Hierarchical Early-warning for Multi-period Balance Risk in Look-ahead Dispatch of Power Grid Considering Uncertainty of Wind Power

MU Zeyu; CHEN Siyuan; XU Peidong; SI Ruiqi; ZHANG Jun; XU Jian; HUANG He; CHEN Yiping

doi:10.7500/AEPS20241127005

您当前的位置：

首页 >

文章列表页 >

Hierarchical Early-warning for Multi-period Balance Risk in Look-ahead Dispatch of Power Grid Considering Uncertainty of Wind Power

Basic Research | 更新时间：2026-02-28

- Hierarchical Early-warning for Multi-period Balance Risk in Look-ahead Dispatch of Power Grid Considering Uncertainty of Wind Power
- Automation of Electric Power Systems Vol. 50, Issue 1, Pages: 61-73(2026)
- 作者机构：
  
  1.武汉大学电气与自动化学院，湖北省武汉市 430072
  2.中国南方电网电力调度控制中心，广东省广州市 510663
  3.南方电网新型电力系统（北京）研究院有限公司，北京市 102218
- 作者简介：
- 基金信息：
  
  National Key R&D Program of China(2022YFB2403500)
- DOI：10.7500/AEPS20241127005
  CLC：
- Received：27 November 2024，
  
  Revised：2025-04-19，
  
  Online First：18 August 2025，
  
  Published：10 January 2026
- 稿件说明：
移动端阅览
穆泽雨,陈思远,许沛东等.计及风电不确定性的电网前瞻调度多时段平衡风险分级预警[J].电力系统自动化,2026,50(1):61-73.

MU Zeyu,CHEN Siyuan,XU Peidong,et al.Hierarchical Early-warning for Multi-period Balance Risk in Look-ahead Dispatch of Power Grid Considering Uncertainty of Wind Power[J].Automation of Electric Power Systems,2026,50(1):61-73.
穆泽雨,陈思远,许沛东等.计及风电不确定性的电网前瞻调度多时段平衡风险分级预警[J].电力系统自动化,2026,50(1):61-73. DOI： 10.7500/AEPS20241127005.

MU Zeyu,CHEN Siyuan,XU Peidong,et al.Hierarchical Early-warning for Multi-period Balance Risk in Look-ahead Dispatch of Power Grid Considering Uncertainty of Wind Power[J].Automation of Electric Power Systems,2026,50(1):61-73. DOI： 10.7500/AEPS20241127005.

摘要

随着风电逐渐成为电力供应主体，风电不确定性引发的日内功率预测偏差将使电力平衡面临严峻挑战。前瞻调度是衔接日前调度计划与日内自动发电控制的有效手段。为此，提出风电不确定性下电网前瞻调度平衡风险分级预警方法。首先，构建前瞻调度约束集以刻画系统的运行边界，通过解析化数学推导分析了风电不确定性对系统运行边界的影响，并在此基础上提出了计及多资源爬坡能力的平衡风险分级预警机制。然后，提出基于点估计与矩阵正态分布理论的样本增强方法，通过参数化数据生成方式扩充少数类样本，提高模型的预测准确率与场景覆盖率。最后，基于净负荷偏差与资源可调容量两个关键指标，构建前瞻调度的多时段平衡风险预警模型，对未来几小时系统的平衡风险进行分级预警。在IEEE 118节点标准算例中进行了仿真验证，结果表明，所提方法可快速准确地对未来几小时系统的平衡风险进行预警，分级预警结果能为前瞻调度提供有效的参考信息。

Abstract

As wind power increasingly becomes the mainstay of electricity supply

intra-day prediction deviations stemming from wind power uncertainty pose severe challenges to power balance. Look-ahead dispatch serves as an effective bridge between day-ahead dispatch and intra-day automatic generation control. To this end

a hierarchical early-warning method for balance risks in look-ahead dispatch of power grid considering the uncertainty of wind power is proposed. Furthermore

a sample enhancement method based on point estimation and matrix normal distribution theory is introduced. The parametric data generation mode is used to expand minority-class samples and enhance the model prediction accuracy and scenario coverage. Finally

based on the two key indicators of net load deviation and adjustable resource capacity

an early-warning model for multi-period balance risk in look-ahead dispatch is constructed to provide hierarchical early-warning for the balance risk of the system in the next few hours. Simulation on the IEEE 118-bus test system verify that the proposed method can rapidly and accurately provide early-warning of balance risks in the next few hours

and the hierarchical warnings furnish valuable reference information for look-ahead dispatch.

关键词

Keywords

references

2025年中国风电年新增装机或超 1 亿千瓦［EB/OL］.［ 2025-01-11 ］. http：//www.newenergy.org.cn/fn/cydt/202502/t20250218_823293.html http://www.newenergy.org.cn/fn/cydt/202502/t20250218_823293.html .

In 2025 ， the annual installed capacity of wind power in China will exceed 100 million kilowatts ［EB/OL］. ［ 2025-01-11 ］. http：//www.newenergy.org.cn/fn/cydt/202502/t20250218_823293.html http://www.newenergy.org.cn/fn/cydt/202502/t20250218_823293.html .

