Biogas Production Prediction Based on Feature Selection and Ensemble Learning
Source abstract
Abstract
The allocation of biogas between power generation and heat supply in traditional kitchen waste power generation system is unreasonable; for this reason, a biogas prediction method based on feature selection and heterogeneous model integration learning is proposed for biogas production predictions. Firstly, the working principle of the biogas generation system based on kitchen waste is analyzed, the relationship between system features and biogas production is mined, and the important features are extracted. Secondly, the prediction performance of different individual learner models is comprehensively analyzed, and the training set is divided to reduce the risk of overfitting by combining K-fold cross-validation. Finally, different primary learners and meta learners are selected according to the prediction error and diversity index, and different learners are fused to construct the stacking ensemble learning model with a two-layer structure. The experimental results show that the research method has a higher prediction accuracy in predicting biogas production, which provides supporting data for the economic planning of kitchen waste power generation systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Energy Efficiency and Management · Energy, Environment, and Transportation Policies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, Shenzhen 518118, China
School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, China
State Grid Zhuzhou Power Supply Company, State Grid Hunan Power Company, Zhuzhou 412011, China
Funding
National Natural Science Foundation of China · Stable Support Projects for Shenzhen Higher Education Institutions
References (25)
Show source-provided references
1. Thermo-economic analysis of biomass-fired organic Rankine cycle combined heat and power system
2. Research on low-carbon power planning with gas turbine units based on carbon transactions
3. Review of research on generative adversarial network and its application in new energy data quality
4. “Smart Grid Plus” research overview
5. Prediction models of the carbon content of fly ash in a biomass boiler based on improved BP neural networks
6. A short-term wind power forecast method via XGBoost hyper-parameters optimization10.3389/fenrg.2022.905155 ↗
7. Short-term load forecasting method based on CNN-LSTM hybrid neural network model
8. A prediction model of biomass three-components contents based on machine learning and thermogravimetric analysis
9. A D-stacking dual-fusion, spatio-temporal graph deep neural network based on a multi-integrated overlay for short-term wind-farm cluster power multi-step prediction10.1016/j.energy.2023.128289 ↗
10. Identification method of electricity charge recovery risk of specialized transformer user based on Stacking model fusion
11. Short-term bus load forecasting based on XGBoost and stacking model fusion
12. Potential reuse of kitchen food waste10.1016/j.jece.2016.11.026 ↗
13. Anaerobic digestion of kitchen waste: The effects of source, concentration, and temperature10.1016/j.bej.2018.04.004 ↗
14. Modelling of environmental benefit evaluation of energy transition to multi-energy complementary system10.1016/j.egypro.2019.01.705 ↗
15. Lautert, R.R., Brignol, W.D., Canha, L.N., Adeyanju, O.M., and Garcia, V.J. (2022). A flexible-reliable operation model of storage and distributed generation in a biogas power plant. Energies, 15.10.3390/en15093154 ↗
16. Data processing strategies in wind energy forecasting models and applications: A comprehensive review10.1016/j.apenergy.2019.04.188 ↗
17. A novel hybrid algorithm for feature selection based on whale optimization algorithm10.1109/ACCESS.2018.2879848 ↗
18. A novel approach to increase the efficiency of filter-based feature selection methods in high-dimensional datasets with strong correlation structure10.1109/ACCESS.2023.3325331 ↗
19. Short-term wind power prediction based on two-layer decomposition and BiTCN-BiLSTM-attention model10.1016/j.energy.2023.128762 ↗
20. Charging demand forecasting of electric vehicle based on empirical mode decomposition-fuzzy entropy and ensemble learning
21. Zhou, Z.H. (2012). Ensemble Methods: Foundations and Algorithms, CRC Press.10.1201/b12207 ↗
22. Load forecasting based on multi-model by stacking ensemble learning
23. Power losses prediction based on feature selection and stacking integrated learning
24. Electricity theft detection based on multiple different learner fusion by stacking ensemble learning
25. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