Font Size: a A A

Research On Carbon Emission Scenario Prediction In Hebei Province Based On IGWO-SVM Model

Posted on:2020-08-11Degree:MasterType:Thesis
Country:ChinaCandidate:F YangFull Text:PDF
GTID:2370330578465202Subject:Technical Economics and Management
Abstract/Summary:PDF Full Text Request
Rapid industrial development and urbanization have accumulated a series of environmental problems,exerting excessive pressure on the city’s environmental capacity,and also brought smog in the city.Hebei Province,as an important component of Beijing-Tianjin-Hebei,its development orientation,energy policy,and industrial structure are closely related to Beijing-Tianjin-Hebei coordination.At the same time,Hebei Province’s carbon emission problem is also one of the main causes of environmental problems in Beijing-Tianjin-Hebei.Facing the new situation of coordinated development and more environmental constraints,the factors affecting the carbon emissions in Hebei Province will be screened and determined,the mechanism of influencing factors will be quantitatively studied,and carbon emissions will be predicted under different synergies to reduce carbon emissions in Hebei Province,which are very important.This will be conducive to the more scientific and rational formulation of carbon emissions and related energy-saving and emission reduction policies in Hebei Province.On the basis of controlling environmental pollution,it will help the smooth implementation of the Beijing-Tianjin-Hebei coordinated development policy and ensure the smooth realization of the medium-and long-term synergy between Beijing and Tianjin.Planning objectives.In this paper,we first analyze the domestic and international factors affecting carbon emissions and forecasting methods.Furthermore,based on the Beijing-TianjinHebei coordinated development policy,we study the functional orientation and carbon emission changes of Hebei Province in this context.Macroscopically grasp the carbon emissions of Hebei Province.Combined with the current situation of energy consumption in Hebei Province,calculate the carbon emissions based on energy consumption.Through the analysis of the positioning and status quo of Hebei Province,it will provide a basis for studying the factors affecting carbon emissions and setting up scenarios to control carbon emissions.This paper innovatively designed a set of carbon emission forecasting system in Hebei Province,through the carbon emission influencing factors grading screening,improved intelligent algorithm model construction,and scenario prediction for the carbon emissions of Hebei Province from 2018 to 2025.In the first stage,the SPIRPAT and ridge regression methods were used to analyze the panel data of carbon emissions and their factors from 1995 to 2016.The most critical factors affecting carbon emissions were economic,population,urban development level,industrial structure,energy structure traffic level,and technical factors.In the second stage,the support vector machine model based on differential evolution improved grey wolf hybrid algorithm(IGWO-SVM)was constructed for the first time,and the factors affecting the carbon emissions based on energy consumption were analyzed.In the third stage,three different scenarios of benchmark synergy,planning synergy and high synergy are defined according to the relevant policies,planning objectives and actual conditions of Hebei Province.Based on different scenarios,the future development trend of carbon emissions in Hebei Province from 2018 to 2025 is predicted.According to the forecast results,by 2025,under the benchmark synergy scenario,Hebei’s carbon emissions will be 364.63 million tons;in the planned synergy scenario,332.7 million tons;in the high synergy scenario,30.632 million tons.Based on the predicted results,this paper puts forward some targeted opinions to provide theoretical basis for Hebei province to formulate carbon emission policies and effectively control carbon emission from the source.
Keywords/Search Tags:Carbon emission prediction, Beijing-Tianjin-Hebei collaboration, SPIRPAT, Improved grey wolf algorithm, Support vector machine
PDF Full Text Request
Related items