[1]吕靖烨,杜靖南,曹铭,等.利用ARIMA-SVM模型的碳排放交易价格预测[J].西安科技大学学报,2020,(03):542-548.[doi:10.13800/j.cnki.xakjdxxb.2020.0323]
 LYU Jing-ye,DU Jing-nan,CAO Ming,et al.Carbon emissions trading price prediction using the ARIMA-SVM model[J].Journal of Xi'an University of Science and Technology,2020,(03):542-548.[doi:10.13800/j.cnki.xakjdxxb.2020.0323]
点击复制

利用ARIMA-SVM模型的碳排放交易价格预测(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2020年03期
页码:
542-548
栏目:
出版日期:
2020-05-15

文章信息/Info

Title:
Carbon emissions trading price prediction using the ARIMA-SVM model
文章编号:
1672-9315(2020)03-0542-07
作者:
吕靖烨12杜靖南1曹铭1樊秀峰2
(1.西安科技大学 管理学院,陕西 西安 710054; 2.西安交通大学 经济与金融学院,陕西 西安 710049)
Author(s):
LYU Jing-ye12DU Jing-nan1CAO Ming1FAN Xiu-feng2
(1.College of Management,Xi'an University of Science and Technology,Xi'an 710054,China; 2.School of Economics and Finance,Xi'an Jiaotong University,Xi'an 710049,China)
关键词:
碳排放交易价格 时间序列 ARIMA-SVM 预测 精度
Keywords:
carbon emissions trading price time series ARIMA-SVM forecast accuracy
分类号:
F 224
DOI:
10.13800/j.cnki.xakjdxxb.2020.0323
文献标志码:
A
摘要:
为了帮助企业、投资者和市场监管部门优化碳排放市场参与行为,需要对碳排放交易价格进行合理有效的预测。考虑到碳排放交易价格时间序列同时具有线性和非线性2种特征,选择ARIMA-SVM融合模型运用到碳排放交易价格预测中,发挥该模型预测精度高的优势。运用ARIMA-SVM模型、ARIMA模型、SVM模型和Db6-SVM模型对湖北碳排放交易价格进行8期预测。通过4种模型预测值的MSE值和MAE值确定预测精度,对比预测精度,探究ARIMA-SVM模型是否为准确有效的预测模型,实证结果表明:ARIMA-SVM模型的MSE值为0.177 0,是4种模型的最低值; MAE值为0.338 7,是4种模型的次低值。可以认为ARIMA-SVM模型的预测精度最高,是一种有效的且精度高的碳排放价格预测模型,可用于碳排放交易价格预测,可以为碳排放交易参与企业和各方投资者把握价格波动趋势,增强防范能力提供保障,也可以为市场监管职能部门防止碳排放交易价格过度波动及时制定有效措施。
Abstract:
Accurate and effective carbon emissions trading price prediction is of great significance to companies,for optimizing behavior of investors and market regulators involved in carbon emissions trading.The Autoregressive Integrated Moving Average model(ARIMA)-Support Vector Machine(SVM)model with a consideration of linear and non-linear features of the carbon emissions trading price time series is applied to the carbon emissions trading price prediction,and the model has the advantage of high prediction accuracy.The ARIMA-SVM model,ARIMA model,SVM model and Db6-SVM model are used to make 8 stage forecast of Hubei carbon emissions trading prices.The prediction accuracy is determined by the MSE and MAE values of the predicted values of the four models,and the prediction accuracy is compared in order to explore whether the ARIMA-SVM model is anaccurate and effective prediction model.The empirical results show that the MSE value of the ARIMA-SVM model is 0.177 0,which is the lowest value of the four models; theMAE value is 0.338 7,which is the second lowest value of the four models.It can be considered that the ARIMA-SVM model has the highest prediction accuracy,and is an effective and high-precision carbon emission price prediction model.It can be used for carbon emission transaction price prediction,and can grasp the price fluctuation trend for companies and investors of carbon emission transactions.In order to enhance the prevention capability and provide protection,it can also formulate effective measures for the market supervision function to prevent excessive fluctuations in carbon emissions trading prices.

