CO2 Emission Measurement and Forecasting for Power Plants Based on Multi-Source Data and Machine Learning

doi:10.12141/j.issn.1000-565X.250086

Abstract

Abstract:

Accurate CO₂ emission measurement and dynamic forecasting are crucial for achieving China’s “dual carbon” goals (carbon peak and carbon neutrality). This study integrates the emission factor method, CO₂-CEMS and machine learning technologies to propose a CO₂ emission measurement and forecasting method based on multi-source data fusion, for the purpose of providing an efficient and accurate carbon emission monitoring tool for coal-fired power plants. In the investigation, by comparing the CO₂ emission calculation results obtained by different methods, the performances of different machine learning algorithms are evaluated, and a dynamic forecasting model based on multi-source data is developed. Experimental results in Units 1 and 3 of a power plant of Guoneng Group Co., Ltd. in Hebei, China show that the relative deviations of CO₂ emission calculations between the emission factor method and CO₂-CEMS for the two units are 1.63% and -1.27%, respectively, meaning that the two methods are of good cross-validation. By comparing the performance of various machine learning models (such as XGBoost, LightGBM, and AdaBoost), beyond the two conventional evaluation metrics, namely the determination coefficient (R²) and the mean absolute percentage error (MAPE), a new selection criterion, namely the mean deviation (x_c), is proposed by applying trained models to other units. Then, x_c is used to assess the generalization capability of machine learning algorithms for further model screening. The results reveal that AdaBoost exhibits superior performance in prediction accuracy and stability, along with higher generalization capability and robustness. The dynamic CO₂ emission forecasting using the optimized AdaBoost algorithm achieves R² values greater than 0.99 on both the training and the testing sets, with a MAPE below 2%, which indicates that the algorithm is of high prediction accuracy, stability, generalization ability and robustness. The proposed multi-source data fusion method not only effectively overcomes the limitations of traditional methods in dynamic scenarios but also enables precise hourly CO₂ emission forecasting based on real-time data.

Key words: carbon dioxide, carbon measurement, carbon forecasting, emission factor method, machine learning

CLC Number:

TK39

SUN Zunqiang, TIAN Yichun, SU Nan, ZHENG Chenghang, ZHANG Zhen, YANG Hongmin, GAO Xiang. CO₂ Emission Measurement and Forecasting for Power Plants Based on Multi-Source Data and Machine Learning[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(11): 52-61.

