USING FUZZY-LOGIC IN ATM SOURCE TRAFFIC CONTROL - LESSONS AND PERSPECTIVES

Due to its capacity to capture human expertise and to formalize approx imate reasoning processes, fuzzy logic can be a good answer to the man y challenges of congestion control in ATM networks. The authors deal w ith the application of fuzzy logic to problems of usage parameter cont rol and propose a simple mechanism which, avoiding complex mathematica l calculations, guarantees low response times while remaining effectiv e. The flexibility of the fuzzy control proposed is discussed with res pect to the probability of facing various types of traffic sources, ra nging from bursty to MPEG video.