An Adaptive Multi-Population Framework for Locating and Tracking Multiple Optima
Multi-population methods are effective to solve dynamic optimization problems. However, to efficiently track multiple optima, algorithm designers need to address a key issue: how to adapt the number of populations. In this paper, an adaptive multi-population framework is proposed to address this issue. A database is designed to collect heuristic information of algorithm behavior changes. The number of populations is adjusted according to statistical information related to the current evolving status in the database and a heuristic value. Several other techniques are also introduced, including a heuristic clustering method, a population exclusion scheme, a population hibernation scheme, two movement schemes, and a peak hiding method. The particle swarm optimization and differential evolution algorithms are implemented into the framework, respectively. A set of multi-population based algorithms are chosen to compare with the proposed algorithms on the moving peaks benchmark using four different performance measures. The effect of the components of the framework is also investigated based on a set of multi-modal problems in static environments. Experimental results show that the proposed algorithms outperform the other algorithms in most scenarios.
Citation : Li, C. et al. (2015) An adaptive multi-population framework for locating and tracking multiple optima. IEEE Transactions on Evolutionary Computation, 20 (4), pp. 590-605
Research Group : Centre for Computational Intelligence
Research Institute : Institute of Artificial Intelligence (IAI)
Peer Reviewed : Yes