Abstract
With the continuous advancement of Chinese electricity market reform, the continuous improvement of the market mechanism and the integration of a large number of new energy sources have brought great challenges to the market’s clear electricity price forecast. The new energy output, load data, and tie-line power schedule are fused to obtain an improved input feature variable, which can better reflect the electricity price trend. Then, the maximum information coefficient method (MIC) was used to analyze the correlation between each characteristic variable and electricity price, and an interpretable time series prediction model (N-BEATSx) based on neural network base expansion analysis of fusion characteristic variables was adopted. It is interpretable and can solve nonlinear forecasting problems of time series with the trend, seasonality, and significant random fluctuations. For the selection of hyperparameters in the N-BEATSx prediction model, the sparrow search algorithm (SSA) is used for optimization, the optimal grid structure hyperparameters are obtained with the minimum loss function of the validation set as the objective function. To verify the validity of the proposed model, the Shanxi Province market electricity price data is taken as an example to analyze and compare with other forecasting models, the results show that the proposed model can predict the electricity price of the day before clearing well.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zou, Y., Teng, X., Wang, Y., et al.: Electricity price forecast based on stacked autoencoder in spot market environment. In: Proceedings of the 2019 Academic Annual Meeting of the Electricity Market Professional Committee of the Chinese Society for Electrical Engineering and the National Electricity Trading Institutions Alliance Forum, pp. 308–315 (2019)
Wei, Q., Chen, S., Huang, W., et al.: Forecasting method of clearing price in spot market by random forest regression. Proceedings of the CSEE 41(04), 1360–1367+1542 (2021)
Shen, Z.: Research on Electricity Price Forecast Based on Extreme Learning Machine and MapReduce. Donghua University (2019)
Chen, J., Tao, C., Ma, G., et al.: Forecasting method of spot market clearing price based on data mining and support vector machine. Power System and Clean Energy 36(10), 14–19+27 (2020)
Wang, D., Luo, H., Grunder, O., et al.: Multi-step ahead electricity price forecasting using a hybrid model based on two-layer decomposition technique and bp neural network optimized by firefly algorithm. Appl. Energy 190, 390–407 (2017)
Dudek, G.: Multilayer perceptron for GEFCom2014 probabilistic electricity price forecasting. Int. J. Forecast. 32(3), 1057–1060 (2016)
Peesapati, R., Kumar, N.: Electricity price forecasting and classification through wavelet–dynamic weighted PSO–FFNN approach. IEEE Syst. J. 12(4), 3075–3084 (2017)
Pindoriya, N.M., Singh, S.N., Singh, S.K.: An adaptive wavelet neural network-based energy price forecasting in electricity markets. IEEE Trans. Power Syst. 23(3), 1423–1432 (2008)
Lu, J., Zhang, Q., Yang, Z., et al.: Short-term load forecasting method based on CNN-LSTM hybrid network model. Automation of Electric Power Systems, pp. 1–7 (2019)
Shen, Y., Zhang, J., Liu, J.: Short-term load forecasting of power system based on similar day method and PSO-DBN. In: 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), pp. 1–6 (2018)
Feng, R., Zhao, L., Yang, Y., et al.: LSTM short-term load forecasting model considering electricity price and attention mechanism. Science and Technology Bulletin 36(11), 57–62, 68 (2020)
Yin, H., Ding, W., Chen, S., et al.: Day-ahead electricity price forecasting of electricity market with high proportion of new energy based on LSTM-CSO model. Power System Technol. 46(02), 472–480 (2022)
Han, S., Hu, F., Chen, Z., et al.: Day-ahead market marginal price forecasting based on GCN-LSTM. Proceedings of the CSEE 42(09), 3276–3286 (2022)
Wu, W., Liao, W., Miao, J., et al.: Using gated recurrent unit network to forecast short-term load considering impact of electricity price. Energy Procedia 158, 3369–3374 (2019)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Cho, K., Van Merriënboer, B., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734 (2014)
Oreshkin, B.N., Carpoy, D., Chapados, N., et al.: N-BEATS: neural basis expansion analysis for interpretable time series forecasting. In: 8th International Conference on Learning Representations, ICLR (2020)
Olivares, K.G., Marciasz, G., et al.: Neural Basis Expansion Analysis with Exogenous Variables: Forecasting Electricity Prices with NBEATSx. ArXiv preprint arXiv: 2104.05522 (2021)
Zhao, Y., Wang, X., Jiang, C., et al.: A novel short-term electricity price forecasting method based on correlation analysis with the maximal information coefficient and modified multi-hierarchy gated LSTM. Proceedings of the CSEE 41(01), 135–146+404 (2021)
Xuefeng, J.I.A., Cunbin, L.I.: Real-time electricity price forecasting of electricity market using DeepESN considering short-term load impact. Smart Power 49(01), 64–70 (2021)
Justin, B.K., Gurinder, S.A.: Equitability mutual information and the maximal information coefficient. PNAS 111(9), 3354–3359 (2014)
Wang, Z., Song, H., Li, S., et al.: Process monitoring based on logarithmic transformation and maximal information coefficient-PCA. Science Technology and Engineering 17(16), 259–265 (2017)
Zhou, J., Zhang, J.: Interpolation model and statistical data test and application. Statistics and Decision (5): 78–80 (2016)
Acknowledgments
This work was financially supported by the project of “Research on adjustable Internet resources and Application Technology” of NARI-TECH Control Systems Ltd. (No.524609220029).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 State Grid Electric Power Research Institute
About this paper
Cite this paper
Xu, F., Teng, X., Lu, J., Zheng, T., Jin, Y. (2023). Prediction of Day-Ahead Electricity Price Based on N-BEATSx Model Optimized by SSA Considering Coupling Between Features. In: Xue, Y., Zheng, Y., Gómez-Expósito, A. (eds) Proceedings of the 7th PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control (PMF2022). PMF 2022. Springer, Singapore. https://doi.org/10.1007/978-981-99-0063-3_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-0063-3_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0062-6
Online ISBN: 978-981-99-0063-3
eBook Packages: EnergyEnergy (R0)