Data driven based strategy of plant-level load dispatch for the coal-fired power plant

DIAO Bing; BI Zhiying; XU Jing

doi:10.19944/j.eptep.1674-8069.2026.04.006

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Data driven based strategy of plant-level load dispatch for the coal-fired power plant

New\-generation flexibility control technologies for coal\-fired power plants | 更新时间：2026-10-14

- Data driven based strategy of plant-level load dispatch for the coal-fired power plant
- Electric Power Technology and Environmental Protection Vol. 42, Issue 4, Pages: 574-581(2026)
- 作者机构：
  
  1.中国五洲工程设计集团有限公司，北京 100053
  2.太原理工大学电气与动力工程学院，山西太原 030024
- 作者简介：
- 基金信息：
- DOI：10.19944/j.eptep.1674-8069.2026.04.006
  CLC： TK01
- Received：05 February 2026，
  
  Accepted：19 June 2026，
  
  Published：15 August 2026
- 稿件说明：
移动端阅览
刁冰,毕志颖,徐婧.基于数据驱动的厂级负荷分配优化策略研究[J].电力科技与环保,2026,42(4):574-581.

DIAO Bing, BI Zhiying, XU Jing. Data driven based strategy of plant-level load dispatch for the coal-fired power plant[J]. Electric Power Technology and Environmental Protection, 2026, 42(4):574-581.
刁冰,毕志颖,徐婧.基于数据驱动的厂级负荷分配优化策略研究[J].电力科技与环保,2026,42(4):574-581. DOI： 10.19944/j.eptep.1674-8069.2026.04.006.

DIAO Bing, BI Zhiying, XU Jing. Data driven based strategy of plant-level load dispatch for the coal-fired power plant[J]. Electric Power Technology and Environmental Protection, 2026, 42(4):574-581. DOI： 10.19944/j.eptep.1674-8069.2026.04.006.

摘要

目的

在双碳目标推动下，煤电机组正由基荷电源向灵活调节电源转型，长期低负荷运行导致供电煤耗显著升高。如何科学分配厂内多台机组负荷以实现全厂能耗最优，是火电行业亟需解决的关键问题。

方法

以某虚拟电厂1 000 MW、600 MW和300 MW 3类6台机组为研究对象，提出一种数据驱动的厂级负荷优化分配策略。采用灰色关联分析筛选影响供电煤耗率的关键参数，结合XGBoost算法构建煤耗特性预测模型；以全厂供电煤耗率最低为目标，引入基于历史成功的自适应参数差分进化算法，动态求解最优厂级负荷分配方案。

结果

研究表明，本文提出的供电煤耗率预测模型的相对误差在±0.05%之间波动，提出的厂级负荷分配优化策略在不同总负荷需求下均可实现全厂能耗的最小化，节煤潜力随着总负荷呈先增加后降低的变化趋势；当厂级负荷达到2 600 MW时，厂级负荷优化分配的供电煤耗率仅为312.29 g/（kW·h），与传统调度模式相比，节煤潜力最高可达1.92 g/（kW·h）。

结论

本文提出的数据驱动厂级负荷分配策略为火电厂在灵活运行工况下挖掘节能潜力提供了低成本、高效率的技术路径，为构建清洁低碳、安全高效的新型电力系统提供了支撑。

Abstract

Objective

Driven by the carbon peaking and carbon neutrality goals

coal-fired units are transitioning from baseload to flexible regulation power sources

resulting in prolonged low-load operation and a significant increase in net standard coal consumption. Scientifically allocating loads among multiple units to minimize plant-level energy consumption has become a critical issue for the thermal power industry.

Methods

This study takes six units of three types (1 000

600 and 300 MW) from a virtual power plant as the research objects

a data-driven plant-level load optimization strategy is proposed. Grey relational analysis is employed to screen key parameters affecting the net standard coal consumption rate

and an XGBoost-based coal consumption characteristic prediction model is constructed. With the objective of minimizing the plant-level net standard coal consumption rate

an adaptive parameter differential evolution algorithm based on historical success is introduced to dynamically solve the optimal load dispatch scheme satisfying grid load commands.

Results

The results indicate that the relative error of the proposed coal consumption rate prediction model fluctuates within 0.05%. The plant-level load allocation optimization strategy proposed in this paper achieves minimized overall energy consumption under varying total load demands. The coal-saving potential exhibits a trend of first increasing and then decreasing with the total load. When the plant-level load reaches 2 600 MW

the net standard coal consumption rate under the optimized load dispatch is only 312.29 g/(kW·h).Compared to conventional dispatch modes

it demonstrates a maximum coal-saving potential of 1.92 g/(kW·h)

effectively reducing both plant-wide fuel consumption and carbon emissions.

Conclusion

The proposed data-driven plant-level load allocation strategy proposed herein offers a low-cost

high-efficiency technical pathway for thermal power plants to unlock energy-saving potential under flexible operating conditions. This provides support for establishing a new power system that is clean

low-carbon

safe

and efficient.

关键词

Keywords

references

王志轩 , 张晶杰 , 董博 , 等 . “双碳”目标下燃煤电厂灵活性改造及政策建议 [J ] . 电力科技与环保 , 2024 , 40 ( 3 ): 213 - 220 .

