دانلود رایگان مقاله رویکرد باندهای بولینگر بر ترقی الگوریتم کلونی زنبور عسل و انواع آن

Abstract

In this study, a new algorithm that will improve the performance and the solution quality of the ABC (artificial bee colony) algorithm, a swarm intelligence based optimization algorithm is proposed. ABC updates one parameter of the individuals before the fitness evaluation. Bollinger bands is a powerful statistical indicator which is used to predict future stock price trends. By the proposed method an additional update equation for all ABC-based optimization algorithms is developed to speed up the convergence utilizing the statistical power of the Bollinger bands. The proposed algorithm was tested against classical ABC algorithm and recent ABC variants. The results of the proposed method show better performance in comparison with ABC-based algorithm with one parameter update in convergence speed and solution quality.

6. Results and discussion ABC methods and variants update each solution that represented by employed bees by changing one parameter each time. The proposed method adds an additional update rule and does not change the original update rule. The proposed approach shows the best performance on classical ABC and the worst performance on ABCVSS but it is still good on the best and the worst values of both ABC and ABCVSS. Standard GABC has smaller standard deviation results, so the algorithm is more robust than BB version. Best values found for BB versions of ABC, GABC and ABC/Best/1 increase bydimensionality.Namely,inahighdimensionalproblem, BB versions of the methods perform better than standard versions. Statistically significant better mean values are increased by dimensionality in GAB BB and ABC/best/1 BB. Standard derivation is better for BB versions of ABC, ABC/Best/1 and ABC/Best/2. Standard version of GABC has smaller standard deviation values, so it is more robust than BB version. ABCVSS has similar standard deviation values for both versions. All convergence graphics show that adding additional BB update rule improves the convergence performance of all methods.