A Parameter Adaptive Artificial Bee Colony Algorithm for Real-Parameter Optimization

Abstract

A new adaptive variant of Artificial Bee Colony algorithm, PAABC, is proposed to improve optimization performance and enhance the robustness of ABC algorithm by incorporating into searching strategy and updating control parameter of searching equation adaptively . The incorporation of the information is helpful to accelerate convergence while avoiding prematurity especially multimodal problem. According to the characteristic of optimization problem, the control parameter will be update adaptively. The better parameter value associated with the mean of the p% best individual will survive into the next generation. Experiment results show that PAABC is better or equal to evolutionary algorithm according to a set of basic test function and the CECâ??13 test suite.