科研之友
微信
新浪微博
Facebook
分享链接
摘要
Evolutionary Algorithms (EA) are robust optimization approaches which have been successfully applied to a wide range of problems. However, these well-established metaheuristic strategies are computationally expensive because of their slow convergence rate. Opposition Based Learning (OBL) theory has managed to alleviate this problem to some extent. Through simultaneous consideration of estimates and counter estimates of a candidate solution within a definite search space, better approximation of the candidate solution can be achieved. Although it addresses the slow convergence rate to some extent, it is far from alleviating it completely. The present work proposes a novel approach towards improving the performance of OBL theory by allowing the exploration of a larger search space when computing the candidate solution. Instead of considering all the components of the candidate solution simultaneously, the proposed method considers each of component individually and attempts to find the best possible combination by using a metaheuristic technique. In the present work, this improved Opposition learning theory has been integrated with the classical HS algorithm, to accelerate its convergence rate. A comparative analysis of the proposed method against classical Opposition Based Learning has been performed on a comprehensive set of benchmark functions to prove its superior performance.
- 出版日期2017
