Determining pump operations using particle swarm optimization

This paper describes the use of Particle Swarm Optimization (PSO) for optimizing pump operations in water distribution systems. Here, the decisions are pump speeds for variable frequency drive (VFD) pumps. The objective is to minimize the energy costs while maintaining pressure heads and tank levels within acceptable bounds. The pressure bounds may be set such that leakage losses will be reduced. Alternatively, target pressure heads may be defined and the objective would become to minimize deviations from those targets. PSO is a stochastic optimization methodology along the lines of evolutionary techniques and based upon the concept of simulating social behavior. Unlike genetic algorithms, PSO considers continuous variables. Solutions computed by PSO are derived from both local and global searches. This allows PSO to consider solutions near the vicinity (local) of the starting point, in addition to a possible solution located within a global region. The search process for new point(s) includes consideration of the pervious best solutions. Thus, results have shown that this method converges to global optimal solutions. Copyright ASCE 2004.