文献类型：期刊文献

英文题名：Forecasting Carbon Dioxide Emissions in China Using Optimization Grey Model

作者：Sun, Wei[1];Wang, Jingmin[2];Chang, Hong[3]

机构：[1]North China Elect Power Univ, Sch Econ & Management, Informat Syst Management & Decis Support Syst, Baoding, Peoples R China;[2]North China Elect Power Univ, Sch Econ & Management, Baoding, Peoples R China;[3]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Shanghai, Peoples R China

年份：2013

卷号：8

期号：1

起止页码：97

外文期刊名：JOURNAL OF COMPUTERS

收录：EI(收录号：20130415927680);WOS:【ESCI(收录号:WOS:000218148100014)】；

基金：This work was supported by NSFC Project (71071052) and Fundamental Research Funds for the Central Universities (12MS137).

语种：英文

外文关键词：Carbon dioxide emissions forecasting; greenhouse gases; Harmony Search algorithm; optimization GM (1, 1) model

摘要：Carbon dioxide (CO2) is one of the most important anthropogenic greenhouse gases (GHG) that caused global environmental degradation and climate change. China has been the top carbon dioxide emitter since 2007, surpassing the USA by an estimated 8%. So, forecasting future CO2 emissions trend in China provides the basis for policy makers to draft scientific and rational energy and economic development policies. This paper presents an optimization GM (1, 1) model to forecast the carbon dioxide emissions in China. In traditional GM (1, 1) model, the background value usually chooses the constant 0.5. But taking the same background parameter values for each time with different trend will result in degrading the forecasting accuracy. And it is also the main reason why the accuracy is lower with non-smooth sequence forecasting. So, the rational background value should be selected during parameter identification process. Considering the limitation of traditional GM (1, 1), the background value vectora is introduced to assign different parameters for different times instead of choosing constant value 0.5 to compute background value array. And the Harmony Search (HS) algorithm is adopted to determine the value of a through optimizing the Mean Absolute Percentage Error (MAPE) function. The proposed HS optimization GM (1, 1) is applied to carbon dioxide emissions forecast in China. And the simulation results show that the HS optimization GM (1, 1) model gives better accuracy.