Intelligent performance management of networks for advanced manufacturing systems

This paper focuses on performance management of communication networks serving various manufacturing systems. The performance management aims to improve the network performance in handling various types of messages by online adjustment of protocol parameters such as timers and queue capacities. The principles of fuzzy logic, genetic algorithms, and neural networks have been combined in formulating the performance management rules and fine-tuning the manager. In order to demonstrate the efficacy of this approach, a performance management procedure developed for the IEEE 802.4 protocol standard has been evaluated via discrete-event simulation.