A Forecasting Method for Frequency Regulation Capacity Demand Interval Based on Chance-Constrained Optimization

YAN Xin; ZHAO Xiaobin; TU Naiwei

doi:10.12096/j.2096-4528.pgt.25274

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

A Forecasting Method for Frequency Regulation Capacity Demand Interval Based on Chance-Constrained Optimization

更新时间：2026-09-30

- A Forecasting Method for Frequency Regulation Capacity Demand Interval Based on Chance-Constrained Optimization
- Power Generation Technology Pages: 1-9(2026)
- 作者机构：
  
  辽宁工程技术大学电气与控制工程学院，辽宁省葫芦岛市 125105
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(52177047;61601212)
- DOI：10.12096/j.2096-4528.pgt.25274
  CLC： TM 73;TK 01
- Received：16 June 2025，
  
  Revised：2025-09-21，
  
  Online First：30 September 2026，
- 稿件说明：
移动端阅览
阎馨,赵晓彬,屠乃威.基于机会约束优化的调频容量需求区间预测方法[J].发电技术,

YAN Xin,ZHAO Xiaobin,TU Naiwei.A Forecasting Method for Frequency Regulation Capacity Demand Interval Based on Chance-Constrained Optimization[J].Power Generation Technology,
阎馨,赵晓彬,屠乃威.基于机会约束优化的调频容量需求区间预测方法[J].发电技术, DOI：10.12096/j.2096-4528.pgt.25274.

YAN Xin,ZHAO Xiaobin,TU Naiwei.A Forecasting Method for Frequency Regulation Capacity Demand Interval Based on Chance-Constrained Optimization[J].Power Generation Technology, DOI：10.12096/j.2096-4528.pgt.25274.

摘要

目的

为实现“双碳”目标，新能源逐渐成为电力系统中装机容量和电量的主要来源。然而，新能源的波动性较强，导致电力系统频率波动加剧，进而增加了对调频能力的需求。为此，提出了一种基于机会约束优化的调频容量需求区间预测方法。

方法

利用改进的自适应噪声完备集合经验模态分解，对新能源、负荷、调频容量波动和气象等与调频容量波动相关的多种因素进行数据处理，建立调度时段的卷积神经网络-双向长短期记忆网络结合自注意力机制调频容量需求点预测模型；采用自适应带宽核密度估计，进行调频容量需求区间的确定，得到置信水平为95%的调频容量波动区间；从机组的实际调度出发，采用蒙特卡洛模拟法，实现调频容量需求区间上限的机会约束优化，以使调频容量需求区间上限更贴近实际值。

结果

所得调频容量需求区间满足实际调频要求，而且平均宽度会比其他方法减小11%~19%。

结论

所提方法可有效解决电力系统调频容量需求预测问题，从而提高电网调度的灵活性、稳定性和经济性。

Abstract

Objectives

To achieve the “dual carbon”goals

new energy sources are gradually becoming the primary contributors to both installed capacity and electricity generation in power systems. However

due to their strong volatility

the frequency fluctuations in the power system are increasing

leading to a higher demand for frequency regulation capacity. Therefore

this paper proposes a forecasting method for the frequency regulation capacity demand interval based on chance-constrained optimization.

Methods

The improved complete ensemble empirical mode decomposition with adoptive noise technique is used to process various factors related to frequency regulation capacity fluctuations

including new energy sources

load

frequency regulation capacity

and meteorological data. A convolutional neural network-bidirectional long short-term memory with self-attenion model is established to predict the point value of frequency regulation capacity demand during scheduling periods. Adaptive Bandwidth Kernel Density Estimation is employed to determine the interval of frequency regulation capacity demand

yielding a 95% confidence interval for the frequency regulation capacity demand. Based on actual unit scheduling

the Monte Carlo simulation method is applied to optimize the upper bound of the demand interval using chance-constrained optimization

thereby aligning the upper bound more closely with actual values.

Results

The predicted interval of frequency regulation capacity demand meets actual regulation requirements. Additionally

the average interval width is reduced by 11%-19% compared to other methods.

Conclusions

The proposed method effectively addresses the challenge of forecasting frequency regulation capacity demand in power systems

thereby enhancing the flexibility

stability

and economic efficiency of power grid scheduling.

