Modeling of Dynamic Trend of Latency Variations on Mobile Network Using Markov Regime Switching

An evaluation model that simulates a realistic trend of latency variation is attracting attention for use in simulation studies on large-scale distributed services provided through mobile networks. Therefore, we propose a new modeling method using a Markov regime switching which builds the evaluation model where latency drastically changes with time as in the mobile network. Furthermore, the effectiveness of the proposed modeling method is evaluated based on the measurement result which is collected while the user of the cellular phone moves around within a wide area. The evaluation results helps us to disclose whether or not the evaluation model estimated from the proposed method can accurately estimate dynamics of the mobile network quality.