Superior-Teaching-Learning Based Optimization Algorithm for Solving Unconstrained Optimization Problems

Teaching-Learning-Based Optimization (TLBO) is recently being used as a reliable, accurate and robust optimization technique for global optimization over continuous spaces. Few variants of TLBO have been proposed by researchers to improve the performance of the original TLBO algorithm. In this paper, an attempt is made to eliminate the mean from the original TLBO algorithm. The purposed algorithm is called Superior-Teaching-Learning-Based Optimization (S-TLBO), the teacher is directly interacting with each student to increase the quality of students. By inclusion of this step, the teacher directly interacts with each student, it is found that improves the convergence speed of original TLBO and also gives the better result for most of the problems with less number of iterations. The performance of proposed S-TLBO after solving numerical problems is compared with original TLBO and other evolutionary techniques. By using standard unconstrained benchmark functions, it can be revealed from the results, that the proposed approach provides superior solutions when compared with original TLBO and other evolutionary approaches, like Particle Swarm Optimization and Differential Evolution.

کلیدواژه ها:

TLBO ، S-TLBO ، PSO ، DE ، Optimization.