参考文献/References:

[1] 王 玉,郇志坚.欧盟碳排放权交易市场的价格发现和波动溢出研究[J].中国人口·资源与环境,2012,22(S1):244-249. WANG Yu,YING Zhi-jian.Price discovery and volatility spillover in EU carbon emission trading market[J].China population·resources and environment,2012,22(S1):244-249. [2]吕靖烨,张金锁,李朋林,等.中国能源消费碳足迹的动态变化研究[J].西安科技大学学报,2014,34(5):539-545. LYU Jing-wei,ZHANG Jin-suo,LI Peng-lin,et al.Study on the Dynamic Change of China's Energy Consumption Carbon Footprint[J].Journal of Xi'an University of Science and Technology,2014,34(5):539-545. [3]程永伟,穆 东.我国试点碳市场运行效率评价研究[J].科技管理研究,2017,37(4):96-100. CHENG Yong-wei,MU Dong.Evaluation on the operational efficiency of the pilot carbon market in China[J].Science and Technology Management Research,2017,37(4):96-100. [4]齐绍洲,赵鑫,谭秀杰.基于EEMD模型的中国碳市场价格形成机制研究[J].武汉大学学报(哲学社会科学版),2015,68(4):56-65. QI Shao-zhou,ZHAO Xin,TAN Xiu-jie.Study on the price formation mechanism of China's carbon market based on EEMD model[J].Journal of Wuhan University(Philosophy And Social SciencesEdition),2015,68(4):56-65. [5]ZENG Shi-hong,NAN Xin,LIU Chao,et al.The response of the Beijing carbon emissions allowance price(BJC)to macroeconomic and energy price indices[J].Energy Policy,2017,106:111-121. [6]Zhu B Z,Ye S X,He K J,et al.Measuring the risk of European carbon market:an empirical mode decomposition-based value at risk approach[J].Annals of Operations Research,2019,281(1-2):373-395. [7]Boersen A,Scholtens B.The relationship between European electricity markets and emission allowance futures prices in phase II of the EU(European Union)emission trading scheme[J].Energy,2014,74:585-594. [8]Li W,Lu C.The research on setting a unified interval of carbon price benchmark in the national carbon trading market of China[J].Applied Energy,2015,155:728-739. [9]LYU Jing-ye,CAO Ming,LI Hai-feng.Price volatility in the carbon market in China[J].Journal of Cleaner Production,Volume 255,2020,289-311 [10]Zhu B Z,Han D,Wang P,et al.Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression[J].Applied Energy,2017,191:521-530. [11]Zhou J G,Yu X C,Yuan X L.Predicting the carbon price sequence in the Shenzhen emissions exchange using a multiscale ensemble forecasting model based on ensemble empirical mode decomposition[J].Energies,11(7):176-184. [12]Zhao X,Han M,Ding L L,et al.Usefulness of economic and energy data at different frequencies for carbon price forecasting in the EU ETS[J].Applied Energy,2018,216:132-141. [13]Yahsi M,Canakoglu E,Agrali S.Carbon price forecasting models based on big data analytics[J].CarbonManagement,2018,10(2):175-187. [14]杨 星,梁敬丽,蒋金良,等.多标度分形特征下碳排放权价格预测算法[J].控制理论与应用,2018,35(2):224-231. YANG Xing,LIANG Jing-li,JIANG Jin-liang,et al.Price prediction algorithm for carbon emission rights under multi-scale fractal features[J].Control Theory and Applications,2018,35(2):224-231. [15]姚 奕,吕 静,章成果.湖北省碳市场价格形成机制及价格预测[J].统计与决策,2017(19):166-169. YAO Wei,LYU Jing,ZHANG Cheng-guo.The price formation mechanism and price forecast of carbon market in Hubei Province[J].Statistics & Decision,2017(19):166-169. [16]刘金培,郭 艺,陈华友,等.基于非结构数据流行学习的碳价格多尺度组合预测[J].