Enhancing the Convergence Speed and Accuracy of Particle Swarm Optimizers through Adaptive Learning

Particle swarm optimization (PSO) comes from a family of swarm optimization techniques that work iteratively to obtain an optimum solution for single or multi objective systems. For instance, teacher learner-based optimization (TLbO) when combined with PSO, fuses swarm intelligence behaviour with teacher-learner relationship for speeding up the learning process. However most of these algorithms do not modify the original PSO learning factors, due to which their performance is limited. In this work, a novel adaptive learning-based TLbO inspired PSO model is proposed. This model aims at improving the convergence speed and reduce solution error via adaptively learning from previous iteration error and modifying social and cognitive learning behaviour of the underlying PSO. The proposed model is 20% more efficient in terms of convergence delay, and 25% efficient in terms of final solution error when compared with existing highly efficient TLbO-PSO models.