Management of Distributed Generation Units under Stochastic Load Demands using Particle Swarm Optimization

This paper presents a particle swarm optimization (PSO) approach to optimize the daily electricity and heat generation in proton exchange membrane (PEM) fuel cells for residential applications under electrical demand uncertainties. The stochastic load processes are modelled as scenario trees using adaptive PSO. The resulting multistage nonlinear stochastic cost model aims to minimize the average operating costs over this scenario tree. Adaptive PSO is used to solve this model and the results are compared with the deterministic model.