WANG Zhixuan , ZHANG Jingjie , DONG Bo , et al . Research on technology and policy of flexibility renovation for coal-fired power plants under carbon peaking and carbon neutrality goal [J ] . Electric Power Technology and Environmental Protection , 2024 , 40 ( 3 ): 213 - 220 .

ZHAO G J , CUI Z P , XU J , et al . Hybrid modeling-based digital twin for performance optimization with flexible operation in the direct air-cooling power unit [J ] . Energy , 2022 , 254 : 124492 .

杨尚谦 , 王双童 . 煤电机组转型升级中的功能研究 [J ] . 电力科技与环保 , 2020 , 36 ( 6 ): 10 - 13 .

YANG Shangqian , WANG Shuangtong . Functional research on transformation and upgrading of coal power unit [J ] . Electric Power Technology and Environment Protection , 2020 , 36 ( 6 ): 10 - 13 .

何青波 . 基于源网荷状态的火电机组优化控制研究 [D ] . 北京 : 华北电力大学 , 2021 .

HE Qingbo . Research on optimal control and simulation of thermal power unit based on source-grid-load state [D ] . Beijing : North China Electric Power University , 2021 .

俞颖 . 全球电力发展现状 [J ] . 电力科技与环保 , 2025 , 41 ( 1 ): F0003 .

YU Ying . Current situation of global power development [J ] . Electric Power Technology and Environmental Protection , 2025 , 41 ( 1 ): F0003 .

LI Z , LI C P , FANG Y J , et al . The paradigm shift in China’s energy consumption: A multi-timescale interpretation of coal consumption fluctuations [J ] . Energy Conversion and Management , 2025 , 341 : 120074 .

谭天宇 . 计及经济性与快速性的厂级负荷优化分配研究 [D ] . 北京 : 华北电力大学 , 2019 .

TAN Tianyu . Research on optimal load dispatch of thermal power plant considering economy and speediness [D ] . Beijing : North China Electric Power University , 2019 .

邢耀敏 . 基于改进粒子群算法的厂级AGC优化分配方法 [J ] . 自动化应用 , 2024 , 65 ( 1 ): 197 - 200 .

XING Yaomin . Optimal allocation method of factory-level AGC based on improved particle swam algorithm [J ] . Automation Application , 2024 , 65 ( 1 ): 197 - 200 .

李佳丽 . 考虑机组动态特性的热电厂厂级负荷分配研究 [D ] . 大连：大连理工大学 , 2024 .

LI Jiali . Research on plant-level load distribution in the combined heat power plant considering unit dynamic characteristics [D ] . Dalian : Dalian University of Technology , 2024 .

陈筑 , 周运虎 , 徐仁博 , 等 . 多类型热电机组群实时负荷动态分配方法 [J ] . 电力自动化设备 , 2023 , 43 ( 6 ): 217 - 224 .

CHEN Zhu , ZHOU Yunhu , XU Renbo , et al . Dynamic allocation method of real-time load for multi-type CHP unit group [J ] . Electric Power Automation Equipment , 2023 , 43 ( 6 ): 217 - 224 .

汪茹康 , 周家辉 , 徐钢 , 等 . 深度调峰背景下的厂级热电负荷分配优化 [J ] . 动力工程学报 , 2023 , 43 ( 2 ): 185 - 193 .

WANG Rukang , ZHOU Jiahui , XU Gang , et al . Optimizaton of plant-level thermal and power load distribution under the back-ground of deep peak shaving [J ] . Journal of Chinese Society of Power Engineering , 2023 , 43 ( 2 ): 185 - 193 .

牟柯昱 , 司风琪 , 邵壮 , 等 . 基于分位数回归的厂级自适应经济负荷分配 [J ] . 热能动力工程 , 2021 , 36 ( 11 ): 164 - 172 .

MOU Keyu , SI Fengqi , SHAO Zhuang , et al . Plant-level adaptive and economic load dispatch based on quantile regression [J ] . Journal of Engineering for Thermal Energy and Power , 2021 , 36 ( 11 ): 164 - 172 .

牟柯昱 . 基于数据挖掘的火电机组运行优化研究 [D ] . 南京：东南大学 , 2021 .

MOU Keyu . Research on optimal operation of thermal power unit based on data mining [D ] . Nanjing : Southeast University , 2021 .

李东麟 , 朱建宏 , 王华广 , 等 . 基于改进人工蜂群动态规划的厂级负荷优化分配 [J ] . 热力发电 , 2022 , 51 ( 3 ): 153 - 158 .

LI Donglin , ZHU Jianhong , WANG Huaguang , et al . Plant-level load optimal distribution based on improved artificial bee colony dynamic programming [J ] . Thermal Power Generation , 2022 , 51 ( 3 ): 153 - 158 .

杨皓 . 基于数据分析及改进遗传算法的厂级负荷优化分配研究 [D ] . 北京：华北电力大学 , 2021 .

YANG Hao . Research on optimal load distribution at thermal power plant based on data analysis and improved genetic algorithm [D ] . Beijing : North China Electric Power University , 2021 .

