Improved Teaching-Learning-based Optimization Algorithm with Advanced Learning Strategy

As an important category of computational intelligence, meta-heuristic algorithms have always been a popular research interests over recent two decades. Teaching-learning-based optimization (TLBO) is one of nature-inspired metaheuristic algorithm which is proven to have effectiveness and efficiency in solving complex optimization problems. Although TLBO has remarkable capacity to solve different optimization problems, but the issue of trapping into local optimal is a common drawback of meta-heuristic algorithm, and TLBO is no exception. Thus we use a novel search strategy to improve the performance of TLBO by means of a new selection operation. We select twenty-nine benchmark functions of IEEE CEC2017 to testify the performance of proposed algorithm in terms of effectiveness and robustness. Experimental results exhibit that the proposed algorithm outperforms other state-of-the-art algorithms.