Particle swarm optimisation in nonlinear model predictive control; comprehensive simulation study for two selected problems
Joanna Ziętkiewicz, Piotr Kozierski, Wojciech Giernacki
Abstract
Direct model predictive control applications for nonlinear systems can result in non-convex minimisation problems, which is additionally complicated if systems are non-minimum phase. In this paper, the Particle Swarm Optimisation (PSO) is applied for these global minimisation problems and tested on two selected nonlinear systems. Obtained results show that, in comparison to the sequential quadratic programming method, PSO is less vulnerable to local minima, and, with appropriate parameters, provides superior quality in nonlinear predictive control. The main results concerning PSO application show that the higher number of particles, comparing to the number of iterations, provides improved accuracy with limited computational burden; this way up to 5% reduction of a proposed quality index is obtained preserving unchanged time of calculations. The performance is also boosted when after several iterations of the algorithm greater emphasis is put on the local search, which is achieved by appropriate learning factors and inertia weight.