Abstract:
The Particle Swarm Optimization algorithm has been empirically shown to perform well on many optimization problems. However, it may easily get trapped in a local optimum (premature convergence) when solving complex multimodal problems. In order to improve performance on complex multimodal problems by fast convergence speed and avoiding the local optima (premature convergence) have become the two most important and appealing goals in particle swarm optimization research. To achieve both goals, in this thesis a best particle mean dimension information-based particle swarm optimization algorithm is proposed. In the proposed algorithm, best particle mean dimension component term is formed by the best value of the fitness function that will be achieved by any particle mean dimension in the current iteration. Then it added to positions update equation in order to diversify the movement of particle and avoid premature convergence. Therefore, every swarm updates its position based upon cognitive, social and best particle mean dimension components information. The key aspect used here is that these parameters are no longer assumed to be accelerating components rather position components. The proposed algorithm is coded in MATLAB R2019a and five benchmark test functions which have different characteristics are optimized. In terms of quality solution, convergence speed and robustness, the experimental results show that the proposed algorithm has a superior performance compared to previously reported results of other three particle swarm optimization algorithms. This suggests that the proposed algorithm has the ability to escape local optima solutions achieving the global optimum efficiently