Figures/Tables 8

Table 1

Table 2

Fig.1

Fig.2

Table 3

Fig.3

Fig.4

Fig.5

References 22

[1]	D-H OH， DAT V N， LEE J-C，et al ．Prediction of CO₂ capture capability of 0.5 MW MEA demo plant using three different deep learning pipelines［J］．Fuel，2022，315：123229．
[2]	姚顺春，李龙千，卢志民，等．机器学习驱动锅炉燃烧优化技术的现状与展望［J］．洁净煤技术，2024，30（2）：228-243．
	YAO Shunchun， LI Longqian， LU Zhimin，et al ．Current situation and prospect of machine learning-driven boiler combustion optimization technology［J］．Clean Coal Technology，2024，30（2）：228-243．
[3]	陈公达，程国辉，蔡汝金，等．烟气碳排放监测数据补缺方法适用性［J］．洁净煤技术，2024，30（8）：32-41．
	CHEN Gongda， CHENG Guohui， CAI Rujin，et al ．Applicability of data gaps imputation methods for monitoring flue gas carbon emissions［J］．Clean Coal Techno-logy，2024，30（8）：32-41．
[4]	李振山，李维成，刘海洋，等．中国化学链燃烧技术研发进展与展望［J］．中国电机工程学报，2024，44（18）：7200-7220．
	LI Zhenshan， LI Weicheng， LIU Haiyang，et al ．Development and prospect of chemical looping combustion technology in China［J］．Proceedings of the CSEE，2024，44（18）：7200-7220．
[5]	王萍萍，赵永椿，张军营，等．双碳目标下燃煤电厂碳计量方法研究进展［J］．洁净煤技术，2022，28（10）：170-183．
	WANG Pingping， ZHAO Yongchun， ZHANG Junying，et al ．Research progress on carbon measurement methods of coal-fired power plants under the background of carbon neutrality［J］．Clean Coal Technology，2022，28（10）：170-183．
[6]	郭军军，张泰，李鹏飞，等．中国煤粉富氧燃烧的工业示范进展及展望［J］．中国电机工程学报，2021，41（4）：1197-1208．
	GUO Junjun， ZHANG Tai， LI Pengfei，et al ．Industrial demonstration progress and trend in pulverized coal oxy-fuel combustion in China［J］．Proceedings of the CSEE，2021，41（4）：1197-1208．
[7]	姚顺春，刘泽明，卢志民，等．软测量技术赋能燃煤电厂碳排放计量的研究进展［J］．洁净煤技术，2024，30（8）：18-31．
	YAO Shunchun， LIU Zeming， LU Zhimin，et al ．Research progress of soft measurement technology optimizing carbon emission measurement of coal-fired power plants［J］．Clean Coal Technology，2024，30（8）：18-31．
[8]	李惠，黄修行，周于惠．“双碳”目标视角下燃煤电厂碳计量方法的研究［J］．资源节约与环保，2024（6）：100-103．
	LI Hui， HUANG Xiuxing， ZHOU Yuhui ．Research on carbon measurement methods of coal-fired ower plants from the perspective of the “Dual Carbon” goals［J］．Resource Conservation and Environmental Protection，2024（6）：100-103．
[9]	曾瑞新，胡松伯，倪忠晓，等．燃煤电厂碳排放典型计算及分析［J］．化工设计通讯，2023，49（3）：167-169．
	ZENG Rui-xin， HU Song-bo， NI Zhong-xiao，et al ．Typical calculation and analysis of carbon emissions from coal-fired power plants［J］．Chemical Engineering Design Communications，2023，49（3）：167-169．
[10]	宋明光，李小江，孙友源，等．基于在线监测法的火电机组碳排放分析［J］．洁净煤技术，2024，30（S1）：464-73．
	SONG Mingguang， LI Xiaojiang， SUN Youyuan，et al ．Analysis of carbon emission for thermal power units based on online monitoring method［J］．Clean Coal Technology，2024，30（S1）：464-473．
[11]	包放．燃煤电厂碳排放核算技术体系研究与应用［J］．能源与节能，2023（9）：94-97．
	BAO Fang ．Research and application of carbon emi-ssion accounting technology system for coal-fired power plants［J］．Energy and Energy Conservation，2023（9）：94-97．
[12]	陈齐，许明海，沈赛燕，等．基于残差双向长短期记忆效应网络模型的电力企业碳排放预测［J］．环境污染与防治，2024，46（5）：689-93，720．
	CHEN Qi， XU Minghai， SHEN Saiyan，et al ．Carbon emission prediction for power companies based on ResNet-BiLSTM model［J］．Environmental Pollution Control，46（5）：689-93，720．
[13]	LEERBECK K， BACHER P， JUNKER RG，et al ．Short-term forecasting of CO₂ emission intensity in power grids by machine learning［J］．Applied Energy，2020，277：115527．
[14]	WU W， LIN Y-T， LIAO P-H，et al ．Prediction of CO-NO _x emissions from a natural gas power plant using proper machine learning models［J］．Energy Techno-logy，2023，11（7）：2300041．
[15]	王妍艳，陆骏超，赵冬建．燃煤电厂二氧化碳排放的核算与管理分析［J］．电力与能源，2024，45（1）：102-106．
	WANG Yanyan， LU Junchao， ZHAO Dongjian ．Accounting and management analysis of CO₂ emissions from coal-fired power plants［J］．Electricity and Energy，2024，45（1）：102-106．
[16]	李朋，周卫青，白孝轩，等．燃煤电厂碳排放绩效核算及影响分析［J］．洁净煤技术，2024，30（8）：66-74．
	LI Peng， ZHOU Weiqing， BAI Xiaoxuan，et al ．Carbon emission performance calculation and impact analysis of coal-fired power plants［J］．Clean Coal Techno-logy，2024，30（8）：66-74．
[17]	王正阳．燃煤电厂的二氧化碳排放计算与影响分析［J］．节能与环保，2022（5）：39-40．
	WANG Zheng-yang ．Calculation and Impact Analysis of carbon dioxide emission from coal-fired power plants［J］．Energy Conservation and Environmental Protection，2022（5）：39-40．
[18]	吴杏平，康重庆，袁启恒．我国碳排放影响因素及电力碳排放核算方法研究综述［J］．中国电机工程学报，2024，44（S1）：1-18．
	WU Xingping， KANG Chongqing， YUAN Qiheng ．A review of the impact factors of carbon emissions and the accounting methods for electricity carbon emissions in China［J］．Proceedings of the CSEE，2024，44（S1）：1-18．
[19]	王明，周志兴，封明敏，等．火电机组实测法CO₂排放监测模型及准确性验证［J］．煤化工，2022，50（2）：18-21，33．
	WANG Ming， ZHOU Zhixing， FENG Mingmin，et al． Online CO 2 emission monitoring system for coal-fired power plant based on direct measurement and its accuracy verification［J］．Coal Chemical Industry，2022，50（2）：18-21，33．
[20]	MA Y， HE P-J， LÜ F，et al ．Machine learning-based prediction of the CO₂ concentration in the flue gas and carbon emissions from a waste incineration plant［J］．ACS ES&T Engineering，2024，4（3）：737-747．
[21]	WEN L， CAO Y ．Influencing factors analysis and forecasting of residential energy-related CO₂ emissions utilizing optimized support vector machine［J］．Journal of Cleaner Production，2020，250：119492．
[22]	YUAN Z， MENG L， GU X，et al ．Prediction of NO _x emissions for coal-fired power plants with stacked-generalization ensemble method［J］．Fuel，2021，289：119748．

日期	日耗煤量			CO₂日排放量
日期	1#	3#	4#	1#	3#	4#
2024-01-01	4 967.54	5 201.15	5 181.70	9 225.26	9 659.10	9 622.98
2024-01-02	5 215.73	5 316.59	5 432.57	9 686.17	9 873.48	10 088.87
︙	︙	︙	︙	︙	︙	︙
2024-03-30	4 118.96	4 855.57	1 852.01	7 757.38	9 281.70	3 560.14
2024-03-31	3 651.09	4 166.70	4 316.76	6 876.23	7 964.89	8 298.15
平均值	4 190.56	4 895.67	4 577.81	7 871.14	9 239.40	9 434.42
最大值	5 301.16	6 303.35	6 482.32	9 900.48	11 706.00	13 266.07
最小值	317.18	3 764.04	12.11	598.99	7 140.53	19.27

时间（2024-01-01）	CO₂体积分数/%	CO₂标干浓度/（mg·m^-3）	CO₂修正浓度/（mg·m^-3）	修正后CO₂排放量/（t·h^-1）	标干浓度/（mg·m^-3）			烟气标干流量/ （m³·h^-1）	烟气修正流量/ （m³·h^-1）	干基O₂百分比/%	烟温/℃	含湿量/%	负荷（蒸气）/%	CO₂日排放量/t
时间（2024-01-01）	CO₂体积分数/%	CO₂标干浓度/（mg·m^-3）	CO₂修正浓度/（mg·m^-3）	修正后CO₂排放量/（t·h^-1）	SO₂	NO _x	颗粒物	烟气标干流量/ （m³·h^-1）	烟气修正流量/ （m³·h^-1）	干基O₂百分比/%	烟温/℃	含湿量/%	负荷（蒸气）/%	CO₂日排放量/t
00：00—01：00	14.80	290 809.39	215 040.59	465.51	10.23	20.84	2.28	1 717 939.50	2 164 746.99	4.60	51.29	13.86	85.70	9 671.20
01：00—02：00	14.09	276 782.41	205 892.88	387.91	9.75	21.81	2.72	1 504 103.50	1 884 022.95	5.35	50.78	13.36	69.70
02：00—03：00	13.75	270 143.71	202 666.64	370.50	9.44	22.13	2.31	1 471 936.50	1 828 154.83	5.77	50.00	12.67	64.67
03：00—04：00	13.69	268 833.16	202 530.89	362.95	13.85	22.45	2.19	1 448 955.63	1 792 082.32	5.84	49.60	12.34	62.98
04：00—05：00	13.01	255 514.08	193 549.90	315.98	12.16	23.24	2.25	1 327 179.38	1 632 536.25	6.57	49.05	11.92	54.47

