Intelligent Optimization Strategies in Uncertain and Dynamic Environments

The use of centralised, multi-threads cooperative systems, has emerged as a successful alternative to deal with static optimisation problems, avoiding the problem of selecting a particular, isolated strategy. However, when the problem to deal with becomes dynamic in some sense, the question as to whether those systems and the type of control rules employed to control the threads are useful or not remains open.

In this article, we depart from a strategy that joint uses a set of solutions and a set of simple agents, and we propose, compare and test two control rules for updating the former. The rules are a simple replacement frequency mechanism and a fuzzy set based one.
Computational experiments are performed on the moving peaks benchmark problem under different scenarios and the main conclusions are: first, the fuzzy set based rule is better than the frequency based rule and second, both rules are competitive when compared with a state-of-the-art algorithm.