Solving the Steiner Tree Problem in graphs with Variable Neighborhood Descent

TL;DR

This paper introduces a Variable Neighborhood Descent algorithm for solving the Steiner Tree Problem in graphs, incorporating new heuristics and a vertex scoring system, demonstrating promising results on benchmark instances.

Contribution

It presents a novel VND-based algorithm with new heuristics and scoring for the Steiner Tree Problem, improving solution quality and search efficiency.

Findings

Encouraging results on benchmark datasets

Effective use of heuristics and scoring system

Demonstrates potential for practical applications

Abstract

The Steiner Tree Problem (STP) in graphs is an important problem with various applications in many areas such as design of integrated circuits, evolution theory, networking, etc. In this paper, we propose an algorithm to solve the STP. The algorithm includes a reducer and a solver using Variable Neighborhood Descent (VND), interacting with each other during the search. New constructive heuristics and a vertex score system for intensification purpose are proposed. The algorithm is tested on a set of benchmarks which shows encouraging results.