An Improved Multi-Objective Quantum-Behaved Particle Swarm Optimization for Railway Freight Transportation Routing Design

Qianqian Zhang,Daqing Gong,Shifeng Liu,Qun Tu,Hankun Zhang

doi:10.1109/access.2019.2948197

Abstract

With the development of railway transportation, the railway transportation enterprises expand their freight transportation from station-to-station transportation to door-to-door transportation, which makes the routing design more complicated. The existing classical optimization algorithms are difficult to meet the needs of practical applications. Therefore, the paper introduces an Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm (IMOQPSO). Then based on the continuous coding for the Railway Freight Transportation Routing Design, the proposed improved algorithm was applied to solve the problem to verify the performance of algorithm. Finally, the paper compared the performance of Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm with other four continuous multi-objective swarm intelligence algorithms. The results shown that the proposed algorithm obtained the best Pareto front which is closer to the real Pareto front of Railway Freight Transportation Routing Design. Hence, the proposed Improved Multi-objective Quantum-behaved Particle Swarm Optimization algorithm can provide support for the railway transport enterprises routing design decisions to some extent.

Highlights

Railway is one of the most efficient and environmentalfriendly way for transportation industry in China [1]
From the Pareto front convergence of the continuous swarm intelligent algorithms in the railway freight transportation routing design (RFTRD), it can be seen that the Improved Multi-objective Quantumbehaved Particle Swarm Optimization algorithm (IMOQPSO) algorithm, obtains better Pareto front convergence than other algorithms
From the population entropy of the continuous swarm intelligence in 30 independent experiment for the RFTRD example, it can be seen that as the number of iterations increases, the population diversity of the IMOQPSO algorithm decreases, which shows that the algorithm has better convergence in the process of optimization

Summary

Introduction

Railway is one of the most efficient and environmentalfriendly way for transportation industry in China [1]. In the process of the continuous growth of other modes of transportation and the increasing market competitiveness, the market share of the railway freight industry has declined year by year [2]. The problems that how to optimize the organization of railway freight transportation enterprises and improve the efficiency and competitiveness of railway transportation. Railway freight door-to-door transportation is a complicated problem involves a range of issues, for example, firstly, the declining market share in freight transportation is a severe. The railway freight door-to-door transportation involving more people and property which is a new challenge for railway freight transportation routing design

Methods

Results

Conclusion