New Approach for Solving The Clustered Shortest-Path Tree Problem Based on Reducing The Search Space of Evolutionary Algorithm

TL;DR

This paper introduces a novel method that decomposes the Clustered Shortest-Path Tree Problem into two sub-problems, reducing search space with a new evolutionary algorithm and Dijkstra's algorithm, leading to more efficient near-optimal solutions.

Contribution

It proposes a problem decomposition approach and a new evolutionary algorithm to improve efficiency in solving the NP-hard CluSTP.

Findings

The method is more efficient than existing approaches.

It achieves solutions close to the optimal.

Experimental results validate the effectiveness of the approach.

Abstract

Along with the development of manufacture and services, the problem of distribution network optimization has been growing in importance, thus receiving much attention from the research community. One of the most recently introduced network optimization problems is the Clustered Shortest-Path Tree Problem (CluSTP). Since the problem is NP-Hard, recent approaches often prefer to use approximation algorithms to solve it, several of which used Evolutionary Algorithms (EAs) and have been proven to be effective. However, most of the prior studies directly applied EAs to the whole CluSTP problem, which leads to a great amount of resource consumption, especially when the problem size is large. To overcome these limitations, this paper suggests a method for reducing the search space of the EAs applied to CluSTP by decomposing the original problem into two sub-problems, the solution to one of which is found by an EAs and that to the other is found by another method. The goal of the first sub-problem is to determine a spanning tree which connects among the clusters, while the goal of the second sub-problem is to determine the best spanning tree for each cluster. In addition, this paper proposes a new EAs, which can be applied to solve the first sub-problem and suggests using the Dijkstra's algorithm to solve the second sub-problem. The proposed approach is comprehensively experimented and compared with existing methods. Experimental results prove that our method is more efficient and more importantly, it can obtain results which are close to the optimal results.