This study proposes an integrated approach to developing a Microservice, Cloud Computing, and Software as a Service (SaaS)-based Real-Time Storm Sewer Simulation System (MBSS). The MBSS combined the Storm Water Management Model (SWMM) microservice running on the EC2 Amazon Web Services (AWS) cloud platform and an Internet of Things (IoT) monitoring device to prevent disasters in smart cities. The Python language and Docker container were used to develop the MBSS and Web API of the SWMM microservice. The IoT comprised a pressure water level meter, an Arduino, and a Raspberry Pi. After laboratory channel testing, the simulated and IoT-monitored water levels under different flow rates indicate that the simulated water level in MBSS was such as that monitored by the IoT. These findings suggest that MBSS is feasible and can be further used as a reference for smart urban early warning systems. The MBSS can be applied in on-site stormwater sewers during heavy rain, with the goal of issuing early warnings and reducing disaster damage. The use case can be the process by which the SWMM model parameters will be optimized based on the water level data from IoT monitoring devices in stormwater sewer systems. The predicted rainfall will then be used by the SWMM microservices of MBSS to simulate the water levels at all manholes. The status of the water levels will finally be applied to early warning.

This paper presents an integrated modeling approach that combines the legacy urban runoff and the legacy storm sewer models with data exchange at runtime to simulate sewer flows with real-time rainfalls. A software system called IRES has been developed to demonstrate the proposed approach. IRES uses the RUNOFF and the EXTRAN block of Storm Water Management Model (SWMM) as the legacy urban runoff and storm sewer models, respectively. This study uses the Open Modeling Interface and Environment (OpenMI) framework, which is the standard interface for model integration, as the platform for dynamic data exchange in IRES. The Jhong-Kang drainage system located in Taipei, Taiwan, is taken as the case study to verify the proposed approach. Simulated results show that IRES is valid, and the proposed approach can be successfully applied to legacy model integration with dynamic data exchange.

The effects of typhoon rainfall cannot be easily investigated to downscale the GCMs (general circulation models) data, because typhoons are short-term highly nonlinear processes. In this study, to explore the impact on the typhoon rainfall for downscaling models, the monthly rainfalls are divided into typhoon rainfall and non-typhoon rainfall. The GA-RBFN downscaling models, integrating genetic algorithm to optimize a radial basis function neural network, were established to enquire into the future rainfall under the effect of typhoons in Taichung and Hualien, Taiwan. The GCM data in this study included MRI-CGCM3 and CSIRO-Mk3.0 from the 5th Assessment Report of the Intergovernmental Panel on Climate Change. The historical monthly rainfall of Taichung and Hualien stations are collected from the Central Weather Bureau, Taiwan, and the best track of typhoons from the Joint Typhoon Warning Center. Principal component analysis (PCA) and the stepwise regression procedure (SRP) were adopted, respectively, to select input variables from the GCM data. The future rainfall trends and uncertainties are evaluated by the best GA-RBFN model, which is selected with the highest performance by applying holistic information criteria. The simulated results show that the model with variables transformed by PCA performs well in forecasting non-typhoon rainfalls, while the model with variables transformed by SRP performs well in forecasting monthly total rainfalls. According to the three classifications of future rainfalls in wet and dry seasons, the mid- and long-term rainfall amount are mainly low to normal for Taichung and normal to high for Hualien. For the long-term rainfall assessment and the probability analysis on exceeding historical rainfalls, the long-term rainfall variability of the two stations is higher than the mid-term rainfall variability. It demonstrates that the future rainfall estimation has high uncertainty under the force of typhoons. Finally, the rainfall variability in the dry period is higher than that in the wet season, and the average probability of the future dry season rainfalls exceeding historical rainfall is high.