Çift yönlü tekrarlayan sinir ağlarına sahip LSTM ve GRU tabanlı elektrik yükü tahmin modelleri

Year 2025, Volume: 14 Issue: 4

Khalid Alhashemi , Ökkeş Tolga Altınöz

Abstract

Doğru elektrik yük tahmini, elektrik sistemi planlaması, güvenilirliği ve sürdürülebilirliği için çok önemlidir ve daha verimli piyasalar ile azaltılmış sera gazı emisyonlarına olanak tanır. Bu çalışma, 2023 yılının tamamı için bir gün önceden elektrik talebini tahmin etmek üzere birleşik bir model geliştirmek amacıyla, özellikle çift yönlü tekrarlayan sinir ağları olmak üzere, derin öğrenme algoritmalarından yararlanmaktadır. Modelin performansı aylık bazda değerlendirilmiş olup, farklı zaman dilimleri boyunca tahmin yeteneklerinin ayrıntılı bir değerlendirmesine olanak sağlamıştır. Dört sinir ağı algoritması karşılaştırılmıştır: Uzun Kısa Süreli Bellek (LSTM), Çift Yönlü LSTM, Gated Recurrent Unit (GRU) ve Çift Yönlü GRU. GRU modeli üstün performans sergileyerek, Ekim ayında 0.8526 R-kare değeri ve Mart ayında %2.34 Ortalama Mutlak Yüzde Hatası (MAPE) elde etmiştir. Bu sonuçlar, önerilen modelin elektrik talep tahmini için etkili bir araç olma potansiyelini vurgulamakta, yenilenebilir enerji kaynaklarının entegrasyonunu desteklemekte ve şebeke dayanıklılığını artırmaktadır.

Keywords

Yük tahmini , Uzun Kısa Süreli Bellek , Geçitli tekrarlayan birim , Çift yönlü tekrarlayan sinir ağları

Electricity load forecasting models based on LSTM and GRU with their bidirectional recurrent neural networks

Abstract

Accurate electricity load forecasting is crucial for power system planning, reliability, and sustainability, enabling more efficient markets and reduced greenhouse gas emissions. This study leverages deep learning algorithms, specifically bidirectional recurrent neural networks, to develop a unified model for predicting one day-ahead electricity demand for the entire year of 2023. The model's performance was evaluated on a monthly basis, allowing for a detailed assessment of its forecasting capabilities across different time periods. Four neural network algorithms were compared: Long Short-Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit (GRU), and Bidirectional GRU. The GRU model demonstrated superior performance, achieving an R-squared value of 0.8526 in October and a Mean Absolute Percentage Error (MAPE) of 2.34% in March. These results highlight the potential of the proposed model as an effective tool for electricity demand forecasting, supporting the integration of renewable energy sources and enhancing grid resilience.

Keywords

Load forecasting , Long short-term memory , Gated recurrent unit , Bidirectional recurrent neural networks

