Optimization of ATM Network Flow Control via Genetic Algorithm

摘要

This paper proposes a control-theoretic algorithm to deal with the congestion control problem which is an important issue in the ATM networks. With the aid of Smith predictor, we can overcome the effect of multiple propagation delays and ensure the stability of the feedback loop. The available ABR bandwidth left by quality of service (QoS) constrained traffic (CBR+VBR) is fully and fairly utilized in the sense of MCR plus equal share. This fairness property holds even if there are uncertainties or measurement errors of the parameters. Further, a simple optimal H_∞ controller is proposed to minimize the variance of the queue occupancy and avoid cell loss. Since no closed form solution can be found for the optimal H_∞ traffic controller, an effective genetic algorithm to find the control parameters is also proposed.