云南电网 1 500 万千瓦新能源并网背后“应并尽并”“能并快并” ［EB/OL］.［ 2024-10-27 ］. https：//www.csg.cn/xwzx/2023/gsyw/202312/t20231229_338292.html https://www.csg.cn/xwzx/2023/gsyw/202312/t20231229_338292.html .

Behind the grid connection of 15 million kilowatts of new energy in Yunnan Power Grid—“connect as much as possible” and “connect as fast as possible” ［EB/OL］. ［ 2024-10-27 ］. https：//www.csg.cn/xwzx/2023/gsyw/202312/t20231229_338292.html https://www.csg.cn/xwzx/2023/gsyw/202312/t20231229_338292.html .

闫炯程，李常刚，刘玉田 . 数据驱动的新型电力系统安全风险预警综述［J］. 电网技术， 2024 ， 48 （ 12 ）： 4989 - 5002 .

YAN Jiongcheng ， LI Changgang ， LIU Yutian . Review of data-driven security risk early warning research of the new-type power system ［J］. Power System Technology ， 2024 ， 48 （ 12 ）： 4989 - 5002 .

MU Z Y ， XU P D ， ZHANG K ， et al . Cascading fault early warning and location method of transmission networks based on wide area time-series power system state ［J］. IEEE Journal of Radio Frequency Identification ， 2022 ， 7 ： 6 - 11 .

陈达，朱林，张健，等 . 基于卷积神经网络的暂态电压稳定评估及风险量化［J］. 电力系统自动化， 2021 ， 45 （ 14 ）： 65 - 71 .

CHEN Da ， ZHU Lin ， ZHANG Jian ， et al . Transient voltage stability assessment and risk quantification based on convolutional neural network ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 14 ）： 65 - 71 .

闫炯程 . 交直流大电网安全风险态势前瞻预警研究［D］. 济南：山东大学， 2022 .

YAN Jiongcheng . Studies on security risk situation early warning for large scale hybrid AC/DC grids ［D］. Jinan ： Shandong University ， 2022 .

YAN J C ， LI C G ， LIU Y T . Insecurity early warning for large scale hybrid AC/DC grids based on decision tree and semi-supervised deep learning ［J］. IEEE Transactions on Power Systems ， 2021 ， 36 （ 6 ）： 5020 - 5031 .

闫炯程，李常刚，刘玉田 . 计及源荷不确定性的交直流大电网动态安全分级滚动预警［J］. 电力系统自动化， 2023 ， 47 （ 1 ）： 35 - 43 .

YAN Jiongcheng ， LI Changgang ， LIU Yutian . Graded rolling early warning of dynamic security for large-scale AC/DC power grid considering uncertainties on source and load sides ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 1 ）： 35 - 43 .

ZHU L P ， LU C ， LUO Y H . Time series data-driven batch assessment of power system short-term voltage security ［J］. IEEE Transactions on Industrial Informatics ， 2020 ， 16 （ 12 ）： 7306 - 7317 .

MENG Y ， YU Z ， LU N ， et al . Time series classification for locating forced oscillation sources ［J］. IEEE Transactions on Smart Grid ， 2021 ， 12 （ 2 ）： 1712 - 1721 .

XU J ， JIANG X X ， LIAO S Y ， et al . High-dimensional feature selection for power system congestion event prognosis with enhanced evolutionary computation ［J］. IEEE Transactions on Power Systems ， 2024 ， 39 （ 1 ）： 1752 - 1770 .

王邦彦，皮俊波，王秀丽，等 . 天气数据驱动下基于深度主动学习的新型电力系统供需失衡风险快速评估方法［J］. 电网技术， 2024 ， 48 （ 10 ）： 4050 - 4060 .

WANG Bangyan ， PI Junbo ， WANG Xiuli ， et al . A fast assessment method for supply-demand imbalance risk of new power systems based on deep active learning driven by weather data ［J］. Power System Technology ， 2024 ， 48 （ 10 ）： 4050 - 4060 .

YAN J C ， LI C G ， LIU Y T ， et al . Incremental model evolution for power system security early warning based on knowledge distillation and active learning ［J］. IEEE Transactions on Industrial Informatics ， 2024 ， 20 （ 11 ）： 12958 - 12968 .

董骁翀，孙英云，蒲天骄，等 . 基于时序混合密度网络的超短期风电功率概率预测［J］. 电力系统自动化， 2022 ， 46 （ 14 ）： 93 - 100 .

DONG Xiaochong ， SUN Yingyun ， PU Tianjiao ， et al . Ultra-short-term probabilistic forecasting of wind power based on temporal mixture density network ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 14 ）： 93 - 100 .

李丹，方泽仁，缪书唯，等 . 考虑训练样本分布不均衡的超短期风电功率概率预测［J］. 电网技术， 2024 ， 48 （ 3 ）： 1133 - 1147 .

LI Dan ， FANG Zeren ， MIAO Shuwei ， et al . Probability prediction of ultra-short-term wind power considering unbalanced distribution of training samples ［J］. Power System Technology ， 2024 ， 48 （ 3 ）： 1133 - 1147 .

