Research On Modification And Application Of Particle Swarm Optimization Algorithm Based On Control Methods

As a swarm intelligence algorithm, particle swarm optimization (PSO) algorithm has been one of the research hotspots in the international artificial intelligence field at present. It takes advantage of colony to find new avenue for the solution of complex problems. Therefore, to study and master the characteristics and rules of PSO is a significant task that in both theory and application areas. In addition, in view of its wide market prospect, extending its application scope in practice is also very important.This paper gives a comprehensive study on PSO from aspects of algorithm convergence analysis, algorithm modification and its application by using control methods and thoughts, and the main content is showed as follows:(1) Introduction to PSO. Firstly the basic principle and algorithm flow of PSO are illustrated in detail, followed by the discussion about the development in theory and applied research of PSO. The comparison between PSO and other evolutionary algorithms is detailed analyzed from many aspects,too.(2) Convergence analysis of PSO. This paper overviews two current theoretical studies about particle trajectories at first, and then, under the condition of pbest and gbest are random, we conduct these studies of particle trajectories by a signal flow graph and Jury's test technique. The obtained result from the analysis offers a more stringent condition on parameter selection in comparison to the existing results on stability analysis. Computer simulation of PSO further confirms better performance of the algorithm with parameters are selected in the light of the results of stability analysis.(3) PSO based on fuzzy PID controllers (fuzzy PID-PSO). With the difference model of PSO, the basic PSO can be viewed as a feedback system with two inputs and one output. Then, the fuzzy PID controller of classical control theory is incorporated into the basic PSO to construct a new PSO model with fuzzy PID controllers in this paper. Simulation results indicate the fuzzy PID-PSO can keep the tradeoff between the local exploitation and the global exploration. The result of eigenvalue analysis of Anderson system shows that the PSS with parameters optimized by fuzzy PID-PSO algorithm can effectively enhance the robustness of power system.(4) PSO based on feedback control of swarm diversity (DPSO). Swarm diversity is an important factor influencing the global convergence of PSO, therefore, this paper proposes a novel evaluation system about swarm diversity and introduces negative feedback mechanism, which develops a PSO algorithm based on feedback control of swarm diversity. Numerical experimental results show that DPSO can improve the global exploration capability significantly. A study on the high-dimensional problem-New England test power system validates effectiveness of the method.