李維平;李元傑;謝明勳;
頁: 25-43
日期: 2014/01
摘要: 人工蜂群演算法（Artificial Bee Colony）是學者Karaboga於2005年所提出之最佳化演算法，具有良好的穩定性、優秀的求解能力、控制參數少、計算簡潔及易於實現等優點，但也存在後期過早收斂、開發精度不佳等問題。因此，本研究提出一種新式的群中心改良策略，以改善人工蜂群演算法之搜尋能力。本研究以常見的六個測試函數進行實驗，從結果得知，本研究提出之群中心策略有效地加強人工蜂群演算法的搜尋能力，使其在演算法後期持續開發而不會過早收斂，在大部分測試函數上都有明顯的改善。
關鍵字: 人工蜂群演算法;最佳化演算法;演化式計算;

Enhancing Artificial Bee Colony Algorithm with Centroid Strategy

Abstract: Artificial Bee Colony algorithm (ABC) is an optimization algorithm proposed by Karaboga in 2005. This method has a good investigation capability, and it is also simple and easy to implement. Though ABC has many advantages, there are still some drawbacks, such as premature convergence and falling into local optimal solutions. In this study, we utilize the centroid strategy to enhance ABC for improving these weak points.In this research we use 6 benchmark functions to test our method and related researches. The results show that our algorithm can enhance the searching capability of ABC and it is better than the other researches in most of benchmark functions.
Keywords: Artificial Bee Colony Algorithm;Optimization Algorithm;Evolutionary Computation;

瀏覽次數: 7027     下載次數: 341

引用     導入Endnote