算法	R²		MAPE/%
算法	1#机组	3#机组	1#机组	3#机组
多元线性回归	0.994 35	0.994 29	1.17	1.25
随机森林	0.991 37	0.993 85	1.38	1.29
决策树	0.986 14	0.989 48	1.67	1.65
LightGBM	0.994 28	0.994 36	1.14	1.26
AdaBoost	0.986 13	0.992 12	1.85	1.60
XGboost	0.995 43	0.994 86	1.03	1.21
岭回归	0.994 37	0.994 30	1.17	1.25
MLPRegressor	-24.350 00	-18.320 00	93.78	93.45
SVR	0.002 00	-0.006 00	15.55	19.94

CO₂ Emission Measurement and Forecasting for Power Plants Based on Multi-Source Data and Machine Learning

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 22

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	WEN Huiying, HUANG Kunhuo, CHEN Zhe, ZHAO Sheng, HU Yuqing, HUANG Junda. An Investigation into Expressway Merging Behavior and Safety Based on ExiD Data [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(8): 50-60.
[2]	WEN Huiying, MA Zhaoliang, ZHAO Sheng, WU Liming, HUANG Kunhuo. Analysis of Factors Affecting Truck Accidents on Mountainous Freeways [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(7): 93-103.
[3]	LIU Wenshuo, ZHONG Mingfeng, ZHOU Bo, LÜ Fangzhou. Research on Temperature Model of Steel Box Girder of High-Speed Railway Cable-Stayed Bridge Based on Machine Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(6): 25-33.
[4]	GONG Zhongwen, XIONG Ergang, WANG Wenxiang, et al. Shear Strength Calculation of RC Beams Without Shear Reinforcement Based on Crack Sliding Model [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(5): 114-126.
[5]	ZHAO Jiandong, XU Huiling, LÜ Xing, et al. Recognition Model of Highway Toll Evasion Behavior Considering Cost-Sensitivity [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(5): 10-19.
[6]	YAO Shunchun, ZHI Jiaqi, FU Jinbei, et al. Research Progress of Online Carbon Emission Monitoring Technology for Thermal Power Enterprises [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(6): 97-108.
[7]	ZHOU Chuhao, LIN Peiqun, YAN Mingyue. Traffic Data Imputation Based on Self-Supervised Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(4): 101-114.
[8]	DONG Ping, WEI Shuyang, LIU Mingbo. Scheduling Strategies for Electric Vehicle Participation in Electricity Markets Under Multi-Network Collaboration [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(12): 83-94.
[9]	WANG Xiaofei, LI Siyu, CHEN Mi, et al. Influence of the Combination Equilibrium of Horizontal and Crest Vertical Curves on Highway Safety [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(7): 76-84.
[10]	SONG Jian, WANG Wenlong, LI Dong, et al. Injection Molding Part Size Prediction Method Based on Stacking Ensemble Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(6): 19-26.
[11]	XIA Shaojun, JIN Qinglong, WU Zhixiang. Exergy Efficiency Analyses and Optimization of Regenerative S-CO₂Brayton Cycle [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(2): 111-120.
[12]	LIN Peiqun XIA Yu ZHOU Chuhao. Freeway Travel Time Prediction Based on Spatial and Temporal Characteristics of Road Networks [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(8): 1-11.
[13]	JIA Ruo, DAI Shenghong, HUANG Ni, et al. Literature Review on Traffic Congestion Identification Methods [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(4): 124-139.
[14]	ZHAO Jing, WANG Xuancang, FAN Zhenyang, et al. Evaluation on Performance of Asphalt Pavement Based on Support Vector Machine [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(9): 116-123.
[15]	ZHANG Ziye, LI Mingchang, LIANG Lingrui, et al. Improved Transfer Learning Algorithm Based on Cross-domain in Recommendation System [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(11): 99-106.