融合VMD和SSA-LSSVM的交通运输业碳排放预测研究

王庆荣; 王俊杰; 朱昌锋; 郝福乐

doi:10.13205/j.hjgc.202310016

融合VMD和SSA-LSSVM的交通运输业碳排放预测研究

doi: 10.13205/j.hjgc.202310016

1. 兰州交通大学电子与信息工程学院, 兰州 730070;
2. 兰州交通大学交通运输学院, 兰州 730070

基金项目:

国家自然科学基金（71961016，72161024）；教育部人文社会科学研究规划基金（18YJAZH148）；甘肃省自然科学基金（20JR10RA212、20JR10RA214）

详细信息

作者简介:
王庆荣(1977-),女,博士,教授,主要从事智能交通、应急物流方面的研究。329046272@qq.com

通讯作者:
王俊杰(1998-),男,硕士,主要从事机器学习、智能交通方面的研究。876087843@qq.com

计量
- 文章访问数: 88
- HTML全文浏览量: 13
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2023-05-18
- 网络出版日期: 2023-12-26

CARBON EMISSION PREDICTION OF TRANSPORTATION INDUSTRY BASED ON VMD AND SSA-LSSVM

1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China;
2. School of Transportation, Lanzhou Jiaotong University, Lanzhou 730070, China

摘要

摘要: 针对交通运输业碳排放数据序列的波动性和非线性问题，采用一种融合变分模态分解（VMD）、麻雀搜索算法（SSA）和最小二乘支持向量机（LSSVM）的组合预测模型，以更精准地对交通运输业碳排放量进行预测。首先，利用VMD方法将原始碳排放数据序列分解为多个复杂度低、平稳的模态分量和一个残差项，以降低碳排放数据序列的波动性和非线性；其次，对各分解模块建立LSSVM模型，并利用SSA对LSSVM模型参数进行寻优；最后，将各模块预测结果进行集成叠加，获得最终的碳排放预测结果。对我国交通运输业1990—2019年碳排放数据进行计算，以此对模型进行验证，并与多种模型进行比较。结果表明：VMD-SSA-LSSVM模型的均方根误差、平均绝对误差、平均绝对百分比误差、可决系数、Nash系数分别为628万t、574万t、0.73%、0.998、0.996，均优于其他模型，表明该模型能够有效提高预测精度。
- 交通运输业 /
- 变分模态分解 /
- 麻雀搜索算法 /
- 最小二乘支持向量机 /
- 碳排放预测
Abstract: Aiming at the volatility and nonlinearity of transport carbon emission data series, a combined prediction model combining variational mode decomposition (VMD), sparrow search algorithm (SSA), and least square support vector machine (LSSVM) was adopted to predict transport carbon emission more accurately. Firstly, the VMD method was used to decompose the original carbon emission data series into multiple low-complexity, stable modal components, and a residual term to reduce the volatility and nonlinearity of the carbon emission data series. Secondly, the LSSVM model was established for each decomposition module, and the parameters of the LSSVM model were optimized by SSA. Finally, the prediction results of each module were integrated and superimposed to obtain the final carbon emission prediction results. The carbon emission data of China's transportation industry from 1990 to 2019 were calculated to verify the model and compare it with various models. The results showed that the root-mean-mean error, mean absolute error, mean absolute percentage error, determination coefficient and Nash coefficient of the VMD-SSA-LSSVM model was 6.28 million t, 5.74 million t, 0.73%, 0.998 and 0.996, respectively, which was superior to other models, indicating that the model can effectively improve the prediction accuracy.
- transportation industry /
- variational mode decomposition /
- sparrow search algorithm /
- least squares support vector machine /
- carbon emission prediction

HTML全文

参考文献(22)

[1]	LIN B, XIE C.Reduction potential of CO₂, emissions in China's transport industry[J].Renewable & Susyainable Energy Reviews, 2014(33):689-700.
[2]	张新生, 任明月, 陈章政.基于CEEMD-SSA-ELM方法的建筑业碳排放预测研究[J/OL].生态经济:1-15[2023-04-14 ].http://kns.cnki.net/kcms/detail/53.1193.F.20221214.1300.002.html.
[3]	YANG H J, O'CONNELL J F.Short-term carbon emissions forecast for aviation industry in Shanghai[J].Journal of Cleaner Production, 2020, 275:122734.
[4]	王阳, 唐朝晖, 王紫勋, 等.选用改进高斯过程回归模型的碳排放短期预测[J].计算机工程与应用, 2018(23):246-251.
[5]	QIAO W B, LU H F, ZHOU G F, et al.A hybrid algorithm for carbon dioxide emissions forecasting based on improved lion swarm optimizer[J].Journal of Cleaner Production, 2020, 244:118612.
[6]	GAO M Y, YANG H L, XIAO Q Z, et al.A novel method for carbon emission forecasting based on Gompertz's law and fractional grey model:evidence from American industrial sector[J].Renewable Energy, 2022, 181:803-819.
[7]	陈亮, 王金泓, 何涛, 等.基于SVR的区域交通碳排放预测研究[J].交通运输系统工程与信息, 2018, 18(2):13-19.
[8]	徐勇戈, 宋伟雪.基于FCS-SVM的建筑业碳排放预测研究[J].生态经济, 2019, 35(11):37-41.
[9]	王珂珂, 牛东晓, 甄皓, 等.基于WOA-ELM模型的中国碳排放预测研究[J].生态经济, 2020, 36(8):20-27.
[10]	张雯, 吴志彬, 徐玖平.基于EMD-PSO-LSSVM的碳排分解集成预测方法[J].控制与决策, 2022, 37(7):1837-1846.
[11]	BOKDE N D, TRANBERG B, ANDRESEN G B.Short-term CO₂ emissions forecasting based on decomposition approaches and its impact on electricity market scheduling[J].Applied Energy, 2021, 281:116061.
[12]	LI W, GAO S B.Prospective on energy related carbon emissions peak integrating optimized intelligent algorithm with dry process technique application for China's cement industry[J].Energy, 2018, 165:33-54.
[13]	IPCC.2006 IPCC Guidelines for National Greenhouse Gas Inventories[R].Cambridge:Cambridge University Press, 2006.
[14]	贾顺平, 毛保华, 刘爽, 等.中国交通运输能源消耗水平测算与分析[J].交通运输系统工程与信息, 2010, 10(1):22-27.
[15]	刘淳森, 曲建升, 葛钰洁, 等.基于LSTM模型的中国交通运输业碳排放预测[J].中国环境科学, 2023, 43(5):2574-2582.
[16]	国家统计局能源统计司, 国家能源局综合司.中国能源统计年鉴2021[M].北京:中国统计出版社, 2021.
[17]	DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J].IEEE Transactions on Signal Processing, 2013, 62(3):531-544.
[18]	XU B Z, FENG X, LI H, et al.Early fault feature extraction of bearings based on Teager energy operator and optimal VMD[J].ISA transactions, 2018.
[19]	XUE J K, SHEN B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science & Control Engineering, 2020, 8(1):22-34.
[20]	池小波, 续泽晋, 贾新春, 等.基于WPD-ISSA-CA-CNN模型的电厂碳排放预测[J/OL].控制工程:1-8[2023-09-09 ].DOI: 10.14107/j.cnki.kzgc.20220983.
[21]	王瑞, 王超, 逯静.基于VMD-ICSA-LSSVM的短期光伏功率预测[J].制造业自动化, 2023, 45(3):124-129.
[22]	潘思羽, 张美玲.基于BP神经网络的甘肃省二氧化碳排放预测及影响因素研究[J].环境工程, 2023, 41(7):61-68 , 85.