The Influence of Population and Memory Sizes on the Evolutionary Algorithm's Performance for Dynamic Environments



Usually, evolutionary algorithms keep the size of the population fixed. In the context of dynamic environments, many approaches divide the main population into two, one part that evolves as usual another that plays the role of memory of past good solutions. The size of these two populations is often chosen off-line. Usually memory size is chosen as a small percentage of population size, but this decision can be a strong weakness in algorithms dealing with dynamic environments.
In this work we do an experimental study about the importance of this parameter for the algorithm's performance. Results show that tuning the population and memory sizes is not an easy task and the impact of that choice on the algorithm's performance is significant. Using an algorithm that dynamically adjusts the population and memory sizes outperforms
standard approach.


Evolutionary Optimization


6th European Workshop on Evolutionary Algorithms in Stochastic and Dynamic Environments (EVOSTOC 2009), April 2009

Cited by

Year 2015 : 1 citations

 du Plessis, M. C., Engelbrecht, A. P., & Calitz, A. (2015, January). Self-Adapting the Brownian Radius in a Differential Evolution Algorithm for Dynamic Environments. In Proceedings of the 2015 ACM Conference on Foundations of Genetic Algorithms XIII (pp. 114-128). ACM.

Year 2013 : 1 citations

 Richter, H. (2013). Dynamic Fitness Landscape Analysis. In Evolutionary Computation for Dynamic Optimization Problems (pp. 269-297). Springer Berlin Heidelberg.

Year 2012 : 1 citations

 Mathys Cornelius du Plessis (2012). “Adaptive Multi-Population Diferential Evolution for Dynamic Environments”. PhD Thesis, University of Pretoria, 2012.