基于BayesianOpt-XGBoost的煤电机组碳排放因子预测

Abstract
Figure/Table
References
Related Citation (8)

Download: PDF (2284 KB) HTML (0 KB)
Export: BibTeX | EndNote (RIS)

Abstract A Bayesian-Opt-XGBoost model was established on the basis of the features of power generation units and coals, in which the parameters were optimized with Bayesian. The prediction of the carbon emission factors of power and heat generation of coal-fired power plants had coefficients of (R²) of 0.91 and 0.87, respectively, the corresponding mean absolute errors are 2.51% and 2.91%. Normalization methods were used to get rid of the dependence on coal's features, the corresponding R² values were 0.79 and 0.77 respectively, and the mean absolute errors were 3.94% and 2.75%, the accuracy can still be acceptable. With the model, the carbon emission factors of coal power units in different provinces of China were estimated and compared with the published data, which proved the valid of this model. The analysis of the above estimated results shown that the carbon emission intensity of coal-fired power industry can be reduced by reforming the existing low-capacity units and building large capacity and high parameters units for newly plants.

Key words： carbon accounting coal-fired power units carbon emission factors prediction Bayesian optimization XGBoost feature normalization

Received: 05 May 2023

PACS:

X24

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHAO Jing-hao
	WANG Na-na
	JIANG Jia-ming
	TIAN Ya-jun

Cite this article:

ZHAO Jing-hao,WANG Na-na,JIANG Jia-ming等. Prediction of coal-fired power units carbon emission factor based on BayesianOpt-XGBoost[J]. CHINA ENVIRONMENTAL SCIENCECE, 2024, 44(1): 417-426.

URL:

