Robust stochastic moment control via genetic-pole placement in communication network parameter setting

In this paper, the problems of stochastic robust approximate covariance assignment and robust covariance feedback stabilization, which are applied to variable parameters of additive increase/multiplicative decrease (AIMD) networks, are considered. The main idea of the developed algorithm is to use the parameter settings of an AIMD network congestion control scheme, where parameters may assign the desired network’s window covariance, with respect to the current network conditions. The aim is to search for the optimal AIMD parameters of a feedback gain matrix such that the objective functions defined via appropriate robustness measures and covariance assignment constraints can be optimized using an adaptive genetic algorithm (AGA). It is shown that the results can be used to develop tools for analyzing the behavior of AIMD communication networks. Quality of service (QoS) and other performance measures of the network have been improved by using the proposed congestion control. The accuracy of the controller is demonstrated by using MATLAB and NS software programs.