TY - JOUR
T1 - Conflict resolution in the multi-stakeholder stepped spillway design under uncertainty by machine learning techniques
AU - Mooselu, Mehrdad Ghorbani
AU - Nikoo, Mohammad Reza
AU - Bakhtiari, Parnian Hashempour
AU - Rayani, Nooshin Bakhtiari
AU - Izady, Azizallah
N1 - Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/10
Y1 - 2021/10
N2 - The optimal spillway design is of great significance since these structures can reduce erosion downstream of the dams. This study proposes a risk-based optimization framework for a stepped spillway to achieve an economical design scenario with the minimum loss in hydraulic performance. Accordingly, the stepped spillway was simulated in the FLOW-3D® model, and the validated model was repeatedly performed for various geometric states. The results were used to form a Multilayer Perceptron artificial neural network (MLP-ANN) surrogate model. Then, a risk-based optimization model was formed by coupling the MLP-ANN and NSGA-II. The concept of conditional value at risk (CVaR) was utilized to reduce the risk of the designed spillway malfunctions in high flood flow rates, while minimizing the construction cost and the loss in hydraulic performance. Lastly, given the conflicting objectives of stakeholders, the non-cooperative graph model for conflict resolution (GMCR) was applied to achieve a compromise on the Pareto optimal solutions. Applicability of the suggested approach in the Jarreh Dam, Iran, resulted in a practical design scenario, which simultaneously minimizes the loss in hydraulic performance and the project cost and satisfies the priorities of decision-makers.
AB - The optimal spillway design is of great significance since these structures can reduce erosion downstream of the dams. This study proposes a risk-based optimization framework for a stepped spillway to achieve an economical design scenario with the minimum loss in hydraulic performance. Accordingly, the stepped spillway was simulated in the FLOW-3D® model, and the validated model was repeatedly performed for various geometric states. The results were used to form a Multilayer Perceptron artificial neural network (MLP-ANN) surrogate model. Then, a risk-based optimization model was formed by coupling the MLP-ANN and NSGA-II. The concept of conditional value at risk (CVaR) was utilized to reduce the risk of the designed spillway malfunctions in high flood flow rates, while minimizing the construction cost and the loss in hydraulic performance. Lastly, given the conflicting objectives of stakeholders, the non-cooperative graph model for conflict resolution (GMCR) was applied to achieve a compromise on the Pareto optimal solutions. Applicability of the suggested approach in the Jarreh Dam, Iran, resulted in a practical design scenario, which simultaneously minimizes the loss in hydraulic performance and the project cost and satisfies the priorities of decision-makers.
KW - CVaR-based optimization model
KW - FLOW-3D®
KW - GMCR-plus
KW - NSGA-II
KW - Stepped spillway
UR - http://www.scopus.com/inward/record.url?scp=85111308641&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111308641&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2021.107721
DO - 10.1016/j.asoc.2021.107721
M3 - Article
AN - SCOPUS:85111308641
SN - 1568-4946
VL - 110
JO - Applied Soft Computing
JF - Applied Soft Computing
M1 - 107721
ER -