References

• J. C. Lu, X. Zhang and W. Sun, A real-time adaptive forecasting algorithm for electric power load. In 2005 IEEE/PES Transmission & Distribution Conference & Exposition, Asia and Pacific, pp. 1-5, IEEE, August, 2005.
•    S. Karthika, V. Margaret and K. Balaraman, Hybrid short term load forecasting using ARIMA-SVM. In 2017 Innovations in Power and Advanced Computing Technologies (i-PACT), pp. 1-7, IEEE, April 2017.
•    M. E. Sertkaya, M. Durmuş and B. Ergen, Detection of early stage alzheimer’s disease in gradient-based MR images using deep learning methods. NÖHÜ Mühendislik Bilimleri Dergisi, 13(3), 2024 https://doi.org/10.28948/ngumuh.139083 0.
•    X. Glorot and Y. Bengio, Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, pp. 315-323, June 2011.
•    D. Hendrycks and K. Gimpel, Gaussian error linear units (GELUs). Scientific Research Publishing, 2016. https://doi.org/10.48550/arXiv.1606.08415.
•    Y. Liao, H. Tang, R. Li, L. Ran and L. Xie, Response prediction for linear and nonlinear structures based on data-driven deep learning. Applied Sciences, 13 (10), 5918, 2023. https://doi.org/10.3390/app13105918.
•    S. Li, W. Li, C. Cook, C. Zhu and Y. Gao, Independently Recurrent Neural Network (IndRNN): Building a longer and deeper RNN. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5457-5466, 2018.
•    H. Lai, J. Shen, W. Zhang and Y. Yu, Bidirectional model-based policy optimization. In International Conference on Machine Learning, pp. 5618-5627, PMLR, November 2020.
•    G. Zhang, B. E. Patuwo and M. Y. Hu, Forecasting with artificial neural networks: The state of the art. international journal of forecasting, 14 (1), 35-62, 1998. https://doi.org/10.1016/S0169-2070(97)00044-7
• S. F. Ahmed, M. S. B. Alam, M. Hassan, M. R. Rozbu, T. Ishtiak, N. Rafa, M. Mofijur, A. B. M. Shawkat Ali and A. H. Gandomi, Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56 (11), pp. 13521-13617, 2023. https://doi.org/10.1007/s1046 2-023-10466-8.
• I. Goodfellow, Y. Bengio and A. Courville, Deep Learning. MIT Press, 2016.
• S. Hochreiter and J. Schmidhuber, Long Short-Term Memory. Neural Comput, 9 (8), 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735.
• M. Mozer, A focused backpropagation algorithm for temporal pattern recognition. Complex Systems, 3, 349-381, 1989.
• W. Kong, Z. Y. Dong, Y. Jia, D. J. Hill and Y. Xu, Short-term residential load forecasting based on LSTM recurrent neural network. IEEE transactions on smart grid, 10(1), 841-851, 2019. https://doi.org/10.1109/TS G.2017.2753802.
• S. Motepe, A. N. Hasan and R. Stopforth, Improving Load Forecasting Process for a Power Distribution Network Using Hybrid AI and Deep Learning Algorithms. IEEE Access, 7, 82584-82598, 2019. https://doi.org/10.1109/ACCESS.2019.2923796.
• Z. C. Lipton, J. Berkowitz and C. Elkan, A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv (Cornell University), 2015. https://doi. org/10.48550/arxiv.1506.00019.
• K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk and Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078. 2014.
• N. Gruber and A. Jockisch, Are GRU cells more specific and LSTM cells more sensitive in motive classification of text?. Frontiers in artificial intelligence, 3, 40, 2020. https://doi.org/10.3389/frai. 2020.00040.
• M. Abumohsen, A. Y. Owda and M. Owda, Electrical Load Forecasting Using LSTM, GRU, and RNN Algorithms. Energies, 16(5), 2283, 2023. https://doi. org/10.3390/en16052283.
• Y. Su and C. C. J. Kuo, On extended long short-term memory and dependent bidirectional recurrent neural network. Neurocomputing, 356, 151-161, 2019. https:// doi.org/10.1016/j.neucom.2019.04.044.
• C. Cai, Y. Tao, T. Zhu and Z. Deng, Short-Term Load Forecasting Based on Deep Learning Bidirectional LSTM Neural Network. Applied Sciences, 11 (17), 8129, 2021. https://doi.org/10.3390/app11178129.
• M. Schuster and K. K. Paliwal, Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45 (11), 2673-2681, 1997. https://doi.org/ 10.1109/78.650093.
• G. Alex, A. Mohamed and G. Hinton, Speech recognition with deep recurrent neural networks. In 2013 IEEE international conference on acoustics, speech and signal processing, pp. 6645-6649. Ieee, 2013. https://doi.org/10.48550/arXiv.1303.5778.
• J. Du, Y. Cheng, Q. Zhou, J. Zhang, X. Zhang and G. Li, Power load forecasting using BiLSTM-attention. IOP Conference Series: Earth and Environmental Science, 440 (3), 032115, 2020. https://doi.org/10.10 88/1755-1315/440/3/032115.
• C. Xiong, S. Merity and R. Socher, Dynamic memory networks for visual and textual question answering. In International conference on machine learning, pp. 2397-2406, PMLR, 4 March 2016.
• Y. Cheng, L. Yao, G. Xiang, G. Zhang, T. Tang and L. Zhong, Text sentiment orientation analysis based on multi-channel CNN and bidirectional GRU with attention mechanism. IEEE Access, 8, 134964-134975, 2020. https://doi.org/10.1109/ACCESS.2020.3005823.
• Y. Cheng, H. Sun, H. Chen, M. Li, Y. Cai, Z. Cai and J. Huang, Sentiment analysis using multi-head attention capsules with multi-channel CNN and bidirectional GRU. IEEE Access, 9, 60383-60395, 2021. https://doi. org/10.1109/access.2021.3073988.
• H. He, H. Wang, H. Ma, X. Liu, Y. Jia and G, Gong, Research on short-term power load forecasting based on Bi-GRU. Journal of Physics: Conference Series, 1639 (1), p. 012017, October 2020.
• S. Wang, C. Shao, J. Zhang, Y. Zheng and M. Meng, Traffic flow prediction using bi-directional gated recurrent unit method. Urban informatics, 1(1), 16, 2022. https://doi.org/10.1007/s44212-022-00015-z.
• A. Grami, Probability, random variables, statistics, and random processes: Fundamentals & applications. John Wiley & Sons, 2019.
• PJM, Data Miner 2 [online]. https://dataminer2.pjm. com/feed/hrl_load_metered, Accessed 02 May 2024.
• G. Zhao, A Test of non null hypothesis for linear trends in proportions. Communications in Statistics-Theory and Methods, 44 (8), 1621-1639, 2015. https://doi.org /10.1080/03610926.2013.776687.
• Y. LeCun, Y. Bengio and G. Hinton, Deep Learning. nature, 521 (7553), 436-444, 2015. https://doi.org/10. 1038/nature14539.
• A. Colin Cameron and F. A. G. Windmeijer, An R-squared measure of goodness of fit for some common nonlinear regression models. Journal of econometrics, 77 (2), 329-342, 1997. https://doi.org/10.1016/S0304-4076(96)01818-0.
• T. Hong and S. Fan, Probabilistic electric load forecasting: A tutorial review. International Journal of Forecasting, 32 (3), 914-938, 2016. https://doi.org/10. 1016/j.ijforecast.2015.11.011.
• A. de Myttenaere, B. Golden, B. Le Grand and F. Rossi, Mean Absolute Percentage Error for regression models. Neurocomputing, 192, 38-48, 2016. https://doi.org/10. 1016/j.neucom.2015.12.114.