Gerçek Zamanlı Elektrik Yük Tahmini için Bir Derin Öğrenme Yaklaşımı

Abstract

Doğru ve gerçek zamanlı elektrik talebi tahmininin artan önemi ışığında, bu araştırma, tahmin doğruluğunu önemli ölçüde artırmak amacıyla bir derin öğrenme modeli sunmaktadır. Doğrusal regresyon gibi geleneksel tahmin yöntemleri, elektrik kullanımıyla ilgili verilerde yer alan karmaşık kalıpları yakalamakta zorlanmaktadır. Standart makine öğrenimi yöntemlerinin, önerilen derin Uzun Kısa Vadeli Bellek (Long Short-Term Memory-LSTM) modeliyle karşılaştırıldığında yetersiz kaldığı görülmüştür. Ortalama Mutlak Hata (MAE) 5.454 ve Ortalama Karesel Hata (MSE) 18.243, derin LSTM modelinin bu sorunun üstesinden gelmedeki yeterliliğini göstermektedir. Doğrusal regresyon ise 47.352 MAE değeri ve 65.606 MSE değeri ile önerilen modelden daha düşük başarı sonucu elde etmiştir. Daha yüksek tahmin hassasiyeti ve güvenilirliği nedeniyle, derin LSTM modeli elektrik talebinin doğru, gerçek zamanlı tahmini için uygun bir seçenektir.

Keywords

• Dizi planı
• Güç akışı
• Derin öğrenme
• Yük talep tahmini
• Akıllı şebekeler
• Yığın LSTM

A Deep Learning Approach to Real-time Electricity Load Forecasting

Abstract

In light of the increasing importance of accurate and real-time electrical demand forecasting, this research presents a deep learning model with the goal of dramatically improving predictive accuracy. Conventional methods of forecasting, such as linear regression, have trouble capturing the complex patterns included in data about electricity usage. Standard machine learning methods are shown to be wanting when compared to the suggested deep Long Short-Term Memory (LSTM) model. Mean Absolute Error (MAE) of 5.454 and Mean Squared Error (MSE) of 18.243 demonstrate the deep LSTM model's proficiency in tackling this problem. The linear regression, on the other hand, achieved a MAE of 47.352 and an MSE of 65.606, which is lower than the proposed model. Because of its greater predictive precision and reliability, the deep LSTM model is a viable option for accurate, real-time prediction of electricity demand.

Keywords

• Plan of array
• Power flow
• Deep learning
• Load demand forecast
• Stacked LSTM
• Smart grids

References

1. [1] S. G. Patil and M. S. Ali, “Review on Analysis of Power Supply and Demand in Maharashtra State for Load Forecasting Using ANN,” Int J Sci Res Sci Technol, vol. 9, no.1, pp. 341-347, 2022, Doi: 10.32628/ijsrst229152.
2. [2] B. U. Islam, M. Rasheed, and S. F. Ahmed, “Review of Short-Term Load Forecasting for Smart Grids Using Deep Neural Networks and Metaheuristic Methods,” Mathematical Problems in Engineering, vol. 2022, 4049685, 2022. Doi: 10.1155/2022/4049685.
3. [3] B. Yildiz, J. I. Bilbao, and A. B. Sproul, “A review and analysis of regression and machine learning models on commercial building electricity load forecasting,” Renewable and Sustainable Energy Reviews, vol. 73, pp. 1104-1122, 2017. Doi: 10.1016/j.rser.2017.02.023.
4. [4] A. Azeem, I. Ismail, S. M. Jameel, F. Romlie, K. U. Danyaro, and S. Shukla, “Deterioration of Electrical Load Forecasting Models in a Smart Grid Environment,” Sensors, vol. 22, no. 12, 4363, 2022, Doi: 10.3390/s22124363.
5. [5] A. Talupula, “Demand Forecasting of Outbound Logistics Using Machine learning,” Faculty of Computing, Blekinge Institute of Technology, Karlskrona, Sweden, February, 2018.
6. [6] I. Zuleta-Elles, A. Bautista-Lopez, M. J. Catano- Valderrama, L. G. Marin, G. Jimenez-Estevez, and P. Mendoza-Araya, “Load Forecasting for Different Prediction Horizons using ANN and ARIMA models,” in 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2021, 2021. Doi: 10.1109/CHILECON54041.2021.9702913.
7. [7] M. L. Abdulrahman et al., “A Review on Deep Learning with Focus on Deep Recurrent Neural Network for Electricity Forecasting in Residential Building,” in Procedia Computer Science, vol. 193, pp. 141-154, 2021. Doi: 10.1016/j.procs.2021.10.014.
8. [8] G. Chitalia, M. Pipattanasomporn, V. Garg, and S. Rahman, “Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks,” Appl Energy, vol. 278, 115410, 2020, Doi: 10.1016/j.apenergy.2020.115410.

