Continuous-time Hidden Markov models in Network Simulation

The use of continuous-time hidden Markov models for network protocol and application performance evaluation has been validated to simulate network environments. In this paper, we develop a better algorithm to infer the continuous-time hidden Markov model from a series of end-to-end delay and loss observation of probing packets. We prove the algorithm´s feasibility by theory deduction and realize numerable validation by comparing the probability of the observed sequence produced by the model inferred by different methods. The algorithm complexity is lower.