Accuracy of Simulation Models among Real Lab, LAN, WAN, and Relative Error Rate for Remote Data Transfer Performance Analysis

摘要

This paper presents a novel approach for measuring oneway delays and throughput between network nodes in a heterogeneous environment. This research investigates the performance evaluation of remote data transfers on the heterogeneous services and technologies environment. We propose an enhanced equation to evaluate the performance of network traffic management via the Little Law and queuing theory to improve the evaluation algorithm. To get accuracy results on the simulation model performance, we measure (verify and validate) data from a lab experiment. We use a network management tool to capture the data and Ping Plotter application (network analyzer) to generate traffic. As a result, this simulation model can provide a good approximation of real traffic (e.g., one-way delays, throughput) observed in real network environments such as local-area networks (LANs) and wide-area networks (WANs). Laboratory and field experiments show that the model via simulation is capable of approximating the performance of remote data transfers over heterogeneous services and techniques in a minimum error range.