NC-MOPSO: Network centrality guided multi-objective particle swarm optimization for transport optimization on networks

TL;DR

This paper introduces NC-MOPSO, a multi-objective particle swarm optimization algorithm guided by network centrality, to optimize transport networks by improving capacity and efficiency, demonstrating superior performance over existing methods.

Contribution

The paper proposes a novel MOEA based on PSO that incorporates network centrality for better initialization and local search, advancing transport network optimization techniques.

Findings

NC-MOPSO outperforms four state-of-the-art algorithms on multiple metrics.

The hybrid initialization and local search improve solution quality.

Simulation results on real networks validate the effectiveness of the approach.

Abstract

Transport processes are universal in real-world complex networks, such as communication and transportation networks. As the increase of the traffic in these complex networks, problems like traffic congestion and transport delay are becoming more and more serious, which call for a systematic optimization of these networks. In this paper, we formulate a multi-objective optimization problem (MOP) to deal with the enhancement of network capacity and efficiency simultaneously, by appropriately adjusting the weights of edges in networks. To solve this problem, we provide a multi-objective evolutionary algorithm (MOEA) based on particle swarm optimization (PSO), namely network centrality guided multi-objective PSO (NC-MOPSO). Specifically, in the framework of PSO, we propose a hybrid population initialization mechanism and a local search strategy by employing the network centrality theory to enhance the quality of initial solutions and strengthen the exploration of the search space, respectively. Simulation experiments performed on network models and real networks show that our algorithm has better performance than four state-of-the-art alternatives on several most-used metrics.