
基于CEEMDAN-WD-PSO-LSSVM模型的月径流预测研究
徐冬梅, 庄文涛, 王文川
基于CEEMDAN-WD-PSO-LSSVM模型的月径流预测研究
Monthly Runoff Prediction Based on CEEMDAN-WD-PSO-LSSVM Model
针对径流序列的非线性、非稳态化的特点导致直接预测精度低的问题,提出了一种二次分解径流时间序列,再经过最小二乘支持向量机(LSSVM)模型进行月径流预测的新途径。该方法首先利用自适应噪声的完整集成经验模态分解(CEEMDAN)算法来分解原始径流时间序列,得到一系列本征模态分量(IMF)。再利用小波分解(WD)对高频分量进行二次分解,更有效地提取原始数据中的隐含信息。把各分量作为基于粒子群算法(PSO)优化的LSSVM预测模型的输入,最后将每个分量预测结果进行叠加重构,得到最终结果。以洛河流域长水水文站月径流为例,验证结果表明:提出的CEEMDAN-WD-PSO-LSSVM组合模型的预测精度较单一模型有效提高了径流预报精度,CEEMDAN-WD二次分解可更有效地提取复杂径流序列的信息,为非线性、非稳态化的月径流时间序列预测提供了新方法。
Aiming at the problem of low accuracy of direct prediction due to the non-linear and unstable characteristics of runoff series, a new method based on double decomposition of runoff time series and least squares support vector machine (LSSVM) model is proposed for monthly runoff prediction. Firstly, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the original runoff time series into a series of intrinsic mode function (IMF). Then the technique of wavelet decomposition (WD) is utilized to decompose the high-frequency components to extract the implicit information from the original data more effectively. Each component is taken as the input of the LSSVM prediction model optimized by particle swarm optimization (PSO). Finally, the prediction results of each component are superimposed and reconstructed to obtain the final result. Taking the monthly runoff at Changshui Hydrological Station in Luohe River Basin as an example, the verification results show that the proposed CEEMDAN-WD-PSO-LSSVM combination model improves the accuracy of runoff prediction better than that of the single model. The double decomposition conducted by CEEMDAN-WD is more powerful to detect the information of complex runoff series, and provide a new approach for forecasting the nonlinear and unstable monthly runoff time series.
径流预测 / CEEMDAN / 小波分解 / PSO-LSSVM模型 / 二次分解 {{custom_keyword}} /
runoff prediction / CEEMDAN / wavelet decomposition / PSO-LSSVM model / the secondary decomposition {{custom_keyword}} /
表1 各种模型预测误差对比Tab.1 Comparison of prediction errors of various models |
模 型 | 训练期 | 验证期 | ||||||
---|---|---|---|---|---|---|---|---|
R | NSEC | RMSE | MAPE/% | R | NSEC | RMSE | MAPE/% | |
PSO-LSSVM | 0.49 | 0.24 | 10 640.31 | 204.87 | 0.32 | -0.24 | 4 426.27 | 554.29 |
CEEMDAN-PSO-LSSVM | 0.94 | 0.89 | 4 137.93 | 111.57 | 0.83 | 0.66 | 2 331.12 | 164.06 |
WD-PSO-LSSVM | 0.98 | 0.95 | 2 627.13 | 67.75 | 0.94 | 0.87 | 1 419.97 | 117.70 |
CEEMDAN-WD-PSO-LSSVM | 0.98 | 0.96 | 2 389.06 | 57.19 | 0.96 | 0.91 | 1 165.00 | 83.90 |
1 |
王鑫,徐淑琴,李洪涛. 河川径流预测方法比较研究[J]. 中国农村水利水电,2014(4):98-100.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
雷晓辉,王浩,廖卫红,等. 变化环境下气象水文预报研究进展[J]. 水利学报,2018,49(1):9-18.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
王佳,王旭,王浩,等. 基于EEMD与ANN混合方法的水库月径流预测[J]. 人民黄河,2019,41(5):43-46.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
赵益平,王文圣,刘浅奎. R/S-BP网络耦合模型及其在年径流预测中的应用[J]. 华北水利水电大学学报(自然科学版),2019,40(4):40-45.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
张辉. 灰色理论在中长期水文预报中的应用研究[J]. 地下水,2014,36(6):164-165.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
李继伟,纪昌明,张新明,等. 基于支持向量机的水电站中长期径流组合预报[J]. 水电能源科学,2013,31(11):13-16.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
李文莉,李郁侠. 基于粒子群最小二乘支持向量机的水文预测[J]. 计算机应用,2012,32(4):1 188-1 190.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
张洪波,余荧皓,孙文博,等. 面向EMD分解的径流分量重构方法对比研究[J]. 南水北调与水利科技,2017,15(1):60-66.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
张敬平,黄强,赵雪花. 经验模态分解和RBF网络在径流预测中的应用[J]. 干旱区资源与环境, 2014,28(6):118-123.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
周婷,金菊良,李荣波,等. 基于小波支持向量机的径流预测性能优化分析[J]. 水力发电学报,2017,36(10):45-55.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
姜锋,丁志宏,赵焱. 基于CEEMDAN的黑河莺落峡年径流量多时间尺度变化特征研究[J]. 中国农村水利水电,2018(2):64-67.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
桑燕芳,王中根,刘昌明. 水文序列小波分析中分解层数选择方法[J]. 水文,2012,32(4):1-7.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
龙文,梁昔明,肖金红,等. 一种动态分级的混合粒子群优化算法[J]. 控制与决策,2009,24(10):1 513-1 516.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |