Graph Partition Based Traffic Balance in Industrial Network

The traffic load balancing problem in switched industrial Ethernet is a key component of QoS performance, which is shown to be equivalent to a multi-constraint optimization problem: the network design should minimize the amount of inter-network communication time, and simultaneously balance the communication time and network size evenly over the resultant sub-networks. To solve this optimization problem, a graph partitioning strategy is proposed, which can give a good network solution by partitioning a graph- based representation of industrial network. In the experiments the network partitions obtained by graph partitioning strategy are compared with those obtained by a random partitioning method. The experimental results show the graph partitioning strategy is significantly better than those obtained by random partitioning method.

[1]  Bradford L. Chamberlain,et al.  Graph Partitioning Algorithms for Distributing Workloads of Parallel Computations , 2001 .

[2]  George Karypis,et al.  A Software Package for Partitioning Unstructured Graphs , Partitioning Meshes , and Computing Fill-Reducing Orderings of Sparse Matrices Version 5 . 0 , 1998 .

[3]  George Karypis,et al.  Scalable partitioning-driven algorithms for solving complex and emerging problems in vlsi physical design automation , 2005 .

[4]  Alejandro Quintero,et al.  Assigning cells to switches in cellular mobile networks: a comparative study , 2003, Comput. Commun..

[5]  Vipin Kumar,et al.  Multilevel Algorithms for Multi-Constraint Graph Partitioning , 1998, Proceedings of the IEEE/ACM SC98 Conference.

[6]  Youxian Sun,et al.  How to guarantee factory communication with switched Ethernet: survey of its emerging technology , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[7]  Sami Khuri,et al.  Heuristic algorithms for the terminal assignment problem , 1997, SAC '97.

[8]  Jürgen Jasperneite,et al.  Switched Ethernet for factory communication , 2001, ETFA 2001. 8th International Conference on Emerging Technologies and Factory Automation. Proceedings (Cat. No.01TH8597).

[9]  Jurgen Jasperneite,et al.  Analysis of Switched Ethernet Networks with Different Topologies Used in Automation Systems , 1999 .

[10]  Xin Yao,et al.  A hybrid Hopfield network-genetic algorithm approach for the terminal assignment problem , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Bruce Hendrickson,et al.  A Multi-Level Algorithm For Partitioning Graphs , 1995, Proceedings of the IEEE/ACM SC95 Conference.

[12]  Vipin Kumar,et al.  Analysis of Multilevel Graph Partitioning , 1995, Proceedings of the IEEE/ACM SC95 Conference.

[13]  Sadiq M. Sait,et al.  Topology design of switched enterprise networks using a fuzzy simulated evolution algorithm , 2002 .

[14]  Alejandro Quintero,et al.  Evolutionary approach to optimize the assignment of cells to switches in personal communication networks , 2003, Comput. Commun..

[15]  U. Ruckert,et al.  Measurements in switched Ethernet networks used for automation systems , 2000, 2000 IEEE International Workshop on Factory Communication Systems. Proceedings (Cat. No.00TH8531).

[16]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Juan Li,et al.  Effect of genetic algorithm parameters on PCS network planning , 2000, Proceedings 25th Annual IEEE Conference on Local Computer Networks. LCN 2000.