Risk assessment method for power communication network based on LTA-EN
- 1Changchun University of Science and Technology, School of Electronic Information Engineering, Changchun, Jilin, China
- 2Changchun University of Science and Technology, School of Artificial Intelligence, Changchun, Jilin, China
- 3Changchun Institute of Engineering, School of Electrical Engineering and Information Technology, Changchun, Jilin, China
Abstract
As the nerve center of power systems, power communication networks require risk assessment methods with lightweight architecture and high prediction accuracy to support reliable operation and maintenance decision-making. To overcome the limitations of conventional models—including weak temporal feature extraction, static weight assignment, and poor generalization in small-sample scenarios—this paper proposes a risk assessment method for power communication networks based on the fusion of Lightweight Temporal Attention (LTA) and Elastic Net (EN). First, a risk indicator system is constructed, and redundant features are eliminated through variance-based screening to reduce data dimensionality. The LTA module discards complex multi-head structures and computes dynamic weights solely by combining indicator-risk correlations and normalized interaction terms, enabling adaptive focusing on core time-series indicators. The EN regression is adopted to construct the prediction model, in which bi-regularization balances fitting performance and generalization ability to further improve prediction accuracy. Tests on 12-month small-sample datasets show that the MAE of the LTA-EN model is reduced by 23.4% compared with the conventional fixed-weight linear regression scheme and by 12.1% compared with the complex attention-ridge regression approach. The small-sample generalization error is decreased by 10% on average, and the core indicator recognition efficiency is improved by 40%. The model achieves an optimal tradeoff among small-sample adaptability, lightweight deployment, and high-precision prediction, and can provide efficient quantitative support for monthly risk early warning of power communication networks.
Related
- Do Botanical Gardens Pose a Pollen Allergenicity Risk? A Multi-Method Assessment Integrating Species-Specific Values of Potential Allergenicity and Pollen Concentration Monitoring
- Monocular Deep Learning Pipeline for 3D Bird Collision Risk Assessment on Power Transmission Lines
- Second-line treatment selection for advanced hepatocellular carcinoma: a network meta-analysis with reconstructed survival curves and integrated benefit–risk assessment
- HyperCom: a hypergraph-based method to infer cell-resolved cell-cell communication
- Kontext: Kernel-based method bridging spatial domain identification and cell-cell communication
BibTeX
@article{chen2026risk,
title = {{Risk assessment method for power communication network based on LTA-EN}},
author = {Xiaojuan Chen and Yuanming Liu and Chang Qu and Xue Li},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0354026},
url = {https://doi.org/10.1371/journal.pone.0354026},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Risk assessment method for power communication network based on LTA-EN
AU - Xiaojuan Chen
AU - Yuanming Liu
AU - Chang Qu
AU - Xue Li
PY - 2026
DA - 2026/09/03
JO - PLOS One
DO - 10.1371/journal.pone.0354026
UR - https://doi.org/10.1371/journal.pone.0354026
AB - As the nerve center of power systems, power communication networks require risk assessment methods with lightweight architecture and high prediction accuracy to support reliable operation and maintenance decision-making. To overcome the limitations of conventional models—including weak temporal feature extraction, static weight assignment, and poor generalization in small-sample scenarios—this paper proposes a risk assessment method for power communication networks based on the fusion of Lightweight Temporal Attention (LTA) and Elastic Net (EN). First, a risk indicator system is constructed, and redundant features are eliminated through variance-based screening to reduce data dimensionality. The LTA module discards complex multi-head structures and computes dynamic weights solely by combining indicator-risk correlations and normalized interaction terms, enabling adaptive focusing on core time-series indicators. The EN regression is adopted to construct the prediction model, in which bi-regularization balances fitting performance and generalization ability to further improve prediction accuracy. Tests on 12-month small-sample datasets show that the MAE of the LTA-EN model is reduced by 23.4% compared with the conventional fixed-weight linear regression scheme and by 12.1% compared with the complex attention-ridge regression approach. The small-sample generalization error is decreased by 10% on average, and the core indicator recognition efficiency is improved by 40%. The model achieves an optimal tradeoff among small-sample adaptability, lightweight deployment, and high-precision prediction, and can provide efficient quantitative support for monthly risk early warning of power communication networks.
SN - 1932-6203
ER -