Dynamic Vehicle Routing with Time-Linkage: From Problem States to Algorithm Performance.

Dynamic optimization problems are of significant practical relevance, but suffer from a lack of analysis. The characteristics of time-linked problems are especially difficult to capture as future problem states depend on the optimizer’s performance. By tracking numeric features along the optimization process, information about the problems characteristics can be obtained, which can then be used to analyse algorithmic performance. We demonstrate this approach on a dynamic vehicle routing problem combining domain specific and fitness landscape features that can be applied to any optimization problem.