ZHANG H ， LIU Y Q ， YAN J ， et al . Improved deep mixture density network for regional wind power probabilistic forecasting ［J］. IEEE Transactions on Power Systems ， 2020 ， 35 （ 4 ）： 2549 - 2560 .

吕崇帅 . 含风光水储电源的电力系统优化调度研究［D］. 哈尔滨：哈尔滨工业大学， 2016 .

LÜ Chongshuai . Research on power system optimal dispatch with wind-PV-hydro-storage power source ［D］. Harbin ： Harbin Institute of Technology ， 2016 .

辛禾 . 考虑多能互补的清洁能源协同优化调度及效益均衡研究［D］. 北京：华北电力大学， 2019 .

XIN He . The synergetic optimal scheduling and benefit equilibrium model for clean energy absorptive considering multi-energy hybrid ［D］. Beijing ： North China Electric Power University ， 2019 .

南方能源监管局 . 南方区域电力并网运行管理实施细则［S］. 2022 .

South China Energy Regulatory Bureau . Implementation rules for the grid-connected operation and management of southern regional power ［S］. 2022 .

南方能源监管局 . 南方区域风电并网运行及辅助服务管理实施细则［S］. 2022 .

South China Energy Regulatory Bureau . Implementation rules for grid-connected operation and auxiliary service management of wind power in southern region ［S］. 2022 .

南方能源监管局 . 南方区域新型储能并网运行及辅助服务管理实施细则［S］. 2022 .

South China Energy Regulatory Bureau . Implementation rules for the grid-connected operation and auxiliary service management of new energy storage in the southern region ［S］. 2022 .

南方能源监管局 . 南方区域可调节负荷并网运行管理及辅助服务管理实施细则［S］. 2022 .

South China Energy Regulatory Bureau . Implementation rules of operation management and auxiliary service management of adjustable load connected to the grid in southern region ［S］. 2022 .

南方能源监管局 . 南方区域电力市场现货电能量交易实施细则［S］. 2022 .

South China Energy Regulatory Bureau . Implementation rules of spot power energy trading in southern regional power market ［S］. 2022 .

DUTILLEUL P . The MLE algorithm for the matrix normal distribution ［J］. Journal of Statistical Computation and Simulation ， 1999 ， 64 （ 2 ）： 105 - 123 .

DING S S ， COOK R D . Dimension folding PCA and PFC for matrix-valued predictors ［J］. Statistica Sinica ， 2014 （ 24 ）： 463 - 492 .

MOORE R H . Regression graphics： ideas for studying regressions through graphics ［J］. Technometrics ， 1999 ， 41 （ 4 ）： 368 - 369 .

COOK R D . Fisher lecture： dimension reduction in regression ［J］. Statistical Science ， 2007 ， 22 （ 1 ）： 1 - 26 .

JAYNES E T . Information theory and statistical mechanics ［J］. Physical Review ， 1957 ， 106 （ 4 ）： 620 - 630 .

FISHER R A . On the mathematical foundations of theoretical statistics ［J］. Philosophical Transactions of the Royal Society of London ， 1922 ， 222 （ 594-604 ）： 309 - 368 .

GOODFELLOW I J ， POUGET-ABADIE J ， MIRZA M ， et al . Generative adversarial networks ［EB/OL］. ［ 2024-10-27 ］. https：//arxiv.org/abs/1406.2661v1 https://arxiv.org/abs/1406.2661v1 .

KINGMA D P ， WELLING M . Auto-encoding variational Bayes ［EB/OL］. ［ 2024-10-27 ］. https：//arxiv.org/abs/1312.6114v11 https://arxiv.org/abs/1312.6114v11 .

马欢，李常刚，刘玉田 . 风电爬坡事件多级区间预警方法［J］. 电力系统自动化， 2017 ， 41 （ 11 ）： 39 - 47 .

MA Huan ， LI Changgang ， LIU Yutian . Multi-level early warning method for wind power ramp events ［J］. Automation of Electric Power Systems ， 2017 ， 41 （ 11 ）： 39 - 47 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-period Online Preventive Control Strategy for Power Grid with High Proportion of Renewable Energy Based on Reinforcement Learning

Distributed Algorithm for Robust Economic Dispatch of Integrated Transmission and Distribution System Considering Wind Power Uncertainty

Collaborative Robust Planning of Electric and Thermal Flexibility Resources Considering Reserve Optimization

Bi-layer Uncertainty Economic Scheduling for Port Multi-energy Microgrid with Cascade Utilization of Cold Energy

Related Author

JIANG Tao

QIE Zhaohui

LI Wei

LI Zhaowei

WU Xuelian

HUANG Xinyi

LIU Mingbo

LIN Shunjiang

Related Institution

Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education (Northeast Electric Power University)

State Grid Electric Power Research Institute (NARI Group Corporation)

School of Power Engineering, South China University of Technology

Guangdong Key Laboratory of Clean Energy Technology

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University)

⁰