Adaptive ATM call access control using learning algorithms

The broadband integrated services digital network (B-ISDN) is an emerging communication network which is intended to provide multimedia services to its customers in a flexible and cost-effective manner. The traditional transport paradigm used for ISDN is synchronous transfer mode (STM). However, the asynchronous transfer mode (ATM) has attracted significant attention as a transport paradigm for B-ISDN. In comparison to STM, ATM is more flexible, and may have potential gain in bandwidth efficiency by buffering and statistically multiplexing bursty traffic at the expense of cell delay and loss. The authors concentrate on the statistical multiplexing control strategy and consider two access control strategies based on learning algorithms. They discuss the basic problem of bandwidth resource management in ATM. Two new adaptive strategies are then considered with associated simulation results and a critical discussion