Ant Colony Optimization for Dynamic Optimization Problems

This interesting talk will take place next Wednesday the 5th of December, 16:00-17:00 at P302.
Our external guest is Dr Michalis Mavrovouniotis from the University of Leicester, an specialists in evolutionary algorithms, ant colony optimization, memetic computation and dynamic optimization.

Dr Mavrovouniotis will discuss very recent advances in nature-inspired computational intelligence. These ideas have also relevant implications for optimization problems, knowledge transfer and meta-learning; thus I think may be of great interest of many students, PhD candidates and senior researchers of the three centres in our school.
Abstract: In the last decade, there is a growing interest to apply nature-inspired metaheuristics in optimization problems with dynamic environments. Usually, dynamic optimization problems (DOPs) are addressed using evolutionary algorithms. Recently, ant colony optimization (ACO) algorithms proved that they are also good methods to address DOPs.

However, conventional ACO algorithms have difficulty in addressing DOPs. This is because once the algorithm converges to a solution and a dynamic change occurs, it is difficult for the population to adapt to a new environment since high levels of pheromone will be generated to a single trail and force the ants to follow it even after a dynamic change. A good solution to address this problem is to increase the diversity of solutions via transferring knowledge from previous environments to the pheromone trails of the new environment.

Best wishes, Emili

Emili Balaguer-Ballester, PhD

School of Engineering & Computing, Bournemouth University

Center for Computational Neuroscience, University of Heidelberg