One of the basic problems faced in the design of efficient traffic and congestion control schemes is related to the wide variety of services with different traffic characteristics and quality of service (QoS) requirements supported by ATM networks. The authors propose a new way of organizing the control system so that complexity is easier to manage. The multi-agent system approach, which provides the use of adaptative and intelligent agents, is investigated. The authors show, through the two congestion control schemes proposed, how to take advantage of using intelligent agents to increase the efficiency of the control scheme. First, TRAC (threshold based algorithm for control) is proposed, which is based on the use of fixed thresholds which enables the anticipation of congestion. This mechanism is compared with the push-out algorithm and it is shown that the authors' proposal improves the network performance. Also discussed is the necessity of taking into account the network dynamics. In TRAC, adaptative agents with learning capabilities are used to tune the values of the thresholds according to the status of the system. However, in this scheme, when congestion occurs, the actions we perform are independent of the nature of the traffic. Subsequently, we propose PATRAC (predictive agents in a threshold based algorithm for control) in which different actions are achieved according to the QoS requirements and to the prediction of traffic made by the agents. Specifically, re-routing is performed when congestion is heavy or is expected to be heavy and the traffic is cell loss sensitive. This re-routing has to deflect the traffic away from the congestion point. In this scheme, we propose a cooperative and predictive control scheme provided by a multi-agent system that is built in to each node.
展开▼
