasting is achieved using a lifting scheme and autoregressive integrated moving average (ARIMA) models. Lifting scheme is embedded into the ARIMA models to enhance forecasting accuracy. The Coeflet 12 wavelet is ...
Short-Term Load Forecasting Based on Rough Set and Wavelet Neural Network
CIS '08: Proceedings of the 2008 International Conference on Computational Intelligence and Security - Volume 02This paper aims for developing a method, based on rough set (RS) reduction and wavelet neural network (WNN), to improve the efficiency of short-term load forecasting (STLF). The RS reduction could erase redundant characters and this makes it possible to ...
A novel trilinear deep residual network with self-adaptive Dropout method for short-term load forecasting
Highlights- A novel deep residual network with self-adaptive Dropout method is proposed.
- A ...
AbstractShort-term load forecasting underlies the effective energy management. However, accurate short-term load forecasting is a big challenge owing to the significant uncertainty and volatility of load demand. Deep learning has successfully ...
Comments
Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 27 March 2023
Accepted: 12 March 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Jan 2025