Real-Time Pumping Optimization of Combined Sewer Overflow Systems

Combined sewer systems play a crucial role in sustaining urban environments by managing sewer and urban runoff flows. However, because of their combined nature, during wet weather events their capacity may be surpassed and untreated water may be discharged as combined sewer overflows (CSOs). Thus, optimizing the operation of combined sewer pump stations in real-time cannot only improve energy efficiency but also minimize pollution from CSOs. This task poses a multifaceted challenge due to the computational burden of generating an optimal policy in short run times, conflicting objectives, and several uncertainty factors regarding the inflow rates from rain runoff and domestic effluents. This study introduces a real-time decision-making framework that uses threshold triggers to set pump cut-in and cut-out levels as well as pump speed. Two objectives are targeted: minimizing total overflow volume and reducing energy consumption. The results demonstrate that incorporating dynamic pump speed adjustments alongside threshold-based triggers is an effective strategy for achieving these objectives, highlighting its potential for energy-efficient and environmentally responsible pump station operation.