Influencing factors analysis and forecasting of residential energy-related CO2 emissions utilizing optimized support vector machine

Abstract With the economy development and rapid urbanization, the residential usage of energy has been increasing in China, leading to more CO2 emissions in resident sector. To predict the trend of residential energy-related CO2 emissions accurately, it is significant to analyze the influential factors. In this paper, 18 preliminary indicators are identified by grey relational analysis to prove their correlation with CO2 emissions firstly. To reduce the redundancy of data, 4 main components are extracted by principal component analysis as predicting input data of support vector machine (SVM). By adding chaotic mutation and nonlinear weight index, the improved chicken swarm optimization (ICSO) algorithm is proposed to optimize the parameters of SVM, hereafter referred as ICSO-SVM. Finally, the new hybrid model is applied to predict residential energy-related CO2 emissions in Shanghai, China. The simulation results in the forecasting accuracy demonstrate that the ICSO-SVM model outperforms the compared original chicken swarm optimization model (CSO-SVM), particle swarm optimization model (PSO-SVM), genetic algorithm optimization model (GA-SVM) and basic SVM. The rigorous influencing factors analysis and the outstanding performance in predicting CO2 emissions of ICSO-SVM model can offer relevant scholars and policy makers more breakthrough points of residential CO2 emissions abatement.

[1]  Yi-Ming Wei,et al.  Residential energy-related carbon emissions in urban and rural China during 1996–2012: From the perspective of five end-use activities , 2015 .

[2]  Shenggang Ren,et al.  The effects of urbanization, consumption ratio and consumption structure on residential indirect CO2 emissions in China: A regional comparative analysis , 2015 .

[3]  Raymond R. Tan,et al.  Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm , 2020, Journal of Cleaner Production.

[4]  João F.D. Rodrigues,et al.  Driving forces of household carbon emissions in China: A spatial decomposition analysis , 2019, Journal of Cleaner Production.

[5]  Liyin Shen,et al.  What drives the carbon emission in the Chinese cities?—A case of pilot low carbon city of Beijing , 2018 .

[6]  Xilong Yao,et al.  Can urbanization process and carbon emission abatement be harmonious? New evidence from China , 2018, Environmental Impact Assessment Review.

[7]  Liyin Shen,et al.  Decoupling China's economic growth from carbon emissions: Empirical studies from 30 Chinese provinces (2001-2015). , 2019, The Science of the total environment.

[8]  Yue‐Jun Zhang,et al.  The indirect energy consumption and CO2 emission caused by household consumption in China: an analysis based on the input–output method , 2017 .

[9]  Arthur P.J. Mol,et al.  Energy consumption practices of rural households in north China: Basic characteristics and potential for low carbon development , 2013 .

[10]  Tomohiko Ihara,et al.  Estimating residential CO2 emissions based on daily activities and consideration of methods to reduce emissions , 2016 .

[11]  Xiaoling Zhang,et al.  A novel method for carbon dioxide emission forecasting based on improved Gaussian processes regression , 2018 .

[12]  Takako Wakiyama,et al.  Scenario analysis of energy saving and CO2 emissions reduction potentials to ratchet up Japanese mitigation target in 2030 in the residential sector , 2017 .

[13]  Boqiang Lin,et al.  Investigating the differences in CO2 emissions in the transport sector across Chinese provinces: Evidence from a quantile regression model , 2018 .

[14]  Lixin Miao,et al.  Quantification and driving force analysis of provincial-level carbon emissions in China , 2017 .

[15]  Huiru Zhao,et al.  Forecasting Energy-Related CO 2 Emissions Employing a Novel SSA-LSSVM Model: Considering Structural Factors in China , 2018 .

[16]  Yacine Rezgui,et al.  Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees , 2018, Journal of Cleaner Production.

[17]  Lu Miao.  Examining the impact factors of urban residential energy consumption and CO2 emissions in China – Evidence from city-level data , 2017 .

[18]  Viktor Pocajt,et al.  Forecasting GHG emissions using an optimized artificial neural network model based on correlation and principal component analysis , 2014 .

[19]  Mohammadamin Azimi,et al.  A hybrid algorithm for carbon dioxide emissions forecasting based on improved lion swarm optimizer , 2020 .

[20]  Wei Sun,et al.  Daily PM2.5 concentration prediction based on principal component analysis and LSSVM optimized by cuckoo search algorithm. , 2017, Journal of environmental management.

[21]  Maria Jesus Herrerias,et al.  Residential energy consumption: A convergence analysis across Chinese regions , 2017 .

[22]  Mingqiang Huang,et al.  Factors influencing CO2 emissions in China based on grey relational analysis , 2016 .

[23]  Edson D. Leonel,et al.  Route to chaos and some properties in the boundary crisis of a generalized logistic mapping , 2017 .

[24]  Xin Meng,et al.  Income inequality and carbon dioxide emissions: The case of Chinese urban households , 2012 .

[25]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[26]  Wenling Liu,et al.  Inequality of household carbon emissions and its influencing factors: Case study of urban China , 2017 .

[27]  Liyan Han,et al.  Applying quantile regression and Shapley decomposition to analyzing the determinants of household embedded carbon emissions: evidence from urban China , 2015 .

[28]  Xuemei Li,et al.  Forecasting Chinese CO 2 emissions from fuel combustion using a novel grey multivariable model , 2017 .

[29]  Yu Liu,et al.  A New Bio-inspired Algorithm: Chicken Swarm Optimization , 2014, ICSI.

[30]  Jinyan Zhan,et al.  Structural decomposition analysis of carbon emissions from residential consumption in the Beijing-Tianjin-Hebei region, China , 2019, Journal of Cleaner Production.

[31]  Reza Shirmohammadi,et al.  Forecasting of CO2 emissions in Iran based on time series and regression analysis , 2019, Energy Reports.

[32]  Shuo Wang,et al.  Exploring potential pathways towards fossil energy-related GHG emission peak prior to 2030 for China: An integrated input-output simulation model , 2018 .

[33]  Wei Sun,et al.  Factor analysis and forecasting of CO2 emissions in Hebei, using extreme learning machine based on particle swarm optimization , 2017 .

[34]  Wei Sun,et al.  Using a back propagation neural network based on improved particle swarm optimization to study the influential factors of carbon dioxide emissions in Hebei Province, China , 2016 .

[35]  Jun Li,et al.  The Impact of Social Awareness and Lifestyles on Household Carbon Emissions in China , 2019, Ecological Economics.

[36]  Martin Skitmore,et al.  Household carbon emission research: An analytical review of measurement, influencing factors and mitigation prospects , 2015 .

[37]  Tao Zhao,et al.  Panel estimation for the impacts of residential characteristic factors on CO2 emissions from residential sector in China , 2018, Atmospheric Pollution Research.

[38]  Boqiang Lin,et al.  Determinants of industrial carbon dioxide emissions growth in Shanghai: A quantile analysis , 2019, Journal of Cleaner Production.

[39]  Muhd Zaimi Abd Majid,et al.  A global review of energy consumption, CO2 emissions and policy in the residential sector (with an overview of the top ten CO2 emitting countries) , 2015 .

[40]  Jinying Li,et al.  Combining a Genetic Algorithm and Support Vector Machine to Study the Factors Influencing CO2 Emissions in Beijing with Scenario Analysis , 2017 .

[41]  René Kemp,et al.  Index Decomposition Analysis of Residential Energy Consumption in China: 2002-2010 , 2014 .