A VLSI FUZZY EXPERT-SYSTEM FOR REAL-TIME TRAFFIC CONTROL IN ATM NETWORKS

Fuzzy expert systems are becoming more and more widespread in the fiel d of real-time control in various applications thanks to the potential offered by fuzzy logic and the possibility of implementation using ve ry large scale integration (VLSI) technology, In this paper, we deal w ith a fuzzy logic-based system which has been purposely designed to ac hieve real-time traffic control in high-speed networks using the async hronous transfer mode (ATM) technique, In this kind of network, one of the most critical functions is ''policing,'' which has the task of en suring that each user source complies with the traffic parameters nego tiated in the call setup to avoid network congestion. This function is difficult to implement on account of certain conflicting requirements such as selectivity and responsiveness, This is confirmed by the seve re limits affecting the most popular mechanisms proposed so far, based on conventional logic. The capacity to formalize approximate reasonin g processes offered by fuzzy logic is exploited to derive rules of beh avior for a policer starting from the know-how of an expert in the fie ld, In the paper, we address two key issues related to the implementat ion of the fuzzy policer, The first focuses on the possibility of hard ware implementation of the mechanism using VLSI technology; we present the design of a VLSI fuzzy processor which exhibits a level of perfor mance of over three mega fuzzy logic inferences per second (MFLIPS), T he second issue concerns the suitability of applying the fuzzy policer to the policing of several classes of sources to reach high levels of cost effectiveness and scalability, As the results presented in the p aper show, both these aims are reached.