Adaptive scheduling for real-time network traffic using agent-based simulation

Since several years, communication networks have known a surprising growth. The increased number of users, the consequent increase of traffic, and the request for new services involve the development of new technologies and the deployment of high throughput networks. Networking technology has correspondingly grown to meet the diverse needs of applications and network administration. In response to the complexity of communication networks, simulation was and remains the only way to evaluate network performance. Unfortunately, traditional simulation methods are not adapted to all networks such as networks with quality of service and networks with dynamic aspect. To overcome this limitation, a new method to simulate dynamic networks based on multi-agents simulation and behavioral approach had been proposed. In this paper, we present an adaptive approach to schedule real-time network traffic using the agent based simulation concept. The paper introduces an adaptive real-time agent scheduler (ARTAS) architecture and agent model as basis for scheduling real-time packet networks.