Comparing several heuristics for a packing problem

TL;DR

This paper compares the effectiveness of a greedy algorithm and a hybrid genetic algorithm in solving a two-dimensional bin packing problem without item rotation, aiming to identify which approach performs better across various data sizes.

Contribution

The study provides a comparative analysis of two heuristics, a greedy algorithm and a hybrid genetic algorithm, for a specific NP-hard packing problem.

Findings

Hybrid genetic algorithm outperforms greedy in larger datasets.

Greedy algorithm is faster but less optimal.

Results vary depending on data size.

Abstract

Packing problems are in general NP-hard, even for simple cases. Since now there are no highly efficient algorithms available for solving packing problems. The two-dimensional bin packing problem is about packing all given rectangular items, into a minimum size rectangular bin, without overlapping. The restriction is that the items cannot be rotated. The current paper is comparing a greedy algorithm with a hybrid genetic algorithm in order to see which technique is better for the given problem. The algorithms are tested on different sizes data.