Inferring operating rules for reservoir operations using fuzzy regression and ANFIS

Mousavi, S. Jamshid; Ponnambalam, K.; Karray, Fakhri

doi:10.1016/j.fss.2006.10.024

Cited by 97 publications

(53 citation statements)

References 26 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A otimização estocástica implícita emprega um modelo de otimização determinística para operar o reservatório sob vários cenários de afluências igualmente prováveis e, em seguida, examina o conjunto resultante de dados operacionais ótimos a fim de estabelecer as curvas-guia [10], [11], [12], [13], [14], [15], [16]. Os cenários de afluência podem ser selecionados a partir dos registros históricos (quando a série é suficientemente longa), mas são geralmente obtidos por modelos de geração de vazões sintéticas.…”

Section: A Otimização Estocástica Implícitaunclassified

Operational Rule Curves of a Reservoir in Sergipe Derived by Implicit Stochastic Optimization and Nonlinear Regression

Santos

Celeste

2016

Sci. cum Ind.

View full text Add to dashboard Cite

ResumoEste artigo apresenta o desenvolvimento e aplicação de curvas-guia operacionais de reservatórios de abastecimento, usando como estudo de caso a barragem do rio Poxim, em Sergipe, por meio da metodologia de otimização estocástica implícita suportada por análises de regressão (OEI-REG). O desempenho da OEI-REG é comparado com os da política de operação padrão de reservatórios (SOP: standard operating policy), da otimização determinística perante previsão perfeita de afluências futuras (ODPP) e da programação dinâmica estocástica (PDE). A princípio, são empregados cem cenários de cem anos de vazões mensais para a calibração do modelo. Posteriormente, lança-se mão de cem novas séries de afluências visando a validação dos quatro procedimentos estudados. Os resultados indicam a viabilidade da utilização da OEI, tendo em vista sua menor vulnerabilidade em relação à SOP, assim como a proximidade de suas operações com as da ODPP. Comparando-se a OEI-REG com a PDE, percebe-se a curta distância entre os valores advindos de ambas, inclusive operações menos vulneráveis por meio da OEI-REG, justificando a adoção desta, por sua matemática simplificada em comparação com a PDE. Palavras-chaveOtimização Estocástica; Operação de Reservatórios; Curvas-guia; Regressão. Operational Rule Curves of a Reservoir in Sergipe Derived by Implicit Stochastic Optimization and Nonlinear RegressionAbstract This paper presents the development and application of operational rule curves for water supply reservoirs, using as a case study the Poxim river dam, Sergipe, by means of implicit stochastic optimization supported by regression analysis (ISO-REG). The performance of ISO-REG is compared with those of the standard reservoir operating policy (SOP), perfect-forecast deterministic optimization (PFDO) and stochastic dynamic programming (SDP). At first, a hundred 100-year monthly inflow scenarios are used for the model calibration. Later, a hundred new inflow series are applied for validation of the four procedures. The results indicate the feasibility of using ISO in view of its less vulnerability when compared to the SOP as well as the proximity of its operations with those from the PFDO. The comparison of ISO-REG with SDP shows small differences between both, including less vulnerable operations by ISO-REG, justifying its adoption for its simplified mathematics as compared to SDP. zado por altas taxas de evaporação, variação espacial e temporal das chuvas, além de baixas intensidades pluviométricas, o que, por sua vez, provocam transtornos sociais, econômicos e ambientais. Deste modo, percebe-se a necessidade da adoção, por parte dos gestores de recursos hídricos, de políticas sustentáveis para a operação das obras hidráulicas existentes, particularmente dos reservatório de abastecimento, visando a racionalização dos insumos disponíveis, tendo em vista a impossibilidade de efetiva interferência nas condicionantes impostas pela natureza. KeywordsA operação de reservatórios de abastecimento é geralmente norteada pelas chamadas curvas-guia, as...

show abstract

Section: A Otimização Estocástica Implícitaunclassified

Operational Rule Curves of a Reservoir in Sergipe Derived by Implicit Stochastic Optimization and Nonlinear Regression

Santos

Celeste

2016

Sci. cum Ind.

