A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism
- 1School of Energy and Power Engineering, Northeast Electric Power University, Jilin, China
- 2Electric Power Research Institute of State Grid Jilin Electric Power Co., Ltd., Changchun, China
- 3State Grid Jilin Electric Power Co., Ltd., Changchun, China
Abstract
Even if persistent stagnant weather does not directly damage power grid equipment, it may lead to prolonged insufficient output of renewable energy sources and further trigger power balance risks. This paper proposes a rapid risk assessment framework that comprehensively incorporates meteorological sensitivity models, time-varying component failure probabilities, a Denoising Variational Autoencoder (DVAE) for generating coupled wind-photovoltaic-temperature scenarios, and a Deep Deterministic Policy Gradient (DDPG) model embedded with the feature token attention mechanism.The 72-hour assessment task is formulated as an offline Markov Decision Process (MDP): the state space covers meteorological conditions, power sources, power grid topology, load profiles, and risk features of the previous time step; continuous actions are defined as risk indicator vectors; the reward function is designed to penalize deviations between model outputs and PSD-BPA benchmarks, temporal inconsistency, and violations of physical constraints.To distinguish the sequential reinforcement learning formulation from direct regression, a feedforward Multi-Layer Perceptron (MLP) is introduced as the non-reinforcement learning baseline. Four metrics, namely Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coefficient of determination (R2), and the 95th percentile of absolute error (P95AE), are adopted to evaluate all models on an independent scenario-level test set.Verified on the planned power grid of Northeast China in 2025 as the test case, the proposed DDPG-Attention achieves MAE of 0.0310, RMSE of 0.0389, R2 of 0.954 and P95AE of 0.0760 on the independent test set. The average time consumption for a single risk assessment is approximately 0.12 seconds, yielding an acceleration ratio of multiple orders of magnitude compared with the traditional time-sequential Monte Carlo simulation based on PSD-BPA. This study provides an efficient and accurate novel technical paradigm for the rapid evaluation of power supply-demand imbalance risks in power systems under extreme weather conditions.
Related
- Combined reinforcement mechanism of TEOS-barium oxalate-phosphate composite on weathered sandstone
- A multi-attention mechanism-improved ResNet18 approach for lithology identification and classification
- Hybrid stacked bidirectional deep learning with attention based air pollution prediction for environmental sustainability
- DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning
- DispSAC: Surface-wave dispersion inversion using soft actor-critic reinforcement learning
BibTeX
@article{hang2026fast,
title = {{A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism}},
author = {Wang Hang and Sun Shouheng and Li Yiming and Li Baoju and Cong Yu and Xu Meiyue and HeXiang Niu},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0359101},
url = {https://doi.org/10.1371/journal.pone.0359101},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism
AU - Wang Hang
AU - Sun Shouheng
AU - Li Yiming
AU - Li Baoju
AU - Cong Yu
AU - Xu Meiyue
AU - HeXiang Niu
PY - 2026
DA - 2026/10/08
JO - PLOS One
DO - 10.1371/journal.pone.0359101
UR - https://doi.org/10.1371/journal.pone.0359101
AB - Even if persistent stagnant weather does not directly damage power grid equipment, it may lead to prolonged insufficient output of renewable energy sources and further trigger power balance risks. This paper proposes a rapid risk assessment framework that comprehensively incorporates meteorological sensitivity models, time-varying component failure probabilities, a Denoising Variational Autoencoder (DVAE) for generating coupled wind-photovoltaic-temperature scenarios, and a Deep Deterministic Policy Gradient (DDPG) model embedded with the feature token attention mechanism.The 72-hour assessment task is formulated as an offline Markov Decision Process (MDP): the state space covers meteorological conditions, power sources, power grid topology, load profiles, and risk features of the previous time step; continuous actions are defined as risk indicator vectors; the reward function is designed to penalize deviations between model outputs and PSD-BPA benchmarks, temporal inconsistency, and violations of physical constraints.To distinguish the sequential reinforcement learning formulation from direct regression, a feedforward Multi-Layer Perceptron (MLP) is introduced as the non-reinforcement learning baseline. Four metrics, namely Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coefficient of determination (R2), and the 95th percentile of absolute error (P95AE), are adopted to evaluate all models on an independent scenario-level test set.Verified on the planned power grid of Northeast China in 2025 as the test case, the proposed DDPG-Attention achieves MAE of 0.0310, RMSE of 0.0389, R2 of 0.954 and P95AE of 0.0760 on the independent test set. The average time consumption for a single risk assessment is approximately 0.12 seconds, yielding an acceleration ratio of multiple orders of magnitude compared with the traditional time-sequential Monte Carlo simulation based on PSD-BPA. This study provides an efficient and accurate novel technical paradigm for the rapid evaluation of power supply-demand imbalance risks in power systems under extreme weather conditions.
SN - 1932-6203
ER -