Search

Research Review and Innovative Framework for Electriciy Market Price Forecasting Methods

Author(s)

Chen Yuan*

Affiliation(s)

Xi’an Jiaotong Liverpool University, Suzhou, China *Corresponding Author

Abstract

Electricity price forecasting is essential for optimizing power systems and market decision-making but is challenged by price volatility driven by factors like weather,demand fluctuations,and renewable energy integration. Traditional methods lack the ability to capture nonlinear dynamics, while machine learning approaches face issues like overfitting and limited temporal modeling. Deep learning models, though effective, require large datasets and are computationally intensive. To address these limitations, this paper proposes an ensemble learning-based framework integrating Seasonal-Trend decomposition (STL), Extreme Gradient Boosting (XGBoost), and Attention-LSTM models within a three-level structure, validated on datasets like Nord Pool, PJM, and the Spanish market. The framework enhances prediction accuracy, spike price capture,and computational efficiency, offering a robust solution for electricity price forecasting.

Keywords

Price Forecasting; Ensemble Learning; Machine Learning; Transformer Models; XGBoost; Nonlinear Dynamics

References

[1] J. Contreras et al.,"ARIMA models to predict next-day electricity prices," IEEE Trans. Power Syst.,vol. 18,no. 3,pp. 1014-1020,2003. [2] R. Weron,"Electricity price forecasting: A review of the state-of-the-art," Energy Econ.,vol. 62,pp. 77-95,2017. [3] F. Ziel et al.,"LSTM-based electricity price forecasting," Energy AI,vol. 5,p. 100083,2021. [4] A. J. Conejo et al.,Electricity Markets: Pricing,Structures,and Economics. Wiley,2010. [5] G. E. P. Box et al.,Time Series Analysis: Forecasting and Control. Wiley,2015. [6] M. M. H. P. M. R. Kristiansen,"Modelling electricity futures prices," Energy Econ.,vol. 34,pp. 882-894,2012. [7] H. Lago et al.,"Forecasting spot electricity prices: Deep learning vs. traditional models," Appl. Energy,vol. 277,p. 115589,2020. [8] ERCOT,"2022 State of the Market Report," 2023. [9] S. Smola et al.,"A tutorial on support vector regression," Stat. Comput.,vol. 14,pp. 199-222,2004. [10] T. Chen et al.,"XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min.,2016,pp. 785-794. [11] C. Cortes et al.,"Support-vector networks," Mach. Learn.,vol. 20,no. 3,pp. 273-297,1995. [12] J. Friedman et al.,"Greedy function approximation: A gradient boosting machine," Ann. Stat.,vol. 29,no. 5,pp. 1189-1232,2001. [13] I. Guyon et al.,"An introduction to variable and feature selection," J. Mach. Learn. Res.,vol. 3,pp. 1157-1182,2003. [14] A. J. Conejo et al.,"Forecasting electricity prices for a day-ahead pool-based electric energy market," Int. J. Forecast.,vol. 21,no. 3,pp. 435-462,2005. [15] S. Hochreiter et al.,"Long short-term memory," Neural Comput.,vol. 9,no. 8,pp. 1735-1780,1997. [16] A. Vaswani et al.,"Attention is all you need," in Proc. 31st Int. Conf. Neural Inf. Process. Syst.,2017,pp. 5998-6008. [17] F. Ziel et al.,"LSTM-based electricity price forecasting," Energy AI,vol. 5,p. 100083,2021. [18] PJM Interconnection,"PJM Market Data," 2023. [19] Y. LeCun et al.,"Deep learning," Nature,vol. 521,no. 7553,pp. 436-444,2015. [20] M. Abadi et al.,"TensorFlow: A system for large-scale machine learning," in Proc. 12th USENIX Symp. Oper. Syst. Des. Implement.,2016,pp. 265-283. [21] J. Bergstra et al.,"Random search for hyper-parameter optimization," J. Mach. Learn. Res.,vol. 13,pp. 281-305,2012. [22] R. Weron,"Electricity price forecasting: A review of the state-of-the-art," Energy Econ.,vol. 62,pp. 77-95,2017. [23] T. Hastie et al.,The Elements of Statistical Learning: Data Mining,Inference,and Prediction. Springer,2009. [24] R. B. Cleveland et al.,"STL: A seasonal-trend decomposition procedure based on loess," J. Off. Stat.,vol. 6,no. 1,pp. 3-73,1990. [25] T. Chen et al.,"XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min.,2016,pp. 785-794. [26] A. Vaswani et al.,"Attention is all you need," in Proc. 31st Int. Conf. Neural Inf. Process. Syst.,2017,pp. 5998-6008. [27] R. Weron,"Electricity price forecasting: A review of the state-of-the-art," Energy Econ.,vol. 62,pp. 77-95,2017. [28] R. Koenker et al.,"Quantile regression," J. Econ. Perspect.,vol. 15,no. 4,pp. 143-156,2001. [29] R. B. Cleveland et al.,"STL: A seasonal-trend decomposition procedure based on loess," J. Off. Stat.,vol. 6,no. 1,pp. 3-73,1990. [30] T. Chen et al.,"XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min.,2016,pp. 785-794. [31] A. Vaswani et al.,"Attention is all you need," in Proc. 31st Int. Conf. Neural Inf. Process. Syst.,2017,pp. 5998-6008. [32] R. Weron,"Electricity price forecasting: A review of the state-of-the-art," Energy Econ.,vol. 62,pp. 77-95,2017. [33] S. Shalev-Shwartz et al.,"Online learning and online convex optimization," Found. Trends Mach. Learn.,vol. 4,no. 2,pp. 107-194,2012. [34] Nord Pool,"Nord Pool Market Data," 2023. [35] M. Abadi et al.,"TensorFlow: A system for large-scale machine learning," in Proc. 12th USENIX Symp. Oper. Syst. Des. Implement.,2016,pp. 265-283. [36] China Electricity Council,"China Electricity Market Report," 2023. [37] IEA,"Renewable Energy Integration: Challenges and Solutions," 2023. [38] J. Hull,Options,Futures,and Other Derivatives. Pearson,2018. [39] A. J. Conejo et al.,Electricity Markets: Pricing,Structures,and Economics. Wiley,2010. [40] Tang H,Zhang C,Jin M,et al. Time series forecasting with llms: Understanding and enhancing model capabilities[J]. ACM SIGKDD Explorations Newsletter,2025,26(2): 109-118.