View full text Add to dashboard Cite

show abstract

“…The best ANFIS model is selected using the fuzzy logic toolbox in MATLAB software version 2008 [48], based on a lower RMSE for both the training and the verifying data sets, in which the RMSE is under control and is not increasing [49,50].…”

Section: Layer 1: Input Node Layermentioning

confidence: 99%

Modelling Production Uncertainties Using the Adaptive Neuro-Fuzzy Inference System

Azizi

Ali

Ping

2015

The South African Journal of Industrial Engineering

View full text Add to dashboard Cite

Production throughput measures the performance and behaviour of a production system. Production throughput modelling is complex because of uncertainties in the production line. This study examined the potential application of the adaptive neuro-fuzzy inference system (ANFIS) to modelling the throughput of production under five significant production uncertainties: scrap, setup time, break time, demand, and lead time of manufacturing. The effects of these uncertainties on the production of floor tiles were studied by performing 104 observations on the production uncertainties over 104 weeks, based on a weekly production plan in a tile manufacturing industry. The results of the ANFIS model were compared with the multiple linear regression (MLR) model. The results showed that the ANFIS model was capable of forecasting production throughput under uncertainty with higher accuracy than was the MLR model, indicated by an R-squared of 98 per cent. OPSOMMINGProduksie deurset meet die vertoning en gedrag van 'n produksiesisteem. Produksie deurset modellering is ingewikkeld as gevolg van die onsekerhede in die produksielyn. Hierdie studie ondersoek die toepassing van die aanpasbare neuro-wasige afleidingsisteem om die deurset van produksie onderhewe aan vyf noemenswaardige produksie onsekerhede, naamlik skroot, opstel tyd, breek tyd, aanvraag en die vervaardiging leityd. Die effek van hierdie onsekerhede op die vervaardiging van vloerteëls is ondersoek deur 104 weeklikse observasies op die produksie onsekerhede oor 'n tydperk van 104 weke te neem. Die resultate van die model is vergelyk met 'n meervoudige lineêre regressie model. Die resultate toon dat die aanpasbare neuro-wasige afleidingsisteem in staat was om produksie deurset onderhewe aan onsekerheid te voorspel met 'n hoër akkuraatheid as die meervoudige lineêre regressie model. Dit word aangedui met 'n bepaalheidskoëffisient van 98 persent.

show abstract

“…This implies that in order for GHMs to function properly, the effects of reservoirs have to be incorporated. Nazemi and Wheater (2015) review the algorithms currently used in GHMs to deal with reservoirs and conclude that large uncertainties remain and there is room for improvement, possibly by representing reservoir operations through rule-based models.…”

Section: Introductionmentioning

confidence: 99%

“…This study proposes a method to link this information to their decisions. Fuzzy logic, as introduced by Zadeh (1965), is a popular method to model decision-making processes that found its way into reservoir management optimization models nearly two decades ago (Macian-Sorribes and Pulido-Velazquez, 2016;Russell and Campbell, 1996;Panigrahi and Mujumdar, 2000;Shrestha et al, 1996;Chang, 2006, 2001;Mousavi et al, 2007). Fuzzy logic has not been used within the field of reservoir release and storage modelling.…”

Section: Introductionmentioning

confidence: 99%

Deduction of reservoir operating rules for application in global hydrological models

Coerver

Rutten

Giesen

2018

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. A big challenge in constructing global hydrological models is the inclusion of anthropogenic impacts on the water cycle, such as caused by dams. Dam operators make decisions based on experience and often uncertain information. In this study information generally available to dam operators, like inflow into the reservoir and storage levels, was used to derive fuzzy rules describing the way a reservoir is operated. Using an artificial neural network capable of mimicking fuzzy logic, called the ANFIS adaptive-network-based fuzzy inference system, fuzzy rules linking inflow and storage with reservoir release were determined for 11 reservoirs in central Asia, the US and Vietnam. By varying the input variables of the neural network, different configurations of fuzzy rules were created and tested. It was found that the release from relatively large reservoirs was significantly dependent on information concerning recent storage levels, while release from smaller reservoirs was more dependent on reservoir inflows. Subsequently, the derived rules were used to simulate reservoir release with an average Nash-Sutcliffe coefficient of 0.81.

show abstract

Inferring operating rules for reservoir operations using fuzzy regression and ANFIS

Cited by 97 publications

References 26 publications

Operational Rule Curves of a Reservoir in Sergipe Derived by Implicit Stochastic Optimization and Nonlinear Regression

Operational Rule Curves of a Reservoir in Sergipe Derived by Implicit Stochastic Optimization and Nonlinear Regression

Modelling Production Uncertainties Using the Adaptive Neuro-Fuzzy Inference System

Deduction of reservoir operating rules for application in global hydrological models

Contact Info

Product

Resources

About