New commodity representations for multicommodity network flow problems: An application to the fixed-charge network design problem

TL;DR

This paper introduces partial aggregation of commodities in multicommodity network flow problems, enabling a controllable trade-off between LP relaxation quality and solve time, improving efficiency in solving large-scale problems.

Contribution

It proposes a novel partial aggregation method that balances LP bound quality and computational efficiency, applied to multicommodity network design models.

Findings

Partial aggregation improves solve times for large-scale problems.

Trade-off between LP bound quality and model size can be effectively managed.

Partial aggregation outperforms full aggregation in computational experiments.

Abstract

When solving hard multicommodity network flow problems using an LP-based approach, the number of commodities is a driving factor in the speed at which the LP can be solved, as it is linear in the number of constraints and variables. The conventional approach to improve the solve time of the LP relaxation of a Mixed Integer Programming (MIP) model that encodes such an instance is to aggregate all commodities that have the same origin or the same destination. However, the bound of the resulting LP relaxation can significantly worsen, which tempers the efficiency of aggregating techniques. In this paper, we introduce the concept of partial aggregation of commodities that aggregates commodities over a subset of the network instead of the conventional aggregation over the entire underlying network. This offers a high level of control on the trade-off between size of the aggregated MIP model and quality of its LP bound. We apply the concept of partial aggregation to two different MIP models for the multicommodity network design problem. Our computational study on benchmark instances confirms that the trade-off between solve time and LP bound can be controlled by the level of aggregation, and that choosing a good trade-off can allow us to solve the original large-scale problems faster than without aggregation or with full aggregation.