Abstract: Aiming at the difficulties in modeling due to variables coupling of ultra-supercritical coal-fired power unit and defects in basic particle swarm optimization, an improved particle swarm optimization algorithm for modeling of load system is proposed. The algorithm introduces the idea of adaptive, Cauchy mutation and gradient guidance crossover, which improves the problems of particle swarm optimization algorithm being prone to premature convergence and has the poor local searching ability. By collecting the actual operation data of the power plant, using the adaptive Cauchy mutation and gradient guidance cross particle swarm optimization (GMGPSO) algorithm, the model established and validated. The simulation results show that the model output obtained by the GMGPSO algorithm has a good effect on fitting the actual data on site. The average convergence speed and the average accuracy both are improved a lot.

Key words: load system, system modeling, Cauchy mutation, gradient guidance crossover, PSO algorithm