A real-time dynamic connection admission controller based on traffic modeling, measurement, and fuzzy logic control

Broad-band networks based on asynchronous transfer mode (ATM) have to suppo rt traffic with widely different traffic characteristics and quality of ser ,ice requirement. In this paper, we extend our earlier work in and develop a dynamic connection admission controller (CAC) that supports cell loss req uirements. The CAC algorithm explicitly computes the equivalent bandwidth r equired to support each class of connections based on on-line observations of aggregate traffic statistics as well as the declared pararameters. We us e Gaussian and diffusion approximations to characterize the aggregate traff ic stream, and use fuzzy control strategy to combine model and measurement results to derive simple closed-form formulas to estimate the equivalent ba ndwidth in real time. We validate the proposed algorithms for various varia ble bit-rate traffic profiles and show that the system utilization can be s ubstantially improved by appropriately tuning the fuzzy logic controller to combine traffic characteristics deduced from the declared pararameters and traffic measurements.