| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 495309 | Applied Soft Computing | 2015 | 8 Pages |
•A new chaotic-based bat swarm optimisation algorithm has been developed.•For devising it, different chaotic Bat strategies map functions were tested.•In the proposed chaotic BSO, the loudness is updated via multiplying a linearly decreasing function by chaotic map function.
Bat swarm optimisation (BSO) is a novel heuristic optimisation algorithm that is being used for solving different global optimisation problems. The paramount problem in BSO is that it severely suffers from premature convergence problem, that is, BSO is easily trapped in local optima. In this paper, chaotic-based strategies are incorporated into BSO to mitigate this problem. Ergodicity and non-repetitious nature of chaotic functions can diversify the bats and mitigate premature convergence problem. Eleven different chaotic map functions along with various chaotic BSO strategies are investigated experimentally and the best one is chosen as the suitable chaotic strategy for BSO. The results of applying the proposed chaotic BSO to different benchmark functions vividly show that premature convergence problem has been mitigated efficiently. Actually, chaotic-based BSO significantly outperforms conventional BSO, cuckoo search optimisation (CSO), big bang-big crunch algorithm (BBBC), gravitational search algorithm (GSA) and genetic algorithm (GA).
Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide
