Search

Electricity Market Price Time Series Forecasting

Author(s)

Sihai Wu*

Affiliation(s)

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

Abstract

The development of electricity is closely linked to the overall economy and is related to all works of life [1]. In the context of competitive electricity markets, both power producers and consumers require imperious demands of precise price forecasting tools. However, it is challenging to forecast due to a series of factors such as periods of high volatility and seasonal patterns that would skew the consequence [1]. In response to the challenges raised above, ensemble learning. Some researchers apply a single such as time-delay dynamic mechanical model to reach the goal, which leads to errors that are difficult to avoid. This paper proposes a highly precise and efficient price forecasting function based on time series analysis: ensemble learning and Bootstrap aggregating to generate models [2]. Ensemble learning is a machine learning (ML) function, instead of taking advantage of one single model, ensemble learning can improve prediction performance by combining multiple models. Multiple "weak learners" are combined into a "strong learner" to reduce errors and improve generalization.

Keywords

Electricity Market; Ensemble Learning; Recurrent Neural Network; Bootstrap Aggregating; Time Series Analysis

References

[1] Jan, F., Shah, I., & Ali, S. (2022). "Short-Term Electricity Prices Forecasting Using Functional Time Series Analysis." Energies, 15(9), 323, pp. 1-2. [2] Pełka, Paweł. (2023). "Analysis and Forecasting of Monthly Electricity Demand Time Series Using Pattern-Based Statistical Methods." Energies, 16(2), 827, pp. 1-3. [3] Hansun, S., & Kristanda, M. B. (2017). "Performance analysis of conventional moving average methods in forex forecasting." 2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS), Yogyakarta, Indonesia, pp. 11-17. DOI: 10.1109/ICON-SONICS.2017.8267814. [4] Ben Chaabene, Wassim, Flah, Majdi, & Nehdi, Moncef L. (2020). "Machine learning prediction of mechanical properties of concrete: Critical review." Construction and Building Materials, vol. 260, Art. no. 119889. DOI: 10.1016/j.conbuildmat.2020.119889. [5] Dong, X., Yu, Z., Cao, W., et al. (2020). "A survey on ensemble learning." Frontiers of Computer Science, 14, 241–258. DOI: 10.1007/s11704-019-8208-z. [6] Salehinejad, H., Sankar, S., Barfett, J., Colak, E., & Valaee, S. (2018). "Recent Advances in Recurrent Neural Networks." arXiv preprint arXiv:1801.01078. [7] Gajewski, P., Čule, B., & Rankovic, N. (2023). "Unveiling the Power of ARIMA, Support Vector and Random Forest Regressors for the Future of the Dutch Employment Market." Journal of Theoretical and Applied Electronic Commerce Research, 18(3), 1365-1403. DOI: 10.3390/jtaer18030069. [8] Kwon, H., Park, J., & Lee, Y. (2019). "Stacking Ensemble Technique for Classifying Breast Cancer." Healthcare Informatics Research, 25(4), 283-288. DOI: 10.4258/hir.2019.25.4.283. [9] 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.