Towards an intelligent VNS heuristic for the k-labelled spanning forest problem

TL;DR

This paper proposes an intelligent Variable Neighbourhood Search metaheuristic for solving the k-labelled spanning forest problem, combining VNS with machine learning and statistical methods to improve solution quality and automation.

Contribution

It introduces a novel hybrid metaheuristic for the kLSF problem, integrating VNS with machine learning and statistical techniques for enhanced performance.

Findings

The proposed Int-VNS achieves high-quality solutions.

The method automates the search process effectively.

It extends VNS strategies from related problems.

Abstract

In a currently ongoing project, we investigate a new possibility for solving the k-labelled spanning forest (kLSF) problem by an intelligent Variable Neighbourhood Search (Int-VNS) metaheuristic. In the kLSF problem we are given an undirected input graph G and an integer positive value k, and the aim is to find a spanning forest of G having the minimum number of connected components and the upper bound k on the number of labels to use. The problem is related to the minimum labelling spanning tree (MLST) problem, whose goal is to get the spanning tree of the input graph with the minimum number of labels, and has several applications in the real world, where one aims to ensure connectivity by means of homogeneous connections. The Int-VNS metaheuristic that we propose for the kLSF problem is derived from the promising intelligent VNS strategy recently proposed for the MLST problem, and integrates the basic VNS for the kLSF problem with other complementary approaches from machine learning, statistics and experimental algorithmics, in order to produce high-quality performance and to completely automate the resulting strategy.