慕昀翰 . 基于燃煤机组深度调峰安全性条件下负荷优化分配 [D ] . 北京 : 华北电力大学 , 2021 .

MU Yunhan . Based on deep peak shaving safety load distribution optimization of coal fired units [D ] . Beijing : North China Electric Power University , 2021 .

刘梦杰 . 基于改进长短期记忆神经网络的火电机组动态煤耗建模 [D ] . 北京：华北电力大学 , 2023 .

LIU Mengjie . Dynamic coal consumption modeling of thermal power units based on improved long and short-term memory neural network [D ] . Beijing : North China Electric Power University , 2023 .

XU J , BI D P , MA S X , et al . A data-based approach for benchmark interval determination with varying operating conditions in the coal-fired power unit [J ] . Energy , 2020 , 211 : 118555 .

刘吉 , 刘炳含 , 张月 , 等 . 基于大数据技术的火电厂节能环保多目标负荷优化分配 [J ] . 工程热物理学报 , 2020 , 41 ( 1 ): 29 - 38 .

LIU Ji , LIU Binghan , ZHAN Yue , et al . Energy-saving and environmental protection multi-target load dispatching of thermal power plants based on big data technology [J ] . Journal of Engineering Thermophysics , 2020 , 41 ( 1 ): 29 - 38 .

DONG L J , CHEN D G , WANG N L , et al . Key energy-consumption feature selection of thermal power systems based on robust attribute reduction with rough sets [J ] . Information Sciences , 2020 , 532 : 61 - 71 .

ZHU C , ZHANG G M , ZHU K Y , et al . Control-oriented modeling and dynamic energy balance control strategy of steam generation system in coal-fired power plants [J ] . Applied Energy , 2026 , 404 : 127172 .

张磊 , 熊健 , 金龙云 , 等 . 基于改进决策树的发电运行控制优化技术 [J ] . 电子设计工程 , 2024 , 32 ( 21 ): 65 - 69 .

ZHANG Lei , XIONG Jian , JIN Longyun , et al . Optimization technology for power generation operation control based on improved decision tree [J ] . Electronic Design Engineering , 2024 , 32 ( 21 ): 65 - 69 .

崔智鹏，徐婧，冯征，等 . 数据-机理融合的汽轮机末级排汽焓在线测量 [J ] . 中国电机工程学报 , 2023 , 43 ( 4 ): 1369 - 1377 .

CUI Zhipeng , XU Jing , FENG Zheng , et al . Data and mechanism based online measurement of the discharged steam enthalpy for steam turbine [J ] . Proceedings of the Chinese Society for Electrical Engineering , 2023 , 43 ( 4 ): 1369 - 1377 .

FRIEDMAN J H . Greedy function approximation: A gradient boosting machine [J ] . The Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

THONGSUWAN S , JAIYEN S , PADCHAROEN A , et al . ConvXGB: A new deep learning model for classification problems based on CNN and XGBoost [J ] . Nuclear Engineering and Technology , 2021 , 53 ( 2 ): 522 - 531 .

TANABE R , FUKUNAGA A . Success-history based parameter adaptation for differential evolution [C ] // 2013 IEEE Congress on Evolutionary Computation June 20 - 23 , 2013, Cancun, Mexico. IEEE , 2013: 71 - 78 .

VIKTORIN A , SENKERIK R , PLUHACEK M , et al . Distance based parameter adaptation for success-history based differential evolution [J ] . Swarm and Evolutionary Computation , 2019 , 50 : 100462 .

XU J , WANG X Y , GU Y J , et al . A data-based day-ahead scheduling optimization approach for regional integrated energy systems with varying operating conditions [J ] . Energy , 2023 , 283 : 128534 .

GUO S M , TSAI J S , YANG C C , et al . A self-optimization approach for L-SHADE incorporated with eigenvector-based crossover and successful-parent-selecting framework on CEC 2015 benchmark set [C ] // 2015 IEEE Congress on Evolutionary Computation (CEC) . May 25-28, 2015 , Sendai, Japan IEEE , 2015 : 1003 - 1010 .

徐婧，赵鹏程，袁国生，等 . 基于数据挖掘的汽轮机组冷端优化. 中国电机工程学报 [J ] , 2021 , 41 ( 2 ): 423 - 431 .

XU Jing , ZHAO Pengcheng , YUAN Guosheng , et al . Data-mining based operational optimization for cold-end subsystem of the steam turbine [J ] . Proceedings of the Chinese Society for Electrical Engineering , 2021 , 41 ( 2 ): 423 - 431 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

The "Six Firsts" in coal power integrated innovation in Changzhou, Jiangsu

Mix proportion optimization and performance of one-part multi-solid-waste geopolymer matrix under multi-factor coupling

Review on resource management of waste photovoltaic modules

Mechanism of solidifying sulfate saline soil using fly ash-based cementitious materials

Bi-level optimization of energy storage configuration for photovoltaic-storage-charging integrated stations under two-part tariff

Related Author

No data

Related Institution

No data

AI脑图

AI问答

⁰