关键词

Keywords

references

胡山鹰，金涌，张臻烨．发展新质生产力，实现碳中和 [J ] ．发电技术， 2025 ， 46 ( 1 )： 1 - 8 ． doi: 10.12096/j.2096-4528.pgt.24222 http://dx.doi.org/10.12096/j.2096-4528.pgt.24222

HU S Y ， JIN Y ， ZHANG Z Y ． Developing new quality productive forces to achieve carbon neutrality [J ] ． Power Generation Technology ， 2025 ， 46 ( 1 )： 1 - 8 ． doi: 10.12096/j.2096-4528.pgt.24222 http://dx.doi.org/10.12096/j.2096-4528.pgt.24222

郁海彬，严威，文光磊，等．双碳约束下高渗透新能源电力系统特性分析、提升路径及多元市场机制设计 [J ] ．电力大数据， 2023 ， 26 ( 3 )： 77 - 88 ．

YU H B ， YAN W ， WEN G L ， et al ． Characteristics analysis，promotion path and multi-market mechanism design of high permeability new energy power system under double carbon constraint [J ] ． Power Systems and Big Data ， 2023 ， 26 ( 3 )： 77 - 88 ．

胡泽春，谢旭，张放，等．含储能资源参与的自动发电控制策略研究 [J ] ．中国电机工程学报， 2014 ， 34 ( 29 )： 5080 - 5087 ．

HU Z C ， XIE X ， ZHANG F ， et al ． Research on automatic generation control strategy incorporating energy storage resources [J ] ． Proceedings of the CSEE ， 2014 ， 34 ( 29 )： 5080 - 5087 ．

HOLTTINEN H ， MILLIGAN M ， ELA E ， et al ． Methodologies to determine operating reserves due to increased wind power [J ] ． IEEE Transactions on Sustainable Energy ， 2012 ， 3 ( 4 )： 713 - 723 ． doi: 10.1109/tste.2012.2208207 http://dx.doi.org/10.1109/tste.2012.2208207

钟浩，张小兵，李飞，等．考虑中长期交易的水电站电转气容量双层优化配置 [J ] ．高电压技术， 2023 ， 49 ( 2 )： 822 - 830 ．

ZHONG H ， ZHANG X B ， LI F ， et al ． Optimal allocation of power-to-gas capacity of hydropower stations considering double-layer medium and long-term transactions [J ] ． High Voltage Engineering ， 2023 ， 49 ( 2 )： 822 - 830 ．

LEI X Y ， YANG Z F ， YU J ， et al ． Data-driven optimal power flow：a physics-informed machine learning approach [J ] ． IEEE Transactions on Power Systems ， 2021 ， 36 ( 1 )： 346 - 354 ． doi: 10.1109/tpwrs.2020.3001919 http://dx.doi.org/10.1109/tpwrs.2020.3001919

YANG Y ， YU J ， YANG Z F ， et al ． A trustable data-driven framework for composite system reliability evaluation [J ] ． IEEE Systems Journal ， 2022 ， 16 ( 4 )： 6697 - 6707 ． doi: 10.1109/jsyst.2021.3131822 http://dx.doi.org/10.1109/jsyst.2021.3131822

刘礼恺，胡泽春，罗浩成，等．基于数据驱动和条件概率的调频容量需求计算方法 [J ] ．电网技术， 2021 ， 45 ( 7 )： 2569 - 2576 ．

LIU L K ， HU Z C ， LUO H C ， et al ． Data-driven based regulation reserve capacity requirement calculation using conditional probability [J ] ． Power System Technology ， 2021 ， 45 ( 7 )： 2569 - 2576 ．

张小兵，雷星雨，刘育明，等．基于调度时段内波动极值可信预测的调频容量需求量化方法 [J ] ．中国电机工程学报， 2025 ， 45 ( 21 )： 8431 - 8445 ．

ZHANG X B ， LEI X Y ， LIU Y M ， et al ． Method for quantifying frequency regulation capacity requirements based on credible prediction of fluctuation extremum in the dispatch period [J ] ． Proceedings of the CSEE ， 2025 ， 45 ( 21 )： 8431 - 8445 ．

QU S P ， YANG Z F ． Optimality guaranteed UC acceleration via interactive utilization of adjoint model [J ] ． IEEE Transactions on Power Systems ， 2023 ， 39 ( 3 )： 5191 - 5203 ． doi: 10.1109/tpwrs.2023.3329986 http://dx.doi.org/10.1109/tpwrs.2023.3329986

吴志，李广焕，顾伟．考虑耦合电压稳定联合机会约束的新型配电网优化运行研究 [J ] ．中国电机工程学报， 2026 ， 46 ( 2 )： 493 - 505 ．

WU Z ， LI G H ， GU W ． Study on optimal operation of new distribution network considering coupled voltage stability and joint opportunity constraint [J ] ． Proceedings of the CSEE ， 2026 ， 46 ( 2 )： 493 - 505 ．

雷星雨，杨林泽，陈咏涛，等．计及自动发电控制精细响应动作的机会约束经济调度方法 [J ] ．电力系统自动化， 2025 ， 49 ( 5 )： 118 - 127 ．

LEI X Y ， YANG L Z ， CHEN Y T ， et al ． Chance-constrained economic dispatch method considering fine-grained response actions of automatic generation control [J ] ． Automation of Electric Power Systems ， 2025 ， 49 ( 5 )： 118 - 127 ．