http://www.zghjkx.com.cn/EN/ OR http://www.zghjkx.com.cn/EN/Y2024/V44/I1/417

[1]	Stechemesser K, Guenther E.Carbon accounting:A systematic literature review [J].Journal of Cleaner Production, 2012,36:17-38.
[2]	闫丰,王洋,杜哲,等.基于IPCC排放因子法估算碳足迹的京津冀生态补偿量化[J].农业工程学报, 2018,34(4):15-20.Yan F, Wang Y, Du Z, et al.Quantification of ecological compensation in Bejing-Tianjin-Hebei based on carbon footprint calculated using emission factor method proposed by IPCC [J].Transactions of the Chinese Society of Agricultural Engineering 2018,34(4):15-20.
[3]	Liu Z, Guo D B, Wei W, et al.Reduced carbon emission estimates from fossil fuel combustion and cement production in China [J].Nature, 2015,524(7565):335-338.
[4]	Li J J, Zhang Y L, Tian Y J, et al.Reduction of carbon emissions from China's coal-fired power industry:Insights from the province-level data [J].Journal of Cleaner Production, 2020,242:118518.
[5]	刘淳森,曲建升,葛钰洁,等.基于LSTM模型的中国交通运输业碳排放预测[J].中国环境科学, 2023,43(5):2574-2582.Liu C S, Qu J S, Ge Y J, et al.LSTM model-based prediction of carbon emissions from China's transportation sector [J].China Environmental Science 2023,43(5):2574-2582.
[6]	Umit A.Forecasting of transportation-related energy demand and CO2 emissions in Turkey with different machine learning algorithms [J].Sustainable Production and Consumption, 2022,29:141-157.
[7]	余文梦,张婷婷,沈大军.基于随机森林模型的我国县域碳排放强度格局与影响因素演进分析[J].中国环境科学, 2022,42(6):2788-2798.Yu W M, Zhang T T, Shen D J County-levelspatial patter and influencing factors evolution of carbon emission intensity in China:A random forest model analysis [J].China Environmental Science, 2022, 42(6):2788-2798.
[8]	Sun W, Wang Y W, Zhang C C.Forecasting CO2 emissions in Hebei, China, through moth-flame optimization based on the random forest and extreme learning machine [J].Environmental Science and Pollution Research, 2018,25(29):28985-28997.
[9]	Chen T, Guestrin C.XGBoost:A Scalable Tree Boosting System [EB/OL].https://dl.acm.org/doi/pdf/10.1145/2939672.2939785.
[10]	康俊锋,谭建林,方雷,等.XGBoost-LSTM变权组合模型支持下短期PM2.5浓度预测——以上海为例[J].中国环境科学, 2021,41(9):4016-4025.Kang J F, Tan J L, Fang L, et al.Short-term PM2.5 concentration prediction based on XGBoost and LSTM variable weight combination model:a case study of Shanghai [J].China Environmental Science 2021,41(9):4016-4025.
[11]	Chen Y F, Li F, Zhou S Q, et al.Bayesian optimization based random forest and extreme gradient boosting for the pavement density prediction in GPR detection [J].Construction and Building Materials, 2023,387:131564.
[12]	中国电力企业联合会.中国电力行业年度发展报告2022[R].北京:中国电力企业联合会, 2022.China Electricity Council.Annual development report of China's power industry 2022[R].Beijing:China Electricity Council, 2022.
[13]	中华人民共和国国家能源局.2022年全国电力工业统计数据[R].北京:中华人民共和国国家能源局, 2023.National Energy Administration.Electric power industry statistical data of China 2022[R].Beijing:National Energy Administration, 2023.
[14]	王小龙,王强,王小峰,等.燃煤电厂关键排放因子对碳排放量影响研究[J].山东化工, 2019,48(23):239-243.Wang X L, Wang Q, Wang X F, et al.A study on the lnfluence of key emission factors of coal-fired power plant on carbon emission [J].Shandong Chemical Industry 2019,48(23):239-243.
[15]	蒋春来,宋晓晖,钟悦之,等.2010~2015年中国燃煤电厂NOx排放特征[J].中国环境科学, 2018,38(8):2903-2910.Jiang C L, Song X H, Zhong Y Z, et al.Characteristics of NOx emissions from coa-fired power plants in China from 2010 to 2015[J].China Environmental Science 2018,38(8):2903-2910.
[16]	马学礼,王笑飞,孙希进,等.燃煤发电机组碳排放强度影响因素研究[J].热力发电, 2022,51(1):190-195.Ma X L, Wang X F, Sun X J, et al.Influence factors of carbon emission intensity of coal-fired power units Thermal Power Generation 2022,51(1):190-195.
[17]	郑剑平.我国煤炭的单位热值碳含量研究[J].煤炭加工与综合利用, 2022,(1):58-62.Zheng J P.Study on carbon content per unit calorific value of coals in China [J].Coal Processing & Comprehensive Utilization, 2022,(1):58-62.
[18]	甘萍香.褐煤、烟煤、无烟煤及其混煤的燃烧特性研究[D].昆明:昆明理工大学, 2013.Gan P X.Study on combustion characteristics of blended coals which formed by lignite, bituminous coal, anthracite [D].KunMing:Kunming University of Science and Technology, 2013.
[19]	龚丽华,张国金,王应高,等.火电厂入厂煤与入炉煤热值差大的原因分析及对策[J].中国电力, 2009,42(8):32-34.Gong L H, Zhang G J, Wang Y G, et al.Reasons analysis and countermeasure of caloric value differences between coal as received and coal as fired in thermal power plant [J].Electric Power, 2009, 42(8):32-34.
[20]	Friedman J H.Greedy function approximation:A gradient boosting machine [J].The Annals of Statistics, 2001,29(5).
[21]	Frazier P.A Tutorial on Bayesian Optimization [EB/OL].https://arxiv.org/abs/1807.02811.
[22]	Assessing the impact of clean air action on air quality trends in Beijing using a machine learning technique [J].Atmospheric Chemistry and Physics, 2019,19(17):11303-11314.
[23]	中华人民共和国国家发展和改革委员会.中国发电企业温室气体排放核算方法与报告指南(试行) [R].北京:中华人民共和国国家发展和改革委员会, 2013.National Development and Reform Commission.Guideline of the greenhouse gas emissions accounting and reporting for the power generation enterprises of China (Trial) [R].Beijing:National Development and Reform Commission, 2013.
[24]	Nisbet A.Open topo data [EB/OL].https://www.opentopodata.org/.
[25]	Shan L Q, Liu Y C, Tang M, et al.CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction [J].Journal of Petroleum Science and Engineering, 2021,205:108838.
[26]	中国电力企业联合会.中国电力统计年鉴2020[M].北京:中国统计出版社, 2020:30-31.China Electricity Council.China electric power yearbook 2022[M].Beijing:China Statistics Press, 2020:30-31.
[27]	中国电力企业联合会.二〇一八年电力工业统计资料汇编[M].北京:中国电力企业联合会, 2019 China Electricity Council.Electric power industry statistical compilation of China 2018[M].Beijing:Electricity Council China, 2019