Genetic algorithms for industrial ethernet network design

The Ethernet network is increasingly being used for industrial communications which are strongly time-constrained. This kind of network is intrinsically nondeterministic and does not guarantee that communication end-to-end delays will be bounded. Nevertheless, from the observed traffic between industrial devices, some network topologies improving the availability and temporal performances can be designed. This paper describes the use of a genetic algorithm approach for the optimisation and design of industrial control networks. We propose to solve the combinatorial problem which consists of finding the best distribution of industrial devices on a switched Ethernet architecture with GA techniques, so that the required quality of service is provided.