基于EMD-PSO-LSSVM的碳排分解集成预测方法
DOI:
作者:
作者单位:

四川大学

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

国家自然科学基金面上项目


A decomposition integration forecasting method of carbon emission based on EMD-PSO-LSSVM
Author:
Affiliation:

Sichuan University

Fund Project:

National Natural Science Foundation of China

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    二氧化碳排放量的发展趋势作为能够反映各国减排措施的指标之一, 近些年来受到了广泛关注. 为了缓解碳排放数据的非线性和波动性对预测精度造成的影响, 本文提出了一种高效的分解集成预测方法用于预测二氧化碳的年排放量. 碳排的原始序列数据被经验模态分解(Empirical Mode Decomposition, EMD) 方法分解为不同频率的振动模块和残差项, 粒子群优化算法(Particle Swarm Optimization, PSO) 优化后的最小二乘支持向量机(Least Squares Support Vector Machine, LSSVM) 用于预测每个分解模块. 本文选取了世界上12 个国家的真实碳排数据进行实例验证. 预测结果表明:1) EMD 方法能够有效提高碳排预测的精准度? 2) 和其他预测模型相比, 分解集成预测方法能够将平均绝对误差(Mean Absolute Error, MAE) 的均值最少提高49.69%, 最多提高90.68%, 能够将平均Pearson 相关系数(Pearson correlation coefficient, PCC) 值最少提高13.43%, 最多提高49.02%.

    Abstract:

    The emission of carbon dioxide has received many attention in recent years, as it can reflect the effectiveness of those lowcarbon measures. To alleviate the nonlinearity and volatility of the annual carbon dioxide emissions, which may affect the forecast accuracy, this paper proposes an efficient decompositionintegration forecasting method to forecast the annual carbon emissions. The empirical mode decomposition (EMD) is used to decompose the original emission series into intrinsic oscillatory modes (IMFs) and a residual with different frequencies. The least squares support vector machine (LSSVM) is optimized by particle swarm optimization (PSO) algorithm to predict each decomposed part. This paper chooses the real annual carbon emission of 12 countries all over the world to do the case study. The forecasting results indicate the validity of the EMD on improving the accuracy of carbon emission prediction. Furthermore, the comparison results between the EMDPSOLSSVM method and other forecasting models show the EMDPSOLSSVM can improve the average accuracy of the mean absolute error (MAE) at least 49.69% and at most 90.68%, and can improve the average Pearson correlation coefficient (PCC) at least 13.43% and at most 49.02%.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-12-21
  • 最后修改日期:2021-04-07
  • 录用日期:2021-04-21
  • 在线发布日期:
  • 出版日期: