CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework

As the greenhouse effect intensifies, China faces pressure to manage CO<sub>2</sub> emissions. Coal-fired power plants are a major source of CO<sub>2</sub> in China. Traditional CO<sub>2</sub> emission accounting methods of power plants are deficient in computatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Kezhi Tu, Yanfeng Wang, Xian Li, Xiangxi Wang, Zhenzhong Hu, Bo Luo, Liu Shi, Minghan Li, Guangqian Luo, Hong Yao
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/24/6449
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850241927552696320
author Kezhi Tu
Yanfeng Wang
Xian Li
Xiangxi Wang
Zhenzhong Hu
Bo Luo
Liu Shi
Minghan Li
Guangqian Luo
Hong Yao
author_facet Kezhi Tu
Yanfeng Wang
Xian Li
Xiangxi Wang
Zhenzhong Hu
Bo Luo
Liu Shi
Minghan Li
Guangqian Luo
Hong Yao
author_sort Kezhi Tu
collection DOAJ
description As the greenhouse effect intensifies, China faces pressure to manage CO<sub>2</sub> emissions. Coal-fired power plants are a major source of CO<sub>2</sub> in China. Traditional CO<sub>2</sub> emission accounting methods of power plants are deficient in computational efficiency and accuracy. To solve these problems, this study proposes a novel RF-RFE-DF-Optuna (random forest–recursive feature elimination–deep forest–Optuna) framework, enabling accurate CO<sub>2</sub> emission prediction for coal-fired power plants. The framework begins with RF-RFE for feature selection, identifying and extracting the most important features for CO<sub>2</sub> emissions from the power plant, reducing dimensionality from 46 to just 5 crucial features. Secondly, the study used the DF model to predict CO<sub>2</sub> emissions, combined with the Optuna framework, to enhance prediction accuracy further. The results illustrated the enhancements in model performance and showed a significant improvement with a 0.12706 increase in R<sup>2</sup> and reductions in MSE and MAE by 81.70% and 36.88%, respectively, compared to the best performance of the traditional model. This framework improves predictive accuracy and offers a computationally efficient real-time CO<sub>2</sub> emission monitoring solution in coal-fired power plants.
format Article
id doaj-art-eeeedacfa9084ca8b9cab9221901309f
institution OA Journals
issn 1996-1073
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-eeeedacfa9084ca8b9cab9221901309f2025-08-20T02:00:27ZengMDPI AGEnergies1996-10732024-12-011724644910.3390/en17246449CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna FrameworkKezhi Tu0Yanfeng Wang1Xian Li2Xiangxi Wang3Zhenzhong Hu4Bo Luo5Liu Shi6Minghan Li7Guangqian Luo8Hong Yao9State Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaGuoneng Yongfu Power Generation Co., Ltd., Guilin 541805, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Coal Combustion, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaAs the greenhouse effect intensifies, China faces pressure to manage CO<sub>2</sub> emissions. Coal-fired power plants are a major source of CO<sub>2</sub> in China. Traditional CO<sub>2</sub> emission accounting methods of power plants are deficient in computational efficiency and accuracy. To solve these problems, this study proposes a novel RF-RFE-DF-Optuna (random forest–recursive feature elimination–deep forest–Optuna) framework, enabling accurate CO<sub>2</sub> emission prediction for coal-fired power plants. The framework begins with RF-RFE for feature selection, identifying and extracting the most important features for CO<sub>2</sub> emissions from the power plant, reducing dimensionality from 46 to just 5 crucial features. Secondly, the study used the DF model to predict CO<sub>2</sub> emissions, combined with the Optuna framework, to enhance prediction accuracy further. The results illustrated the enhancements in model performance and showed a significant improvement with a 0.12706 increase in R<sup>2</sup> and reductions in MSE and MAE by 81.70% and 36.88%, respectively, compared to the best performance of the traditional model. This framework improves predictive accuracy and offers a computationally efficient real-time CO<sub>2</sub> emission monitoring solution in coal-fired power plants.https://www.mdpi.com/1996-1073/17/24/6449CO<sub>2</sub> emissioncoal-fired power plantdeep forestRFEOptuna
spellingShingle Kezhi Tu
Yanfeng Wang
Xian Li
Xiangxi Wang
Zhenzhong Hu
Bo Luo
Liu Shi
Minghan Li
Guangqian Luo
Hong Yao
CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
Energies
CO<sub>2</sub> emission
coal-fired power plant
deep forest
RFE
Optuna
title CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
title_full CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
title_fullStr CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
title_full_unstemmed CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
title_short CO<sub>2</sub> Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework
title_sort co sub 2 sub emission prediction for coal fired power plants by random forest recursive feature elimination deep forest optuna framework
topic CO<sub>2</sub> emission
coal-fired power plant
deep forest
RFE
Optuna
url https://www.mdpi.com/1996-1073/17/24/6449
work_keys_str_mv AT kezhitu cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT yanfengwang cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT xianli cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT xiangxiwang cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT zhenzhonghu cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT boluo cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT liushi cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT minghanli cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT guangqianluo cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework
AT hongyao cosub2subemissionpredictionforcoalfiredpowerplantsbyrandomforestrecursivefeatureeliminationdeepforestoptunaframework