安徽大学学报（自然科学版）2025，Vol.49Issue(4)：28-37,10.DOI:10.3969/j.issn.1000-2162.2025.04.004
基于序列重构的VMD-SSA-LSSVM组合模型短期碳排放预测
Short-term carbon emission prediction of VMD-SSA-LSSVM combined model based on sequence reconstruction
摘要
Abstract
Due to the randomness and volatility of carbon emission series,the prediction accuracy was not high.A combined VMD-SSA-LSSVM(variational mode decomposition-sparrow search algorithm-least square support vector machine)model based on sequence reconstruction was proposed for short-term carbon emission prediction.Initially,VMD decomposed the daily carbon emission data series into four sub-sequences with distinct center frequencies,along with one residual sequence to mitigate irregular data interference.Subsequently,sequence reconstruction was applied to each decomposed sequence to enhance prediction accuracy,particularly at mutation points.Utilizing the relevant parameters of SSA optimization kernel function,an SSA-LSSVM prediction model was established for each sequence post-reconstruction,taking into account the characteristics of different components.At last,the predicted values were fused to obtain the predicted results.The results showed that the combined model based on sequence reconstruction could effectively improve the accuracy of short-term carbon emission prediction.关键词
短期碳排放预测/序列重构/变分模态处理/最小二乘支持向量机Key words
short-term carbon emission prediction/sequence reconstruction/variational mode decomposition/least square support vector machine分类
信息技术与安全科学引用本文复制引用
徐正林,程志友,张帅,杨猛..基于序列重构的VMD-SSA-LSSVM组合模型短期碳排放预测[J].安徽大学学报（自然科学版）,2025,49(4):28-37,10.基金项目
国家自然科学基金资助项目(61672032) （61672032）
安徽省自然科学基金资助项目(2108085QE237) （2108085QE237）
