TDMA time slot and turn optimization with evolutionary search techniques

In this paper we present arithmetic real-coded variation operators tailored for time slot and turn optimization on TDMA-scheduled resources with evolutionary algorithms. Our operators implement an heuristic strategy to converge towards the solution space and are able to escape local minima. Furthermore, we explicitly separate the variation of the admitted loads and the turn-length in order to give the designer increased control over the optimization process. Experimental results show that our variation operators have advantages over string-coded binary variation operators which are frequently used to solve continuous optimization problems.