2nd International ICST Conference on Communications and Networking in China

Research Article

The Research of Load Balance Improvement in Industrial Networks

  • @INPROCEEDINGS{10.1109/CHINACOM.2007.4469323,
        author={Feng Li and Yanjun Xiao and Qizhi  Zhang},
        title={The Research of Load Balance Improvement in Industrial Networks},
        proceedings={2nd International ICST Conference on Communications and Networking in China},
        publisher={IEEE},
        proceedings_a={CHINACOM},
        year={2008},
        month={3},
        keywords={Automation  Communication industry  Communication switching  Ethernet networks  Genetic algorithms  Local area networks  Network topology  Telecommunication network reliability  Telecommunication traffic  Traffic control},
        doi={10.1109/CHINACOM.2007.4469323}
    }
    
  • Feng Li
    Yanjun Xiao
    Qizhi Zhang
    Year: 2008
    The Research of Load Balance Improvement in Industrial Networks
    CHINACOM
    IEEE
    DOI: 10.1109/CHINACOM.2007.4469323
Feng Li1,*, Yanjun Xiao2,*, Qizhi Zhang3,*
  • 1: Automation Department,Shanghai Jiao Tong University Shanghai, China 200240
  • 2: School of Mechanical Engineering, Hebei University of Technology Tianjin, China 300130
  • 3: Automation Department, Shanghai Jiao Tong University Shanghai, China 200240
*Contact email: lifeng@sjtu.edu.cn, xyj@jsmail.hebut.edu.cn, zhangqz@sjtu.edu.cn

Abstract

The network load balance problem in an industrial network is investigated and this problem is equivalent to an optimization problem: the network partition should reduce the inter-network communication time and simultaneously minimize the communication time difference over the sub-networks for the sake of real-time and reliability performance. Simultaneously the switching capability must be respected when partitioning devices into sub-networks, which sets the constraints of the network optimization problem. The genetic algorithm strategy is proposed to find near-optimal solution for the network partition problem. Then a simulation research is carried out to investigate the capability of the proposed genetic algorithm, and the simulation result shows significant improvement of the network performance after the network optimization.