Generic placeholder image

Recent Advances in Electrical & Electronic Engineering

Author(s): Xingrui Fan and Yuancheng Li*

DOI: 10.2174/2352096516666230217113610

DownloadDownload PDF Flyer Cite As
An Improved Informer Network for Short-Term Electric Load Forecasting

Page: [532 - 540] Pages: 9

  • * (Excluding Mailing and Handling)

Abstract

Background: Electric load forecasting plays an essential role in the dispatching operation of power systems. It can be divided into long-term, medium-term, and short-term according to the forecast time. Accurate short-term electric forecasting helps the system operate safely and reliably, reduces resource waste, and improves economic efficiency.

Objective: To fully use the time-series characteristics in load data and improve the accuracy of short-term electric load forecasting, we propose an improved Informer model called Nysformer.

Methods: Firstly, the input of data is improved, and the information is input into the model in the form of difference. Then, the Nystrom self-attention mechanism was proposed, approximating the standard self-attention mechanism using an approximation with O(n) time complexity and memory utilization.

Results: We conducted experiments on a publicly available dataset, and the results show that the proposed Nysformer model has lower time complexity and higher accuracy than the standard Informer model.

Conclusion: An improved informer network is proposed for short-term electric load forecasting, and the experimental results demonstrate the proposed model Nysformer can improve the accuracy of short-term electric load forecasting.

Graphical Abstract

[1]
L. ChunSing, and Y. Yuxiang, "Multi-view neural network ensemble for short and mid-term load forecasting", IEEE Trans. Power Syst., vol. 36, no. 4, 2021.
[2]
A. Garulli, S. Paoletti, and A. Vicino, "Models and techniques for electric load forecasting in the presence of demand response", IEEE Trans. Control Syst. Technol., vol. 23, no. 3, pp. 1087-1097, 2015.
[http://dx.doi.org/10.1109/TCST.2014.2361807]
[3]
K.B. Song, Y.S. Baek, D.H. Hong, and G. Jang, "Short-term load forecasting for the holidays using fuzzy linear regression method", IEEE Trans. Power Syst., vol. 20, no. 1, pp. 96-101, 2005.
[http://dx.doi.org/10.1109/TPWRS.2004.835632]
[4]
Zhiyu Yang, Junyong Liu, and Youbo Liu, "Substation load forecasting based on adaptive deep belief network", Chinese Journal of electrical engineering, vol. 39, no. 14, p. 12, 2019.
[5]
Xueneng Su, "Short-term load forecasting method based on multiple distributed BP neural networks based on Hadoop architecture", Chinese Journal of electrical engineering, vol. 37, no. 17, p. 8, 2017.
[6]
Shuqing Zhang, Xiaoning Duan, and Liguo Zhang, "Application of Tsne dimensionality reduction visualization analysis and moth flame optimization ELM algorithm in power load forecasting", Chinese Journal of electrical engineering, vol. 41, no. 9, p. 10, 2021.
[7]
W. Kong, Z.Y. Dong, Y. Jia, D.J. Hill, Y. Xu, and Y. Zhang, "Short-term residential load forecasting based on LSTM recurrent neural network", IEEE Trans. Smart Grid, vol. 10, no. 1, pp. 841-851, 2019.
[http://dx.doi.org/10.1109/TSG.2017.2753802]
[8]
M. Rafiei, T. Niknam, J. Aghaei, M. Shafie-Khah, and J.P.S. Catalão, "Probabilistic load forecasting using an improved wavelet neural network trained by generalized extreme learning machine", IEEE Trans. Smart Grid, vol. 9, no. 6, pp. 6961-6971, 2018.
[http://dx.doi.org/10.1109/TSG.2018.2807845]
[9]
C. Pang, and Z. Bo, Yu Jianming Short-term power load forecasting based on LSTM cyclic neural network., Power Engineering Technology, 2021.
[10]
Chengwen Yao, Yang Ping, and Zejian Liu, "Load forecasting method based on CNN-GRU hybrid neural network", grid technology, vol. 44, no. 9, p. 8, 2020.
[11]
Zhao Bing, Zengping Wang, and Weijia Ji, "CNN-GRU shortterm power load forecasting method based on attention mechanism", grid technology, vol. 43, no. 12, p. 7, 2019.
[12]
Li Xiao, and Xianling Lu, "Short-term load prediction model based on dual attention mechanism and GRU network", computer engineering, vol. 48, no. 2, p. 7, 2022.
[13]
R. Gao, L. Du, and P.N. Suganthan, "Random vector functional link neural network based ensemble deep learning for short-term load forecasting, 10.48550", [P]",
[14]
A A Mamun, M. Sohel, and N. Mohammad, "Comprehensive review of the load forecasting techniques using single and hybrid predictive models", IEEE Access, no. 99, pp. 1-1, 2020.
[15]
Z. Li, Y. Li, and Y. Liu, "Deep learning based densely connected network for load forecasting", IEEE Transactions on Power Systems, no. 99, pp. 1-1, 2020.
[16]
S. Li, X. Jin, Y. Xuan, X. Zhou, W. Chen, and Y.-X Wang, "Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting", arXiv, 2019.
[17]
S. Wu, X. Xiao, and Q. Ding, "Adversarial Sparse Transformer for Time Series Forecasting", In the 34th Conference on Neural Information Processing Systems, 2020.
[18]
H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, "Informer: Beyond efficient transformer for long sequence time-series forecasting. [J", The Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021.
[http://dx.doi.org/10.1609/aaai.v35i12.17325]
[19]
W. Ha, J. Xu, and J. Wang, "Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting", In The 35th Conference on Neural Information Processing Systems, 2021.
[20]
Y. Xiong, Z. Zeng, R. Chakraborty, M. Tan, G. Fung, Y. Li, and V. Singh, "Nyströmformer: A nyström-based algorithm for approximating self-attention", The Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021.
[21]
F K Sun, C I Lang, and D S Boning, "Adjusting for autocorrelated errors in neural networks for time series regression and forecasting",
[22]
M. Lichman, "UCI Machine Learning Repository", Available from: http://archive.ics.uci.edu/ml