A self-adaptive chaos and Kalman filter-based particle swarm optimization for economic dispatch problem

It is challenging to obtain global minima for practical economic dispatch (ED) problem with heavy constraints. Traditional PSO is easy to fall into local optimum when it is applied to solve the ED problem; therefore, in this paper, an efficient self-adaptive chaos and Kalman filter-based particle swarm optimization algorithm (SCKF-PSO) is proposed to solve economic dispatch (ED) problem while considering minimizing the cost with various equality and inequality constraints. The algorithm adopts both the learning mechanism of PSO and the estimation strategy of Kalman filter to update the position of the particle, which can improve the convergence performance. Moreover, a novel self-adaptive chaotic strategy is utilized to increase the diversity of the population. The feasibility of SCKF-PSO algorithm is illustrated by testing on several benchmark functions and three different ED problems in power systems. The simulation results show that compared with previous approaches reported in the literature, the proposed SCKF-PSO can obtain higher quality solutions with stability and efficiency in the ED problem.