Minimizing pump energy in a wastewater processing plant

This paper discusses energy savings in wastewater processing plant pump operations and proposes a pump system scheduling model to generate operational schedules to reduce energy consumption. A neural network algorithm is utilized to model pump energy consumption and fluid flow rate after pumping. The scheduling model is a mixed-integer nonlinear programming problem (MINLP). As solving a data-driven MINLP is challenging, a migrated particle swarm optimization algorithm is proposed. The modeling and optimization results show that the performance of the pump system can be significantly improved based on the computed schedules. ▸ Energy minimization of pumps is studied. ▸ Pump performance is measured with two parameters. ▸ A neural network algorithm is used to develop models. ▸ Pump configuration and control parameters are optimized. ▸ A migrated particle swarm optimization algorithm solves the model.