Intelligent Scenario Generation for Weekly and Daily Power System Operations under Typhoon Conditions

Jinxin Wang; Mengyuan Liu; Nan Yang; Zhenhuan Song; Jin Chen; Yunqi Zhou; Xueling Hong

doi:10.53941/aieng.2025.100004

Abstract

Typhoons, as a representative form of extreme weather, pose serious threats to power system security by inducing renewable energy volatility and damaging transmission infrastructure. To address these challenges, this study proposes an intelligent scenario generation framework for weekly and daily power system operations under typhoon conditions, aiming to capture the spatiotemporal impacts of typhoon events and support dispatch optimization under extreme weather conditions. The framework first integrates ARIMA-based deterministic forecasting with Monte Carlo simulation to construct stochastic scenario ensembles that capture the variability in renewable generation and load. Then, it applies numerical integration to estimate the probabilities of transmission line faults under the wind stress induced by typhoons. Finally, clustering analysis is used to extract representative and extreme operational scenarios, and a multi-scenario dynamic simulation model is established to evaluate system stability and quantify operational risks. The proposed methodology effectively captures the spatiotemporal characteristics of typhoon impacts on power systems and provides theoretical support for dispatch optimization, fault risk assessment, and resilience enhancement in complex meteorological environments.

References

1.
The Central People’s Government of the People’s Republic of China. Xi Jinping Presided over the 9th Meeting of the Central Financial and Economic Affairs Commission. 2024. Available online: http://www.gov.cn/xinwen/2021-03/15/content_5593154.htm (accessed on 15 May 2025).
2.
Yang, Y.; Sun, Y.-Y.; Mao, Z.-H.; et al. Generation Method for Extreme Wind Power Scenarios Induced by Mid-term Weather Processes. Proc. CSEE 2024, 1, 1–11.
3.
World Meteorological Organization. State of the Global Climate 2023. WMO, 2024. Available online: https://wmo.int/publication-series/state-of-global-climate-2023 (accessed on 19 May 2025).
4.
Gao, Z.-T.; Zhang, J.; Li, Y.; et al. Impact of Extreme Weather on Local Wind Conditions in Wind Farms. J. Huazhong Univ. Sci. Technol. 2024, 52, 106–112.
5.
Yang, N.; Xu, G.; Fei, Z.; et al. Two-Stage Coordinated Robust Planning of Multi-Energy Ship Microgrids Considering Thermal Inertia and Ship Navigation. IEEE Trans. Smart Grid 2025, 16, 1100–1111. https://doi.org/10.1109/TSG.2024.3524550.
6.
Dong, X.-C.; Zhang, S.; Li, Y.; et al. Review of Sequential Scenario Generation and Reduction Methods in Power Systems. Power Syst. Technol. 2023, 47, 709–721.
7.
Wang, X.-Y.; Li, Y.; Dong, X.-C.; et al. Multi-source and Load Scenario Generation Method for Active Distribution Networks Based on Variational Autoencoder. Power Syst. Technol. 2021, 45, 2962–2969.
8.
Kang, M.Y.; Zhu, R.; Chen, D.X.; et al. A Cross-modal Generative Adversarial Network for Scenarios Generation of Renewable Energy. IEEE Trans. Power Syst. 2024, 39, 2630–2640.
9.
Dong, X.-C.; Mao, Z.-H.; Sun, Y.-Y.; et al. Short-term Wind Power Scenario Generation Based on Conditional Latent Diffusion Models. IEEE Trans. Sustain. Energy 2024, 15, 1074–1085.
10.
Wang, J.; Yu, J.; Kong, X. Mid- to Long-term Load Forecasting Model Based on Dual Decomposition and Bidirectional Long Short-term Memory Network. Power Syst. Technol. 2024, 48, 3418–3426.
11.
Munkhammar, J.; van der Meer, D.; Widén, J. Very Short Term Load Forecasting of Residential Electricity Consumption Using the Markov-chain Mixture Distribution (MCM) Model. Appl. Energy 2021, 282, 116180.
12.
Sharifzadeh, M.; Sikinioti-Lock, A.; Shah, N. Machine-learning Methods for Integrated Renewable Power Generation: A Comparative Study of Artificial Neural Networks, Support Vector Regression, and Gaussian Process Regression. Renew. Sustain. Energy Rev. 2019, 108, 513–538.
13.
Lucheroni, C.; Boland, J.; Ragno, C. Scenario Generation and Probabilistic Forecasting Analysis of Spatio-temporal Wind Speed Series with Multivariate Autoregressive Volatility Models. Appl. Energy 2019, 239, 1226–1241.
14.
Zhou, N.; Xu, X.; Yan, Z.; et al. Spatio-temporal Probabilistic Forecasting of Photovoltaic Power Based on Monotone Broad Learning System and Copula Theory. IEEE Trans. Sustain. Energy 2022, 13, 1874–1885.
15.
Yang, N.; Xiong, Z.; Ding, L.; et al. A Game-based Power System Planning Approach Considering Real Options and Coordination of All Types of Participants. Energy 2024, 312, 133400. https://doi.org/10.1016/j.energy.2024.133400.
16.
Ye, L.; Pei, M.; Yang, J.-B.; et al. Power Balance Mechanism in New Energy Power Systems Under Extreme Weather Conditions. Autom. Electr. Power Syst. 2025, 49, 2–18.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us