• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.461-466
• /
• 1993

This paper focuses on development and implementation of a performance management algorithm for IEEE802.4 token bus networks to serve large-sale integrated systems. The delivery of time critical messages within delay constraints is an important criterion in the design and management of computer communication networks. In order to achieve this goal, the theory of fuzzy sets has been employed to imitate human's reasoning. The Fuzzy Network Performance Manager(FNPM) is composed of two parts: FNPM1 & FNPM2. FNPM1 is solily intended to satisfy the data latencyfor the highest priority while the other part is trying to satisfy those for the lower priorities. The FNPM requires average data latency, throughput, and token circulation time for its inputs. The efficacy of the FNPM has been evaluated by a series of simulation experiments.

• International Journal of Precision Engineering and Manufacturing
• /
• v.1 no.2
• /
• pp.5-13
• /
• 2000

Most networks for automation are tuned to an expected traffic condition ar their design stage. During their actual operations, however, the networks experience considerable changes in traffic from time to time. These traffic changes caused by common events like machine failure and production schedule change may adversely affect th network performance and, in turn , the performance of the connected devices. This paper presents experimental results for performance management of a Profibus-FMS network. The performance management aims to maintain a uniform level of network performance at all stations under changing network traffic. The performance management algorithm monitors the performance of individual network stations and commands the stations to change their timer values in order to have comparable performance at all stations. In order to determine the amount of timer change, the algorithm employs a set of fuzzy rules. The algorithm has been evaluated on a Profibus network.