Academic Journal
A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism.
| Τίτλος: | A fast risk assessment method for power balance under extreme weather conditions based on deep reinforcement learning with a coupled attention mechanism. |
|---|---|
| Συγγραφείς: | Hang W; School of Energy and Power Engineering, Northeast Electric Power University, Jilin, China.; Electric Power Research Institute of State Grid Jilin Electric Power Co., Ltd., Changchun, China., Shouheng S; Electric Power Research Institute of State Grid Jilin Electric Power Co., Ltd., Changchun, China., Yiming L; State Grid Jilin Electric Power Co., Ltd., Changchun, China., Baoju L; State Grid Jilin Electric Power Co., Ltd., Changchun, China., Yu C; Electric Power Research Institute of State Grid Jilin Electric Power Co., Ltd., Changchun, China., Meiyue X; Electric Power Research Institute of State Grid Jilin Electric Power Co., Ltd., Changchun, China., Niu H; School of Energy and Power Engineering, Northeast Electric Power University, Jilin, China. |
| Πηγή: | PloS one [PLoS One] 2026 Oct 08; Vol. 21 (10), pp. e0359101. Date of Electronic Publication: 2026 Oct 08 (Print Publication: 2026). |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: San Francisco, CA : Public Library of Science |
| Ιατρικοί όροι (MeSH): | Weather* , Deep Learning*, Risk Assessment/methods ; Reinforcement Machine Learning ; Markov Chains ; Autoencoder ; Attention ; Multilayer Perceptrons |
| Περίληψη: | 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. (Copyright: © 2026 Hang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
| Competing Interests: | The authors have declared that no competing interests exist. |
| References: | IEEE Trans Neural Netw Learn Syst. 2024 Jul;35(7):9970-9984. (PMID: 37022042) Nat Commun. 2023 Oct 4;14(1):6202. (PMID: 37794008) |
| Entry Date(s): | Date Created: 20261008 Date Completed: 20261008 Latest Revision: 20261010 |
| Update Code: | 20261010 |
| PubMed Central ID: | PMC13649036 |
| DOI: | 10.1371/journal.pone.0359101 |
| PMID: | 42848814 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1932-6203 |
|---|---|
| DOI: | 10.1371/journal.pone.0359101 |