摘要
为准确进行需水预测,提出一种基于灰色关联度分析的PSO-SVR需水预测模型,该模型运用灰色关联度分析方法筛选出需水的主要影响因子,在此基础.上应用粒子群算法优化支持向量回归机(SVR)模型中的参数,并利用此模型预测2015~2017年山西省需水量。结果表明,总需水量相对误差的绝对值分别为0.02%、0.08%、0.03%,可见PSO-SVR模型具有较高的拟合度和预测精度,可为需水预测提供一种新方法。
In order to accurately-predict water demand,a PSO-SVR water demand forecast model is proposed based on gray correlation analysis.The gray correlation analysis method was used to screen out the main influencing factors of water demand.And then the particle swarm optimization algorithm was adopted to optimize the parameters of support vector regression machine(SVR) model.The model was used to predict the water demand in Shanxi Province from 2015 to 2017.The results show that the absolute values of the relative errors of the total water demand are 0.02%,0.08%,and0.03%,respectively.It can be seen that the PSO-SVR model has a high degree of fitting and prediction accuracy,which can provide a new method for water demand prediction.
作者
单义明
杨侃
SHAN Yi-ming;YANG Kan(College of Hydrology and Water Resources,Hohai University,Nanjing 210098,China)
出处
《水电能源科学》
北大核心
2021年第2期18-21,共4页
Water Resources and Power
基金
山西省水利科学技术研究与推广项目
国家重点基础研究发展计划(973计划)(2012CB417006)。
关键词
灰色关联分析
支持向量回归机模型
粒子群算法
需水预测
山西省
grey relational analysis
SVR model
particle swarm algorithm
water demand prediction
Shanxi Province
