A Fast Scalable Heuristic for Bin Packing

TL;DR

This paper introduces a fast, scalable heuristic for bin packing that divides the problem into smaller sub-problems, efficiently solving them by limiting configurations, with empirical evidence supporting its effectiveness and improved analysis of hard instances.

Contribution

The paper proposes a novel heuristic that partitions bin packing into identical sub-problems and considers limited configurations, enhancing scalability and analysis of complex instances.

Findings

Supports scalability through empirical evidence

Provides tighter bounds on wastage in optimal solutions

Efficiently solves large bin packing instances

Abstract

In this paper we present a fast scalable heuristic for bin packing that partitions the given problem into identical sub-problems of constant size and solves these constant size sub-problems by considering only a constant number of bin configurations with bounded unused space. We present some empirical evidence to support the scalability of our heuristic and its tighter empirical analysis of hard instances due to improved lower bound on the necessary wastage in an optimal solution.