Forecasting Daily Runoff by Extreme Learning Machine Based on Quantum-Behaved Particle Swarm Optimization

被引:86
作者
Niu, Wen-jing [1 ]
Feng, Zhong-kai [2 ]
Cheng, Chun-tian [3 ]
Zhou, Jian-zhong [2 ]
机构
[1] ChangJiang Water Resources Commiss, Bur Hydrol, Wuhan 430010, Hubei, Peoples R China
[2] Huazhong Univ Sci & Technol, Sch Hydropower & Informat Engn, Wuhan 430074, Hubei, Peoples R China
[3] Dalian Univ Technol, Inst Hydropower & Hydroinformat, Dalian 116024, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Hydrologic time series; Daily runoff prediction; Extreme learning machine (ELM); Quantum-behaved particle swarm optimization (QPSO); Artificial neural network; XINANJIANG MODEL; GENETIC ALGORITHM; PREDICTION; PERFORMANCE; NETWORKS; CALIBRATION; ACCURACY; IMPROVE; ARIMA;
D O I
10.1061/(ASCE)HE.1943-5584.0001625
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Accurate hydrologic time-series prediction plays an important role in modern water resource planning, water supply management, environmental protection, and power system operation. In general, single-layer feedforward networks (SLFNs) can provide satisfactory forecasting results, but classical gradient-based learning algorithms are time consuming and easily trapped into local optimums. As a new training method for SLFNs, extreme learning machine (ELM) has faster training speed and stronger nonlinear mapping than gradient-based algorithms, and provides an effective technique for hydrologic time-series prediction. However, ELM may converge to local minimums in some cases due to the random determination of input weights and hidden biases. Thus, in order to overcome the shortcomings of ELM, this paper introduces a novel ELM-quantum-behaved particle swarm optimization (QPSO) model (ELM-QPSO) combining the advantages of ELM and QPSO. The proposed model adopts the QPSO algorithm to select the optimal input-hidden weights and hidden biases of ELM, and uses the Moore-Penrose generalized inverse to analytically determine the output weights. The proposed approach is assessed with daily runoff data of Xinfengjiang reservoir in China from January 1, 2000 to December 31, 2014. The results indicate that the ELM-QPSO can significantly improve the generalization performance of ELM for hydrologic time-series prediction, and that QPSO is an alternative training algorithm for ELM parameters selection. (c) 2018 American Society of Civil Engineers.
引用
收藏
页数:10
相关论文
共 50 条
[11]   A comparative study of population-based optimization algorithms for downstream river flow forecasting by a hybrid neural network model [J].
Chen, X. Y. ;
Chau, K. W. ;
Busari, A. O. .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2015, 46 :258-268
[12]   A Hybrid Double Feedforward Neural Network for Suspended Sediment Load Estimation [J].
Chen, Xiao Yun ;
Chau, Kwok Wing .
WATER RESOURCES MANAGEMENT, 2016, 30 (07) :2179-2194
[13]   Forecasting Concurrent Flows in a River System Using ANNs [J].
Choudhury, Parthasarathi ;
Roy, Parthajit .
JOURNAL OF HYDROLOGIC ENGINEERING, 2015, 20 (08)
[14]   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
[15]   Multiobjective Operation Optimization of a Cascaded Hydropower System [J].
Feng, Zhong-Kai ;
Niu, Wen-Jing ;
Zhou, Jian-Zhong ;
Cheng, Chun-Tian .
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2017, 143 (10)
[16]   Multi-objective quantum-behaved particle swarm optimization for economic environmental hydrothermal energy system scheduling [J].
Feng, Zhong-kai ;
Niu, Wen-jing ;
Cheng, Chun-tian .
ENERGY, 2017, 131 :165-178
[17]   Hydropower system operation optimization by discrete differential dynamic programming based on orthogonal experiment design [J].
Feng, Zhong-kai ;
Niu, Wen-jing ;
Cheng, Chun-tian ;
Liao, Sheng-li .
ENERGY, 2017, 126 :720-732
[18]   Parallel Multi-Objective Genetic Algorithm for Short-Term Economic Environmental Hydrothermal Scheduling [J].
Feng, Zhong-Kai ;
Niu, Wen-Jing ;
Zhou, Jian-Zhong ;
Cheng, Chun-Tian ;
Qin, Hui ;
Jiang, Zhi-Qiang .
ENERGIES, 2017, 10 (02)
[19]   Modeling of groundwater level fluctuations using dendrochronology in alluvial aquifers [J].
Gholami, V. ;
Chau, K. W. ;
Fadaee, F. ;
Torkaman, J. ;
Ghaffari, A. .
JOURNAL OF HYDROLOGY, 2015, 529 :1060-1069
[20]   Trends in extreme learning machines: A review [J].
Huang, Gao ;
Huang, Guang-Bin ;
Song, Shiji ;
You, Keyou .
NEURAL NETWORKS, 2015, 61 :32-48