SOLVING BANDWIDTH AND PRIORITY DOMINATION PROBLEMS OF DQDB MANS

The Bandwidth Domination Problem (BDP) in the Distributed Queue Dual B us (DQDB) Medium Access Control (MAC) protocol is the problem where th e network bandwidth may be dominated by a single node when it is activ e early and other nodes having heavy-traffic demands are active later. The Priority Domination Problem (PDP) is the problem where the networ k bandwidth may be dominated by an upstream node with a lower priority when it is active early, and other nodes with higher priorities are a ctive later. To solve the BDP means providing a mechanism such that th e bandwidth can be shared (balanced) quickly among all active nodes. T o solve the PDP means providing a mechanism such that the nodes with t he highest priority can capture all the bandwidth. In this paper, we p ropose two adaptive algorithms to solve both the BDP and PDP. The firs t is based on the gradient and the second on the proportional approach . The proposed adaptive algorithms are evaluated by simulation. From t he simulation results, we found that both the proposed adaptive algori thms have a much faster speed to balance the bandwidth than that of th e standard bandwidth balancing mechanism in the BDP. Moreover, in the PDP, the nodes with the highest priority can use all the bandwidth and the bandwidth can be balanced among these nodes quickly.