控制与决策,2019,34(2):279-286. LIU Jin-pei,GUO Yi,CHEN Hua-you,et al.Multi scale combination prediction of carbon price based on popular learning of unstructured data[J].Control and Decision Making,2019,34(2):279-286. [17]王 娜.基于Boosting-ARMA的碳价预测[J].统计与信息论坛,2017,32(3):28-34. WANG Na.Carbon price prediction based on boosting ARMA[J].Statistics and information forum,2017,32(3):28-34. [18]高 杨,李 健.基于EMD-PSO-SVM误差校正模型的国际碳金融市场价格预测[J].中国人口·资源与环境,2014,24(6):163-170. GAO Yang,LI Jian.Price prediction of international carbon financial market based on EMD-PSO-SVM error correction model[J].China Population·Resources and Environment,2014,24(6):163-170. [19]朱帮助,魏一鸣.基于GMDH-PSO-LSSVM的国际碳市场价格预测[J].系统工程理论与实践,2011,31(12):2264-2271. ZHU Bang-zhu,WEI Yi-ming.International carbon market price prediction based on GMDH-PSO-LSSVM[J].System Engineering Theory and Practice,2011,31(12):2264-2271. [20]Fanoodi Bahareh,Malmir Behnam,Jahantigh Farzad Firouzi.Reducing demand uncertainty in the platelet supply chain through artificial neural networks and ARIMA models[J].Computers in Biology and Medicine,2019,113:103415. [21]岳丽欣,周晓英,陈旖旎.基于ARIMA模型的信息构建研究主题趋势预测研究[J].图书情报知识,2019(5):54-63+72. YUE Li-xin,ZHOU Xiao-ying,CHEN Yi-li.Research on the prediction of information construction research theme trend based on ARIMA model[J].Library and Information Knowledge,2019(5):54-63; 72. [22]Babu C N,Reddy B E.A moving-average filter based hybrid ARIMA-ANN model for forecasting time series data[J].Applied Soft Computing,2014,23:27-38. [23]黄同愿,陈芳芳.基于SVM股票价格预测的核函数应用研究[J].重庆理工大学学报(自然科学版),2016,30(2):89-94. HUANG Tong-yuan,CHEN Fang-fang.Application of Kernel function based on SVM stock Price rediction[J].Journal of Chongqing University of Technology(Natural Science Edition),2016,30(2):89-94. [24]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95. LIU Ai-guo,XUE Yun-tao,HU Jiang-lu,et al.Ultra short term prediction of wind power based on GA optimized SVM[J].Power system protection and control,2015,43(2):90-95. [25]吕靖烨,曹 铭,吴 旷,等.湖北省碳排放权市场有效性的实证分析[J].系统工程,2018,36(11):23-30. LYU Jing-ye,CAO Ming,WU Kuang,et al.An empirical analysis of the effectiveness of carbon emission rights market in Hubei Province[J].System Engineering,2018,36(11):23-30. [26]崔焕影,窦祥胜.基于EMD-GA-BP与EMD-PSO-LSSVM的中国碳市场价格预测[J].运筹与管理,2018,27(7):133-143. CUI Huan-ying,DOU Xiang-sheng.China's carbon market price forecast based on EMD-GA-BP and EMD-PSO-LSSVM[J].Operations Research and Management,2018,27(7):133-143.

相似文献/References:

[1]朱 彬,王明明.偏压荷载下地铁隧道变形特征及预测研究[J].西安科技大学学报,2015,(04):458.
 ZHU Bin,WANG Ming-ming.Characteristics and forecast of deformation for shallow buried tunnel[J].Journal of Xi'an University of Science and Technology,2015,(03):458.
[2]陈 柳,吴冬梅,陈 俏.小波分析及支持向量机应用于大气污染预测[J].西安科技大学学报,2010,(06):726.
 CHEN Liu,WU dong-mei,CHEN Qiao.Prediction of air pollution based on wavelet analysis and support vector machine[J].Journal of Xi'an University of Science and Technology,2010,(03):726.

备注/Memo

备注/Memo:
收稿日期:2020-04-13 责任编辑:杨忠民
基金项目:陕西省教育科学“十三五”规划项目(SGH17H099); 西安科技大学博士后启动基金(8250119003)
通信作者:吕靖烨(1975-),男,河南新郑人,博士,副教授,E-mail:Lyujy@xust.edu.cn
更新日期/Last Update: 2020-05-15