運用全域最佳訊息與活化策略改良人工蜂群演算法

A Novel Artificial Bee Colony Algorithm Using Information of The Global Best Solution and Activation Strategy

張鈞彥(Chun-Yen Chang)

指導教授 ： 李維平

中原大學/商學院/資訊管理研究所/碩士(2011年)

https://doi.org/10.6840/CYCU.2011.00176

摘要

人工蜂群演算法是 Karaboga 在 2005 年提出的一種基於群體智慧的仿生優化演算法,為 近年來較新的熱門最佳化問題求解的演算法之一。雖然有優異的求解能力,但仍有過早收斂 和可能陷入區域解等問題的改良研究空間。
本研究提出運用最佳訊息的移動與活化等策略,以針對標準版人工蜂群(ABC)演算法的 缺點進行改良。運用最佳訊息的移動策略能加快收斂速度,活化策略則能在陷入區域解時能 提供有效跳脫的方法。
實驗結果表明,本研究提出新的運用全域最佳訊息與活化策略改良人工蜂群演算法稱作 BPABC 演算法,在單峰、多峰等數種函數問題求解效能與效率上,均優於標準版人工蜂群 (ABC)演算法。

關鍵字

仿生 ； 群體智慧 ； 人工蜂群演算法

並列摘要

Artificial bee colony algorithm is invented in 2005 by the Karaboga a biological-inspired optimization algorithm based on swarm intelligence, the most popular in recent years than the best one of the new algorithm for solving problems. Although better than other algorithms for solving ability, but there is still likely to fall into premature convergence and suboptimal solutions issue.
We propose the use of information of the global best solution and activation strategy to modified the original ABC algorithm to improve the drawbacks. Use of information of the global best solution strategy can speed up the convergence, the activation strategy into a regional solution is able to provide exploration capability.
In this paper. We present an algorithm using information of the global best solution and activation strategy called the BPABC algorithm. To improve and enhance the original ABC algorithm in solving ability. The experimental results show that the new BPABC in the uni-modal, multi-modal benchmark functions on problem-solving performance are better than the original ABC algorithm.

並列關鍵字

Swarm intelligence ； Artificial bee colony algorithm ； biological-inspired

參考文獻

[42] 林豐澤, "演化式計算上篇:演化式演算法的三種理論模," 智慧科技與應用統計學報,

[43] 林豐澤, "演化式計算下篇:基因演算法以及三種應用實例," 智慧科技與應用統計學報, 2005. 3(1)

[2] B. Akay and D. Karaboga, "A modified Artificial Bee Colony algorithm for real-parameter optimization," Inf. Sci., doi:10.1016/j.ins.2010.07.015.

[3] B. Alatas, "Chaotic bee colony algorithms for global numerical optimization," Expert Syst. Appl., doi:10.1016/j.eswa.2010.02.042.

[4] B. Akay, D. Karaboga, "Artificial bee colony algorithm for large-scale problems and engineering design optimization," Journal of Intelligent Manufacturing, 2010.