| 引用本文: | 殷豪,董朕,陈云龙.基于CEEMD和膜计算优化支持向量机的风速预测[J].电力系统保护与控制,2017,45(21):27-34.[点击复制] |
| YIN Hao,DONG Zhen,CHEN Yunlong.Wind speed forecasting based on complementary ensemble empirical mode decomposition and support vector regression optimized by membrane computing optimization[J].Power System Protection and Control,2017,45(21):27-34[点击复制] |
|
| 摘要: |
| 为提高预测的可靠性和准确性，提出一个基于模态分解理论和膜计算优化算法的混合模型用于风速预测。与现有的风速预测方法相比，该模型提高了预测精度。该模型包括3个主要步骤:为了简化数据的复杂度，通过互补集合经验模式分解(CEEMD)将原始风电功率时间序列分解成几个固有模态函数(IMFs)；对每个IMF分量单独建立膜计算优化算法优化支持向量机(MCO-SVR)的模型进行预测；叠加全部IMF分量的预测值作为最终的预测结果。建立包括单一的支持向量回归机模型、不同分解方法以及相同的分解方法但使用不同的优化算法在内的9种基本模型，来验证所提出的混合模型的优越性。实证研究表明，所提出的混合模型在预测精度上显著优于其他的基本模型。 |
| 关键词: 互补经验模态分解 膜计算优化算法 支持向量回归机 风速预测 |
| DOI：10.7667/PSPC161805 |
| 投稿时间：2016-10-29修订日期：2017-02-14 |
| 基金项目:广东省科技计划项目(2016A010104016);广东电网公司科技项目(GDKJQQ20152066) |
|
| Wind speed forecasting based on complementary ensemble empirical mode decomposition and support vector regression optimized by membrane computing optimization |
| YIN Hao,DONG Zhen,CHEN Yunlong |
| (College of Automation, Guangdong University of Technology, Guangzhou 510006, China) |
| Abstract: |
| To enhance prediction reliability and accuracy, a hybrid model based on the promising principle of mode decomposition and new algorithm called Membrane Computing Optimization (MCO) is introduced for wind speed forecasting. Compared with existing wind speed forecasting methods, this proposed model has improved the prediction accuracy. The proposed model involves three main steps:decomposing the original wind speed series into several Intrinsic Mode Functions (IMFs) via Complementary Ensemble Empirical Mode Decomposition (CEEMD) for simplifying the complex data, individually predicting each IMF with Support Vector Regression (SVR) optimized by MCO, and integrating all predicted IMFs for the ensemble result as the final prediction. Nine benchmark models, including single support vector regression models, different decomposition methods and models with the same decomposition method but optimized by different algorithms, are considered to verify the superiority of the proposed hybrid model. The empirical study indicates that the proposed hybrid model is remarkably superior to all considered benchmark models for its higher prediction accuracy. |
| Key words: complementary ensemble empirical mode decomposition membrane computing optimization support vector regression wind speed forecasting |
