Daily Reservoir Runoff Forecasting Method Using Artificial Neural Network Based on Quantum-behaved Particle Swarm Optimization

被引:74
作者
Cheng, Chun-tian [1 ]
Niu, Wen-jing [1 ]
Feng, Zhong-kai [1 ]
Shen, Jian-jian [1 ]
Chau, Kwok-wing [2 ]
机构
[1] Dalian Univ Technol, Inst Hydropower & Hydroinformat, Dalian 116024, Peoples R China
[2] Hong Kong Polytech Univ, Dept Civil & Environm Engn, Hong Kong 999077, Hong Kong, Peoples R China
关键词
SUPPORT VECTOR MACHINES; GLOBAL OPTIMIZATION; GENETIC ALGORITHM; RAINFALL; MODEL; ACCURACY; INFLOW; ARIMA;
D O I
10.3390/w7084232
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate daily runoff forecasting is of great significance for the operation control of hydropower station and power grid. Conventional methods including rainfall-runoff models and statistical techniques usually rely on a number of assumptions, leading to some deviation from the exact results. Artificial neural network (ANN) has the advantages of high fault-tolerance, strong nonlinear mapping and learning ability, which provides an effective method for the daily runoff forecasting. However, its training has certain drawbacks such as time-consuming, slow learning speed and easily falling into local optimum, which cannot be ignored in the real world application. In order to overcome the disadvantages of ANN model, the artificial neural network model based on quantum-behaved particle swarm optimization (QPSO), ANN-QPSO for short, is presented for the daily runoff forecasting in this paper, where QPSO was employed to select the synaptic weights and thresholds of ANN, while ANN was used for the prediction. The proposed model can combine the advantages of both QPSO and ANN to enhance the generalization performance of the forecasting model. The methodology is assessed by using the daily runoff data of Hongjiadu reservoir in southeast Guizhou province of China from 2006 to 2014. The results demonstrate that the proposed approach achieves much better forecast accuracy than the basic ANN model, and the QPSO algorithm is an alternative training technique for the ANN parameters selection.
引用
收藏
页码:4232 / 4246
页数:15
相关论文
共 33 条
[1]   Improved Particle Swarm Optimization-Based Artificial Neural Network for Rainfall-Runoff Modeling [J].
Asadnia, Mohsen ;
Chua, Lloyd H. C. ;
Qin, X. S. ;
Talei, Amin .
JOURNAL OF HYDROLOGIC ENGINEERING, 2014, 19 (07) :1320-1329
[2]   Particle swarm optimization training algorithm for ANNs in stage prediction of Shing Mun River [J].
Chau, K. W. .
JOURNAL OF HYDROLOGY, 2006, 329 (3-4) :363-367
[3]   Comparison of several flood forecasting models in Yangtze river [J].
Chau, KW ;
Wu, CL ;
Li, YS .
JOURNAL OF HYDROLOGIC ENGINEERING, 2005, 10 (06) :485-491
[4]   Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall-runoff model calibration [J].
Cheng, CT ;
Ou, CP ;
Chau, KW .
JOURNAL OF HYDROLOGY, 2002, 268 (1-4) :72-86
[5]   The particle swarm - Explosion, stability, and convergence in a multidimensional complex space [J].
Clerc, M ;
Kennedy, J .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (01) :58-73
[6]   OPTIMAL USE OF THE SCE-UA GLOBAL OPTIMIZATION METHOD FOR CALIBRATING WATERSHED MODELS [J].
DUAN, QY ;
SOROOSHIAN, S ;
GUPTA, VK .
JOURNAL OF HYDROLOGY, 1994, 158 (3-4) :265-284
[7]   SHUFFLED COMPLEX EVOLUTION APPROACH FOR EFFECTIVE AND EFFICIENT GLOBAL MINIMIZATION [J].
DUAN, QY ;
GUPTA, VK ;
SOROOSHIAN, S .
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1993, 76 (03) :501-521
[8]   EFFECTIVE AND EFFICIENT GLOBAL OPTIMIZATION FOR CONCEPTUAL RAINFALL-RUNOFF MODELS [J].
DUAN, QY ;
SOROOSHIAN, S ;
GUPTA, V .
WATER RESOURCES RESEARCH, 1992, 28 (04) :1015-1031
[9]  
Eberhart R., P 6 INT S MICROMACHI, P39, DOI DOI 10.1109/MHS.1995.494215
[10]   A Review of Quantum-behaved Particle Swarm Optimization [J].
Fang, Wei ;
Sun, Jun ;
Ding, Yanrui ;
Wu, Xiaojun ;
Xu, Wenbo .
IETE TECHNICAL REVIEW, 2010, 27 (04) :336-348