Fast reliability assessment of islanded microgrids considering wind power uncertainty and tail risk

YUE Dawei; LI Bingxin; CHAI Yuanyuan; LIU Haoran; LI Yibo

doi:10.19783/j.cnki.pspc.260347

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Fast reliability assessment of islanded microgrids considering wind power uncertainty and tail risk

更新时间：2026-10-15

- Fast reliability assessment of islanded microgrids considering wind power uncertainty and tail risk
- Power System Protection and Control Vol. 54, Issue 20, (2026)
- 作者机构：
  
  智能配用电装备与系统全国重点实验室(河北工业大学),天津,300401
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260347
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
YUE Dawei, LI Bingxin, CHAI Yuanyuan, et al. Fast reliability assessment of islanded microgrids considering wind power uncertainty and tail risk[J]. Power System Protection and Control, 2026, 54(20).
DOI：

YUE Dawei, LI Bingxin, CHAI Yuanyuan, et al. Fast reliability assessment of islanded microgrids considering wind power uncertainty and tail risk[J]. Power System Protection and Control, 2026, 54(20). DOI： 10.19783/j.cnki.pspc.260347.

摘要

针对传统可靠性评估难以兼顾不确定性刻画、尾部风险度量与计算效率的问题，提出尾部风险可靠性快速评估框架。首先，基于实测数据构造小时级容量因子序列，结合“月-时”划分与共形校准，建立有限样本风电条件椭球不确定集，刻画风电波动范围。其次，以直流最优潮流最小切负荷模型为核心，引入条件风险价值(conditional value-at-risk

CVaR)构造尾部风险指标，并提出FAST-CVaR近似策略减少最优潮流(optimal power flow

OPF)调用。进而设计卷积神经网络(convolutional neural network

CNN)分类-回归代理模型，识别样本级尾部风险状态并预测强度，聚合估计可靠性指标。最后，在改进的RTS-GMLC区域1孤岛微电网算例中进行验证。结果表明，FAST-CVaR将OPF调用次数由60 000次减少至400次；CNN代理模型对两类可靠性尾部风险指标的估计相对误差分别为0.21%和0.51%，样本评估时间由743.504 s降至19.523 s。所提方法能够在保持尾部风险指标精度的同时显著降低计算开销，可为孤岛微电网尾部风险快速评估提供参考。

Abstract

To address the difficulty of balancing uncertainty representation

tail-risk evaluation

and computational efficiency in conventional reliability assessment

this paper develops a fast tail-risk reliability assessment framework. First

hourly capacity-factor series are constructed from measured data. By combining month-hour partitioning and conformal calibration

a conditional ellipsoidal uncertainty set for wind power under limited samples is established to characterize wind power fluctuations. Second

based on a DC optimal power flow (DC-OPF) minimum load shedding model

conditional value-at-risk (CVaR) is introduced to construct tail-risk indicators

and a FAST-CVaR approximation strategy is proposed to reduce the number of OPF evaluations. Furthermore

a convolutional neural network (CNN)-based classification-regression surrogate model is developed to identify sample-level tail-risk states and predict risk severity

enabling efficient estimation of reliability indicators through sample aggregation. Finally

the proposed method is validated on a modified RTS-GMLC Area 1 islanded microgrid. The results show that FAST-CVaR reduces the number of OPF evaluations from 60 000 to 400. The relative errors of the CNN surrogate model in estimating the two types of reliability tail-risk indicators are 0.21% and 0.51%

respectively

and the sample evaluation time is reduced from 743.504 s to 19.523 s. The proposed method can significantly reduce computational cost while maintaining the accuracy of tail-risk indicators

providing an effective approach for fast tail-risk reliability assessment of islanded microgrids.

关键词

Keywords

references

ZHAO Siying, SHAO Changzheng, DING Jinfeng, et al. Unreliability tracing of power systems for identifying the most critical risk factors considering mixed uncertainties in wind power output[J]. Protection and Control of Modern Power Systems, 2024, 9(5): 96-111.

LI X, LIU Y, GUO L, et al. Data-driven based uncertainty set modeling method for microgrid robust optimization with correlated wind power[J]. CSEE Journal of Power and Energy Systems, 2022, 9(2): 420-432.

ZUO L, WANG S, FANG J, et al. A quantitative accommodation guaranteed robust scheduling method for renewable power system with dynamic uncertainty set[J]. IEEE Transactions on Sustainable Energy, 2026, 17(1): 130-142.

SUN X, HUI W, DONG X, et al. Evaluating the reliability of microgrids consisting of renewable energy sources using stochastic scheduling based on the data-driven uncertainty set[J]. Engineering Applications of Artificial Intelligence, 2024, 133.

LI K, DUAN P, XUE Q, et al. Enhancing reliability assessment in distributed generation networks: Incorporating dynamic correlation of wind-solar power output uncertainty[J]. Sustainable Energy, Grids and Networks, 2024, 39.

LI X, XIE K, SHAO C, et al. A sensitivity-based rolling operational reliability evaluation method following the changing available generation capacity of renewable energies[J]. IEEE Transactions on Power Systems, 2024, 40(1): 166-177.

PANDIT D, SAKET R K, BERA A, et al. Reliability analysis of power grids considering component failures of variable energy resources[J]. IEEE Transactions on Industry Applications, 2025, 61(6): 8748-8759.

ZHANG S, LIU W, WAN H, et al. Combing data-driven and model-driven methods for high proportion renewable energy distribution network reliability evaluation[J]. International Journal of Electrical Power Energy Systems, 2023, 149.

WAHEED A, LI J. A hybrid model for efficient reliability assessment of power systems[J]. Sustainable Energy, Grids and Networks, 2025, 102.

KAMRUZZAMAN M, BHUSAL N, BENIDRIS M. A convolutional neural network-based approach to composite power system reliability evaluation[J]. International Journal of Electrical Power Energy Systems, 2022, 135.

ZHANG Y, CHEN Z, DONG X, et al. Multi-source-data- driven microgrids reliability analysis via power supply chain using deep learning[J]. Reliability Engineering System Safety, 2025, 111.

MARQUES F, PAULO C. Universal distribution of the empirical coverage in split conformal prediction[J]. Statistics Probability Letters, 2025, 219.

ZHU J, XU Y, TAI N, et al. Day-ahead joint chance- constrained optimal scheduling for distribution networks using partial input convex neural networks[J]. IEEE Transactions on Smart Grid, 2026, 17(1): 375-387.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Wind power ramp event prediction based on SWT-SDA and LightGBM

A novel optimal switching sequence model predictive voltage control for T-type three-level inverters

Optimal operation method for renewable energy islanded microgrids with embedded input convex neural network-based small-signal stability constraints

基于事件触发预设时间一致性的孤岛微电网电压二次控制

基于动态事件触发机制的孤岛微电网频率控制方法研究

Related Author

LI Chunli

HE Xiaoxia

WEN Jiale

LIU Yunbing

DOU Yinke

LÜ Jinyu

WANG Yu

LOU Xuanming

Related Institution

School of Mathematics and Systems Science, Wuhan University of Science and Technology

输变电装备技术全国重点实验室(重庆大学)

南洋理工大学电气与电子工程学院

GAO Kangjia(1. School of Electrical Engineering and Automation, Henan Polytechnic University

Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment (Henan Polytechnic University)

AI问答

⁰