Search

Research on China’s Power Generation Forecasting Based on a Dual-Perspective Grey Forecasting Model

Author(s)

Jiale Fan*

Affiliation(s)

School of Business, Jiangnan University, Wuxi, Jiangsu, China *Corresponding Author

Abstract

Power generation is a critical indicator for measuring a nation’s energy supply capacity, power supply-demand balance, and economic operational level. Accurate forecasting of power generation holds significant practical importance for power grid dispatching, energy infrastructure planning, and strategic management. Based on grey forecasting models, this study investigates China’s power generation from the dual perspectives of total volume trend forecasting and fluctuation interval forecasting. First, the damping discrete GM(1,1) model is employed to conduct medium- and short-term trend forecasting for China’s total annual power generation, aiming to enhance the model’s utilization of new information and improve forecasting precision. Second, addressing the intra-year fluctuation characteristics of power generation, an interval grey number sequence is constructed using the annual maximum and minimum monthly power generation data. By integrating the geometric feature sequence transformation method with the damping discrete GM(1,1) model, an annual interval grey number forecasting model is established to characterize the future fluctuation range of power generation. The results indicate that China’s power generation will maintain an overall growth trend in the future, with the annual power generation fluctuation intervals continuously expanding. This suggests that while the scale of power generation continues to rise, the intra-year fluctuation characteristics will further intensify. This research serves as a foundational framework for energy supply-demand analysis, grid reliability studies, and strategic foresight in the energy domain.

Keywords

Power Generation Forecasting; Grey Forecasting Model; Interval Grey Number; Particle Swarm Optimization

References

[1] Chen K H, Wang X, Alghazzawi D M, et al. Visualized calculation of regional power grid power data based on multiple linear regression equation. Applied Mathematics and Nonlinear Sciences, 2022, 7(1): 93-102. [2] Chang T J, Lee S, Lee J, et al. An interval-valued time series forecasting scheme with probability distribution features for electric power generation prediction. IEEE Access, 2022, 10: 6417-6429. [3] Wu Q, Peng C. A least squares support vector machine optimized by cloud-based evolutionary algorithm for wind power generation prediction. Energies, 2016, 9(8): 585. [4] Yang Z, Mourshed M, Liu K, et al. A novel competitive swarm optimized RBF neural network model for short-term solar power generation forecasting. Neurocomputing, 2020, 397: 415-421. [5] Zhou Binbin, Huang Jiaxin, Geng Ranran, et al. Short-term forecasting of China's electricity generation based on grey-ARIMA coupled model. Science Technology and Industry, 2022, 22(12): 382-387. [6] Ye L, Ye L, Wang J, et al. A novel hybrid ensemble forecasting method based on seasonal feature matching for photovoltaic power generation forecasting. Expert Systems with Applications, 2025: 130811. [7] Zhang P, Hu J, Zheng K, et al. Forecasting Renewable Power Generation by Employing a Probabilistic Accumulation Non-Homogeneous Grey Model. Energies, 2025, 18(18): 5037. [8] Lv Y, Gao M, Xiao X. Unbiased forecasting of seasonal wind power generation based on a novel seasonal multivariable grey model. Renewable Energy, 2025: 124952. [9] Cao Y, Liang S, Shen Q, et al. Damping accumulated discrete GM (1, 1) model and its application. Control and Decision, 2023, 38(6): 1687-1694. [10] Zeng B, Liu S, Xie N. Prediction model of interval grey number based on DGM (1, 1). Journal of Systems Engineering and Electronics, 2010, 21(4): 598-603. [11] Kennedy J, Eberhart R. Particle swarm optimization (PSO)//Proc. IEEE international conference on neural networks, Perth, Australia. 1995, 4(1): 1942-1948. [12] Eberhart R, Kennedy J. A new optimizer using particle swarm theory//MHS'95. Proceedings of the sixth international symposium on micro machine and human science. Ieee, 1995: 39-43.