Multireservoir Modeling with Dynamic Programming and Neural Networks

Chandra-Mouli, Venkatraman; Raman, H.

doi:10.1061/(asce)0733-9496(2001)127:2(89)

Cited by 105 publications

(51 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Where   Chaotic optimization algorithm (COA), which utilizes the nature of chaos sequence including the quasi-stochastic property and ergodicity, is a popular optimization method [6] CPSO is introduction of chaos optimization ideas into particle swarm optimization algorithm; the main purpose is to find the dynamic perturbation of the particles by introducing the norepetitive ergodicity of the chaos into the solution space. By introducing processing, can make the particles in the solution space in the random and regular "flight", jump out from local space to find a better solution, improve the speed and precision of the particle optimization process.…”

Section: Cpsomentioning

confidence: 99%

“…The algorithms are usually classified into three general categories: traditional optimizers, modern metaheuristics, and hybrid approaches. Various optimization models based on linear programming (LP), no-linear programming (NLP), dynamic programming (DP), genetic algorithms (GA), artificial neural Network (ANN) and differential evolution (DE) have been developed for solving the cascade reservoir hydroelectric system scheduling problem in recent years [5,6]. However, the existed drawbacks included premature phenomena and trapping in the local optimum lead to these methods no longer suitable for complex cascaded hydro system [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cascade Reservoir Optimal Operation Based On Chaotic Particle Swarm Optimization

Zhong¹,

Dong²,

Zhao³

et al. 2017

Proceedings of the 2017 2nd Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC

View full text Add to dashboard Cite

In order to solve the cascade reservoir system scheduling, this paper proposed a novel cascade reservoir optimal operation model based on chaotic particle swarm optimization (CPSO) algorithm. The traditional particle swarm algorithm is improved by using the nature of chaos sequence including the quasi-stochastic property and ergodicity, which can avoid particle swarm optimization (PSO) algorithm into local optimum and improve the speed and precision of the particle optimization process. The case study in the Upper Yellow River showed that the proposed model was capable of cascade reservoir optimal operation.

show abstract

Section: Cpsomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Cascade Reservoir Optimal Operation Based On Chaotic Particle Swarm Optimization

Zhong¹,

Dong²,

Zhao³

et al. 2017

Proceedings of the 2017 2nd Joint International Information Technology, Mechanical and Electronic Engineering Conference (JIMEC

View full text Add to dashboard Cite

show abstract

“…The annual sediment runoff a preferable simulation effect for the daily and monthly runoff time series. The ANN is also adopted to derive operating policies of a reservoir, such as [15][16][17][18]. Neelakantan and Pundarikanthan [19] presented a planning model for reservoir operation using a combined backpropagation neural network simulation-optimization (Hooke and Jeeves nonlinear optimization method) process.…”

Section: Introductionmentioning

confidence: 99%

Simulation of Reservoir Sediment Flushing of the Three Gorges Reservoir Using an Artificial Neural Network

Qiu

Shang

et al. 2016

Applied Sciences

View full text Add to dashboard Cite

Abstract:Reservoir sedimentation and its effect on the environment are the most serious world-wide problems in water resources development and utilization today. As one of the largest water conservancy projects, the Three Gorges Reservoir (TGR) has been controversial since its demonstration period, and sedimentation is the major concern. Due to the complex physical mechanisms of water and sediment transport, this study adopts the Error Back Propagation Training Artificial Neural Network (BP-ANN) to analyze the relationship between the sediment flushing efficiency of the TGR and its influencing factors. The factors are determined by the analysis on 1D unsteady flow and sediment mathematical model, mainly including reservoir inflow, incoming sediment concentration, reservoir water level, and reservoir release. Considering the distinguishing features of reservoir sediment delivery in different seasons, the monthly average data from 2003, when the TGR was put into operation, to 2011 are used to train, validate, and test the BP-ANN model. The results indicate that, although the sample space is quite limited, the whole sediment delivery process can be schematized by the established BP-ANN model, which can be used to help sediment flushing and thus decrease the reservoir sedimentation.

show abstract

“…Among those, dynamic programming (DP) has long been recognized as powerful tool and global optimizer, however it targets only continuous optimal control problems in the field of operational optimization of waterwork systems [9][10][11][12][13][14][15]35]. In the context of dynamic programming discrete pump models are rarely used, the literature lacks the application of DP on combinatorial problems introduced by on/off type pumps or/and valves implemented in a water distribution system.…”

Section: Introductionmentioning

confidence: 99%

Water network operational optimization: Utilizing symmetries in combinatorial problems by dynamic programming

Bene

Selek

2012

Per. Pol. Civil Eng.

View full text Add to dashboard Cite

This paper introduces a dynamic programming (DP) approach for solving deterministic combinatorial operational optimization problem of water distribution networks. The implementation of dynamic programming over control domain using permutational symmetries is suggested to replace the state space based DP procedures. To enhance the understanding an application on a ub-network of the water supply and distribution network of the city of Sopron (Hungary) is presented which is sufficiently small to track the (pseudo) state space and approach related quantities.Keywords dynamic programming · combinatorial operational optimization · water distribution systems AcknowledgementThe presented work has been carried out within Project OPUS (Project ID: 138349) funded by the Academy of Finland.This work was partially supported by the scientific program of the "Development of quality-oriented and harmonized R+D+I strategy and functional model at BME" project, New Hungary Development Plan (Project ID: TÁMOP-4.2.1/B-09/1/KMR-2010-0002).The authors would like to express their gratitude to Enso Ikonen, László Kullmann and Csaba Hős for the personal communication. József Gergely Bene

show abstract

Multireservoir Modeling with Dynamic Programming and Neural Networks

Cited by 105 publications

References 18 publications

Cascade Reservoir Optimal Operation Based On Chaotic Particle Swarm Optimization

Cascade Reservoir Optimal Operation Based On Chaotic Particle Swarm Optimization

Simulation of Reservoir Sediment Flushing of the Three Gorges Reservoir Using an Artificial Neural Network

Water network operational optimization: Utilizing symmetries in combinatorial problems by dynamic programming

Contact Info

Product

Resources

About