Learning Automata for Multimedia Traffic Control

Learning automata are used at the source nodes of a multimedia network to dynamically control the externally arriving traffic to the network. A new fixed structure learning automaton algorithm is used to control the traffic. At every network source, each different traffic type (data, voice, video, e.t.c.) is controlled by a different learning automaton. Every learning automaton makes its decisions based on information about the current performance of its associated traffic. Key-words: multimedia networks, learning automata, traffic control, traffic management, adaptive admission control, adaptive routing.