A Disaggregation?Emulation Approach for Optimization of Large Urban Drainage Systems
نویسندگان
چکیده
Multi-objective optimization can help identify efficient and appealing designs of urban drainage systems. However, their application to large-scale problems is hindered by the computational cost simulation. We propose a novel disaggregation approach that allows simulating portion network while remaining part represented surrogate model maps changes in region interest hydraulic head time-series at synthetic nodes shared with network. The proposed demonstrated an many-objective sustainable systems two areas. design problem's decision variables include types systems, combination within subcatchment, surface areas spatial distribution, whereas objectives minimization capital cost, flood volume, duration, total suspended solids or average peak runoff. results show disaggregation-emulation provide accurate representation system dynamics significantly reducing time compared simulates whole dynamics. Two alternative models are considered based on multilayer perceptron (MLP) generalized regression neural networks (GRNN). MLP found be more GRNN larger for training process.
منابع مشابه
Staged Optimization Design for Updating Urban Drainage Systems in a City of China
Flooding has been reported more often than in the past in most cities of China in recent years. In response, China’s State Council has urged the 36 largest cities to update the preparedness to handle the 50-year rainfall, which would be a massive project with large investments. We propose a staged optimization design for updating urban drainage that is not only a flexible option against environ...
متن کاملOptimization of thermal curing cycle for a large epoxy model
Heat generation in an exothermic reaction during the curing process and low thermal conductivity of the epoxy resin produces high peak temperature and temperature gradients which result in internal and residual stresses, especially in large epoxy samples. In this paper, an optimization algorithm was developed and applied to predict the thermal cure cycle to minimize the temperature peak and the...
متن کاملA limited memory adaptive trust-region approach for large-scale unconstrained optimization
This study concerns with a trust-region-based method for solving unconstrained optimization problems. The approach takes the advantages of the compact limited memory BFGS updating formula together with an appropriate adaptive radius strategy. In our approach, the adaptive technique leads us to decrease the number of subproblems solving, while utilizing the structure of limited memory quasi-Newt...
متن کاملProbabilistic runoff volume forecasting in risk-based optimization for RTC of urban drainage systems
متن کامل
Urban Drainage Systems: Evolution of Problems
The practice of urban drainage has been traced back to some of the earliest recorded histories of humankind. The expeditious conveyance of stormwater from urbanized areas was motivated primarily by reasons of convenience and the reduction of ̄ood damage potential. The removal of domestic wastes from households using waterborne conveyances was also found to be convenient. Such practices to improv...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Water Resources Research
سال: 2021
ISSN: ['0043-1397', '1944-7973']
DOI: https://doi.org/10.1029/2020wr029098