Dual-stage ensemble approach using online knowledge distillation for forecasting carbon emissions in the electric power industry

Abd Elaziz, 2021, Advanced metaheuristic optimization techniques in applications of deep neural networks: a review, Neural Comput. Appl., 33, 14079, 10.1007/s00521-021-05960-5 Acheampong, 2019, Modelling carbon emission intensity: application of artificial neural network, J. Clean. Prod., 225, 833, 10.1016/j.jclepro.2019.03.352 Al-Nefaie, 2023, Predicting CO2 emissions from traffic vehicles for sustainable and smart environment using a deep learning model, Sustainability, 15, 7615, 10.3390/su15097615 Ang, 2016, Carbon emission intensity in electricity production: a global analysis, Energy Pol., 94, 56, 10.1016/j.enpol.2016.03.038 Cai, 2023, Forecasting hourly PM 2.5 concentrations based on decomposition-ensemble-reconstruction framework incorporating deep learning algorithms, Data Sci. Manag., 6, 46, 10.1016/j.dsm.2023.02.002 Chung, 2014 Cleveland, 1990, STL: a seasonal-trend decomposition, J. Off. Stat., 6, 3 Diebold, 2002, Comparing predictive accuracy, J. Bus. Econ. Stat., 20, 134, 10.1198/073500102753410444 Griggs, 2002, Climate change 2001: the scientific basis. Contribution of working group I to the third assessment report of the intergovernmental panel on climate change, Weather, 57, 267, 10.1256/004316502320517344 Gurriaran, 2023, Warming-induced increase in power demand and CO2 emissions in Qatar and the Middle East, J. Clean. Prod., 382 Hinton, 2015 Hochreiter, 1997, Long short-term memory, Neural Comput., 9, 1735, 10.1162/neco.1997.9.8.1735 Huan, 2018, Prediction of dissolved oxygen in aquaculture based on EEMD and LSSVM optimized by the Bayesian evidence framework, Comput. Electron. Agric., 150, 257, 10.1016/j.compag.2018.04.022 Huang, 2021, The prediction of carbon emission information in Yangtze River Economic Zone by deep learning, Land, 10, 1380, 10.3390/land10121380 Kaur, 2023, Development of a mathematical model to forecast black carbon concentration using ARIMA and soft computing, Arabian J. Geosci., 16, 258, 10.1007/s12517-023-11321-4 Kong, 2022, A daily carbon emission prediction model combining two-stage feature selection and optimized extreme learning machine, Environ. Sci. Pollut. Res., 29, 87983, 10.1007/s11356-022-21277-9 Kong, 2022, A novel short-term carbon emission prediction model based on secondary decomposition method and long short-term memory network, Environ. Sci. Pollut. Res., 29, 64983, 10.1007/s11356-022-20393-w LeCun, 2015, Deep learning, Nature, 521, 436, 10.1038/nature14539 Li, 2021, A new secondary decomposition ensemble learning approach for carbon price forecasting, Knowl. Base Syst., 214 Luo, 2023, Simulation of tourism carbon emissions based on system dynamics model, Phys. Chem. Earth, 129 Luo, 2021, A hybrid model for financial time-series forecasting based on mixed methodologies, Expet Syst., 38 Modise, 2021, Energy and carbon emission efficiency prediction: applications in future transport manufacturing, Energies, 14, 8466, 10.3390/en14248466 Ndez, 2018, A meta extreme learning machine method for forecasting financial time series, Appl. Intell., 49, 532 Ren, 2021, Carbon emission forecasting and scenario analysis in Guangdong Province based on optimized Fast Learning Network, J. Clean. Prod., 317 Roberts, 2018, Consequences of selecting technology pathways on cumulative carbon dioxide emissions for the United Kingdom, Appl. Energy, 228, 409, 10.1016/j.apenergy.2018.06.078 Romero, 2014 Saputra, 2019, Distilling knowledge from a deep pose regressor network, 263 Sim, 2016, The effect of new carbon emission reduction targets on an apartment building in South Korea, Energy Build., 127, 637, 10.1016/j.enbuild.2016.06.032 Sun, 2021, Short-term prediction of carbon emissions based on the EEMD-PSOBP model, Environ. Sci. Pollut. Res., 28, 56580, 10.1007/s11356-021-14591-1 Sun, 2016, Research on CO2 emissions from China’s electric power industry based on system dynamics model, Int. J. Ind. Syst. Eng., 22, 423 Taieb, 2012, A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition, Expert Syst. Appl., 39, 7067, 10.1016/j.eswa.2012.01.039 Wei, 2018, Forecasting CO2 emissions in Hebei, China, through moth-flame optimization based on the random forest and extreme learning machine, Environ. Sci. Pollut. Res., 25, 28985, 10.1007/s11356-018-2738-z Xiao, 2016, Can China achieve its 2020 carbon intensity target? A scenario analysis based on system dynamics approach, Ecol. Indicat., 71, 99, 10.1016/j.ecolind.2016.06.060 Xu, 2022, Contrastive adversarial knowledge distillation for deep model compression in time-series regression tasks, Neurocomputing, 485, 242, 10.1016/j.neucom.2021.04.139 Yao, 2023, CarbonVCA: a cadastral parcel-scale carbon emission forecasting framework for peak carbon emissions, Cities, 138 Yim, 2017, A gift from knowledge distillation: fast optimization, network minimization and transfer learning, 4133 Yu, 2021, An effective rolling decomposition-ensemble model for gasoline consumption forecasting, Energy, 222 Zhang, 2019, Digital twin-driven carbon emission prediction and low-carbon control of intelligent manufacturing job-shop, Proc. CIRP, 83, 624, 10.1016/j.procir.2019.04.095 Zhang, 2021, A new decomposition ensemble approach for tourism demand forecasting: evidence from major source countries in Asia-Pacific region, Int. J. Tourism Res., 23, 832, 10.1002/jtr.2445 Zhang, 2018, Deep mutual learning, 4320