Balanced artificial bee colony algorithm Online publication date: Thu, 18-Apr-2013
by Jagdish Chand Bansal; Harish Sharma; Atulya Nagar; K.V. Arya
International Journal of Artificial Intelligence and Soft Computing (IJAISC), Vol. 3, No. 3, 2013
Abstract: Artificial bee colony (ABC) optimisation algorithm is relatively a recent and simple population-based probabilistic approach for global optimisation over continuous and discrete spaces. It has reportedly outperformed a few evolutionary algorithms (EAs) and other search heuristics when tested over both benchmark and real world problems. ABC, like other probabilistic optimisation algorithms, has inherent drawback of premature convergence or stagnation that leads to the loss of exploration and exploitation capability of ABC. Therefore, in order to find a trade-off between exploration and exploitation capability of ABC algorithm two modifications are proposed in this paper. First, a new control parameter namely, cognitive learning factor (CLF) is introduced in the employed bees phase and onlooker bees phase. Cognitive learning is a powerful mechanism that adjusts the current position of candidate solution by a means of some specified knowledge. Second, the range of ABC control parameter φ is modified. The proposed strategy named as balanced artificial bee colony (BABC) algorithm, balances the exploration and exploitation capability of the ABC. To prove efficiency of the algorithm, it is tested over 24 benchmark problems of different complexities and compared with the basic ABC.
Online publication date: Thu, 18-Apr-2013
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Artificial Intelligence and Soft Computing (IJAISC):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email email@example.com