GA-Based Support Vector Machine Model for the Prediction of Monthly Reservoir Storage

被引：45

作者：

Su, Jieqiong ^{[1
,2
]}

Wang, Xuan ^{[3
]}

Liang, Yong ^{[4
]}

Chen, Bin ^{[5
]}

机构：

[1] Beijing Normal Univ, Key Lab Water & Sediment Sci, Minist Educ, Sch Environm, Beijing 100875, Peoples R China

[2] Chinese Acad Environm Planning, Minist Environm Protect, Beijing 100012, Peoples R China

[3] Beijing Normal Univ, Key Lab Water & Sediment Sci, Minist Educ, State Key Lab Water Environm Simulat,Sch Environm, Beijing 100875, Peoples R China

[4] Management Off Miyun Reservoir, Beijing 101512, Peoples R China

[5] Beijing Normal Univ, Sch Environm, State Key Lab Water Environm Simulat, Beijing 100875, Peoples R China

来源：

JOURNAL OF HYDROLOGIC ENGINEERING | 2014年 / 19卷 / 07期

基金：

美国国家科学基金会;

关键词：

Prediction model; Reservoir storage; Support vector machine; Genetic algorithm; Miyun Reservoir; ARTIFICIAL NEURAL-NETWORK; PARTICLE SWARM OPTIMIZATION; GENETIC ALGORITHM; FORECASTING SYSTEM; SEDIMENTATION;

D O I：

10.1061/(ASCE)HE.1943-5584.0000915

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

Reservoir storage prediction is essential to the operation and management of reservoirs. In this paper, a genetic algorithm (GA)-based support vector machine (SVM) model was developed for the prediction of monthly reservoir storage of Miyun Reservoir (the only surface drinking water source for Beijing city) over the period of 1995 to 2011. At the same time, two other SVM-based models that combine grid search and particle swarm optimization methods respectively for the parameter optimization, were used for comparison. The results showed that the developed GA-SVM model had the best performance in calibration and prediction. Owing to its high accuracy, the GA-SVM model would be popularized to the prediction of reservoir storage in other regions. (C) 2014 American Society of Civil Engineers.

引用

页码：1430 / 1437

页数：8

共 29 条

[1]

[Anonymous], SOFT COMPUTING WATER

[2] High accuracy measurements of water storage change in Mining Lake 111, Germany [J].

Boehrer, Bertram ;

Kastner, Stephanie ;

Ollesch, Gregor .

LIMNOLOGICA, 2010, 40 (02) :156-160

[3]

Chiang J. L., 2011, APPL MECH MAT, V145, P455, DOI DOI 10.4028/www.scientific.net/AMM.145.455

[4] Dynamically exploring internal mechanism of stock market by fuzzy-based support vector machines with high dimension input space and genetic algorithm [J].

Chiu, Deng-Yiv ;

Chen, Ping-Jie .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :1240-1248

[5] Comparison of two different data-driven techniques in modeling lake level fluctuations in Turkey [J].

Cimen, Mesut ;

Kisi, Ozgur .

JOURNAL OF HYDROLOGY, 2009, 378 (3-4) :253-262

[6] An intelligent computing technique for fluid flow problems using hybrid adaptive neural network and genetic algorithm [J].

El-Emam, Nameer N. ;

Al-Rabeh, Riadh H. .

APPLIED SOFT COMPUTING, 2011, 11 (04) :3283-3296

[7] Fault diagnosis of power transformer based on support vector machine with genetic algorithm [J].

Fei, Sheng-wei ;

Zhang, Xiao-bin .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (08) :11352-11357

[8] Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM) [J].

Fernandez, Michael ;

Caballero, Julio ;

Fernandez, Leyden ;

Sarai, Akinori .

MOLECULAR DIVERSITY, 2011, 15 (01) :269-289

[9] Development of a forecasting system for supporting remediation design and process control based on NAPL-biodegradation simulation and stepwise-cluster analysis [J].

Huang, GH ;

Huang, YF ;

Wang, GQ ;

Xiao, HN .

WATER RESOURCES RESEARCH, 2006, 42 (06)

[10] Nonlinear Inertia Weigh Particle Swarm Optimization combines Simulated Annealing Algorithm and Application in Function and SVM Optimization [J].

Jiao Bin ;

Xu Zhixiang .

MECHANICAL AND ELECTRONICS ENGINEERING III, PTS 1-5, 2012, 130-134 :3467-3471

← 1 2 3 →