Matricial estimation for start times with stochastic behaivor by periodic real time tasks in a concurrent system

Using a multivariable dynamic model for describing startup times of real Time Tasks supposing the following considerations: The system is stationary, first order, with jitter and external perturbations bounded with a normal distribution without correlation that closely represent periodical behavior of real time tasks. To bear closer the task model in a concurrent system, systems internal dynamics are required, those are represented through the parameter matrix in function of output vectors in the regressive model as is for perturbations, but knowing their value is work for a multivariable estimator. Results of an example performed on a real-time platform are presented, considering periodic and concurrent tasks; an instrumental variable algorithm is used because of his good convergence time and his relatively easy implementation.