9. [9] Y. Hong, Y. Zhou, Q. Li, W. Xu, and X. Zheng, “A deep learning method for short-term residential load forecasting in smart grid,” IEEE Access, vol. 8, pp. 55785–55797, 2020, Doi: 10.1109/ACCESS.2020.2981817.
10. [10] B. Dietrich, J. Walther, Y. Chen, and M. Weigold, “A deep learning approach to electric load forecasting of machine tools,” MM Science Journal, vol. 2021-November, 2021, Doi: 10.17973/MMSJ.2021_11_2021146.
11. [11] G. Hafeez et al., “Short term load forecasting based on deep learning for smart grid applications,” in Advances in Intelligent Systems and Computing, Springer Verlag, 2019, pp. 276–288. Doi: 10.1007/978-3-319-93554-6_25.
12. [12] C. P. Joy, G. Pillai, Y. Chen, and K. Mistry, “Micro-genetic algorithm embedded multipopulation differential evolution based neural network for short-term load forecasting,” in 2021 56th International Universities Power Engineering Conference: Powering Net Zero Emissions, UPEC 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., Aug. 2021. Doi: 10.1109/UPEC50034.2021.9548262.
13. [13] X. Luo and L. O. Oyedele, “A self-adaptive deep learning model for building electricity load prediction with moving horizon,” Machine Learning with Applications, vol. 7, p. 100257, Mar. 2022, Doi: 10.1016/j.mlwa.2022.100257.
14. [14] F. Bayram, P. Aupke, B. S. Ahmed, A. Kassler, A. Theocharis, and J. Forsman, “DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks,” Eng Appl Artif Intell, vol. 123, Aug. 2023, Doi: 10.1016/j.engappai.2023.106480.
15. [15] Ernesto Aguilar Madrid, “Short-term electricity load forecasting (Panama).”
16. [16] H. Henderi, “Comparison of Min-Max normalization and Z-Score Normalization in the Knearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer,” IJIIS: International Journal of Informatics and Information Systems, vol. 4, no. 1, pp. 13–20, Mar. 2021, Doi: 10.47738/ijiis.v4i1.73.
17. [17] C. Xiong, H. Sun, D. Pan, and Y. Li, “A personalized collaborative filtering recommendation algorithm based on linear regression,” Mathematical Modelling of Engineering Problems, vol. 6, no. 3, 2019, Doi: 10.18280/mmep.060307.
18. [18] Yılmaz, Y. Doğrusal Regresyon Modeli. Teori ve Uygulamada Makine Öğrenmesi, (21-36), Nobel Akademik Yayıncılık, Ankara, 2022.
19. [19] A. de Myttenaere, B. Golden, B. Le Grand, and F. Rossi, “Mean Absolute Percentage Error for regression models,” Neurocomputing, vol. 192, pp. 38-48, 2016, Doi: 10.1016/j.neucom.2015.12.114.
20. [20] T. O. Hodson, T. M. Over, and S. S. Foks, “Mean Squared Error, Deconstructed,” J Adv Model Earth Syst, vol. 13, no. 12, e2021MS002681, 2021, Doi: 10.1029/2021MS002681.
21. [21] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geoscientific Model Development, vol. 15, no. 14. 2022. Doi: 10.5194/gmd-15-5481-2022.