A data-driven improved fuzzy logic control optimization-simulation tool for reducing flooding volume at downstream urban drainage systems

The uncertainty of climate change and urbanization imposed additional stress for urban drainage systems (UDSs) by intensifying rainfall frequency and magnifying peak runoff rate. UDSs are among the stormwater infrastructures that can be controlled in real-time for mitigating downstream urban flooding. In this paper, a data-driven improved real-time control optimization-simulation tool called SWMM_FLC, which is based on the FLC (fuzzy logic control) and GA (genetic algorithm), was developed for smart decision-making of flooding mitigation. A calibrated and validated SWMM model was used for applying SWMM_FLC to explore the potential in reducing downstream flooding volume at UDSs. The results show that the data-driven enhanced GA optimization significantly reduces fuzzy system deviations from 0.22 (non_optmial scenario) to 0.07 (optimal scenario). The accumulated flooding volume reduction by up to 4.55% under eight artificial rainfall scenarios discloses the possibility of adopting SWMM_FLC as appropriate software to assist decision-makers to effectively minimize urban flooding volume at downstream urban drainage systems.