刘慧鑫，沈晓东，魏泽涛，等．基于校准窗口集成与耦合市场特征的可解释双层日前电价预测 [J ] ．中国电机工程学报， 2024 ， 44 ( 4 )： 1272 - 1286 ．

LIU H X ， SHEN X D ， WEI Z T ， et al ． Interpretable two-layer day-ahead electricity price forecast based on calibration window combination and coupled market characteristics [J ] ． Proceedings of the CSEE ， 2024 ， 44 ( 4 )： 1272 - 1286 ．

LIU N ， TANG Q F ， ZHANG J H ， et al ． A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids [J ] ． Applied Energy ， 2014 ， 129 ： 336 - 345 ． doi: 10.1016/j.apenergy.2014.05.023 http://dx.doi.org/10.1016/j.apenergy.2014.05.023

XU X Q ， CHEN Y ， GOUDE Y ， et al ． Day-ahead probabilistic forecasting for French half-hourly electricity loads and quantiles for curve-to-curve regression [J ] ． Applied Energy ， 2021 ， 301 ： 117465 ． doi: 10.1016/j.apenergy.2021.117465 http://dx.doi.org/10.1016/j.apenergy.2021.117465

SU Q ， LU H L ， YIN X ， et al ． Hybrid point-interval prediction method for stochastic dynamic response of subsea umbilical cable based on BO-BiLSTM and adaptive bandwidth KDE [J ] ． Ocean Engineering ， 2025 ， 320 ： 120317 ． doi: 10.1016/j.oceaneng.2025.120317 http://dx.doi.org/10.1016/j.oceaneng.2025.120317

ABDOOS A A ， ABDOOS H ， KAZEMITABAR J ， et al ． An intelligent hybrid method based on Monte Carlo simulation for short-term probabilistic wind power prediction [J ] ． Energy ， 2023 ， 278 ： 127914 ． doi: 10.1016/j.energy.2023.127914 http://dx.doi.org/10.1016/j.energy.2023.127914

VITHAYASRICHAREON P ， MACGILL I F ． Incorporating short-term operational plant constraints into assessments of future electricity generation portfolios [J ] ． Applied Energy ， 2014 ， 128 ： 144 - 155 ． doi: 10.1016/j.apenergy.2014.04.052 http://dx.doi.org/10.1016/j.apenergy.2014.04.052

ZHANG X P ， SHAHIDEHPOUR M ， ALABDULWAHAB A ， et al ． Hourly electricity demand response in the stochastic day-ahead scheduling of coordinated electricity and natural gas networks [J ] ． IEEE Transactions on Power Systems ， 2015 ， 31 ( 1 )： 592 - 601 ． doi: 10.1109/tpwrs.2015.2390632 http://dx.doi.org/10.1109/tpwrs.2015.2390632

ZHANG C ， JI C L ， HUA L ， et al ． Evolutionary quantile regression gated recurrent unit network based on variational mode decomposition，improved whale optimization algorithm for probabilistic short-term wind speed prediction [J ] ． Renewable Energy ， 2022 ， 197 ： 668 - 682 ． doi: 10.1016/j.renene.2022.07.123 http://dx.doi.org/10.1016/j.renene.2022.07.123

WANG J Z ， WANG S ， ZENG B ， et al ． A novel ensemble probabilistic forecasting system for uncertainty in wind speed [J ] ． Applied Energy ， 2022 ， 313 ： 118796 ． doi: 10.1016/j.apenergy.2022.118796 http://dx.doi.org/10.1016/j.apenergy.2022.118796

焦润海，褚佳杰，李俊良，等．基于数据分解的多区域个性化联邦负荷预测方法 [J ] ．中国电机工程学报， 2025 ， 45 ( 5 )： 1691 - 1704 ．

JIAO R H ， CHU J J ， LI J L ， et al ． Personalized federated multi-region load forecasting method based on data decomposition [J ] ． Proceedings of the CSEE ， 2025 ， 45 ( 5 )： 1691 - 1704 ．

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Evaluation of Comprehensive Benefits of Electric Energy Substitution in Regional Power Grids Based on Improved Cloud Model

Research on the Development Trends and Countermeasures of Integrated Energy Services

Architecture Design of Virtual Power Plant Based on “Three Flow Separation-Convergence”

Study on Participation of Electricity-driven Thermal Load in Real-time Scheduling of New Power System

Analysis and Prediction of Energy Losses in AC/DC Conversion Processes for China’s New Power Systems

Related Author

ZHENG Yang

REN Yucheng

WANG Yuwei

XU Dingji

YANG Huimin

LAN Guoqin

LU Ye

KAN Yansheng

Related Institution

Zhenjiang Power Supply Branch, State Grid Jiangsu Electric Power Company Limited

State Grid Jiangsu Electric Power Company Limited

School of Electrical Engineering, Southeast University

China Huadian Group Co., Ltd., Xicheng District

Jiangsu Huadian Wangting Natural Gas Power Generation Co., Ltd.

AI问答

⁰