The effect of benchmark data characteristics during empirical strip packing heuristic performance evaluation

Abstract

In this paper, we consider the two-dimensional strip packing problem in which a fixed set of items has to be packed into a single object of unlimited height with the aim of minimising the packing height. A new, systematic way of comparing the relative performances of packing algorithms is proposed. A large set of strip packing benchmark instances from various repositories in the literature is clustered into different classes of test problems based on their underlying features. We compare a representative sample of existing strip packing heuristics in terms of solution quality in respect of the clustered data. The effectiveness of the designs of the different algorithms is contrasted for each of the data categories. It is found that the aspects of the test problems affect the solution qualities and relative rankings achieved by the various packing algorithms, but that no single heuristic is superior in respect of all the data categories.