华南理工大学学报（自然科学版）2025，Vol.53Issue(11)：52-61,10.DOI:10.12141/j.issn.1000-565X.250086
基于多源数据及机器学习的电厂CO2排放计量与预测
CO2 Emission Measurement and Forecasting for Power Plants Based on Multi-Source Data and Machine Learning
摘要
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 fac-tor 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(xc),is proposed by applying trained models to other units.Then,xc is used to assess the generalization capability of ma-chine learning algorithms for further model screening.The results reveal that AdaBoost exhibits superior perfor-mance in prediction accuracy and stability,along with higher generalization capability and robustness.The dy-namic 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 predic-tion 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.关键词
二氧化碳/碳计量/碳预测/排放因子法/机器学习Key words
carbon dioxide/carbon measurement/carbon forecasting/emission factor method/machine learning分类
能源科技引用本文复制引用
孙尊强,田一淳,苏楠,郑成航,张振,杨宏旻,高翔..基于多源数据及机器学习的电厂CO2排放计量与预测[J].华南理工大学学报（自然科学版）,2025,53(11):52-61,10.基金项目
国家重点研发计划项目(2022YFC3701504) （2022YFC3701504）
国家能源集团科技项目(GJNY-23-82) Supported by the National Key Research&Development Program of China(2022YFC3701504) （GJNY-23-82）
