A COMPARATIVE-ANALYSIS OF FUZZY VERSUS CONVENTIONAL POLICING MECHANISMS FOR ATM NETWORKS

In ATM networks, usage parameter control is required in order to ensur e that each source conforms to its negotiated parameters. To this purp ose, several policing methods, such as leaky bucket and window mechani sms, have been introduced in literature. However, traditional methods have proved to be inefficient in coping with the conflicting requireme nts of ideal policing, that is, a low false alarm probability and high responsiveness. This led us to explore alternative solutions based on artificial intelligence techniques, specifically, in the field of fuz zy systems, In this paper, we propose a policing mechanism based on fu zzy logic that aims at detecting violations of the parameters negotiat ed. The main characteristics of the proposed fuzzy policer are simplic ity and the capacity to combine a high degree of responsiveness with a selectivity close to that of an ideal policer. Moreover, it can easil y be implemented in hardware, thus, enhancing both cost and processing performance. The reported simulation results show that the performanc e of our fuzzy policer is much better than that of conventional polici ng mechanisms.