ExperimentalandAnalytical.ppt

Experimental and Analytical Evaluationof Available Bandwidth Estimation Tools Outline Motivation Problem Testbed Description Analytical Model Target Tools Performance Evaluation Conclusions MotivationWhy to evaluate available bandwidth tools? ProblemWhat issues do we want to solve? Testbed DescriptionArchitecture Analytical ModelJackson Network Target ToolsEstimation Approaches Target ToolsPathload Target ToolsIGI Target ToolsSpruce Performance EvaluationExperiments Performance EvaluationAccuracy with 75% of the capacity as cross traffic Performance EvaluationRelative Error Performance EvaluationConvergence Time Performance EvaluationOverhead Conclusions Experimental and Analytical Evaluationof Available Bandwidth Estimation Tools * * * * * Cesar D. Guerrero and Miguel A. Labrador Department of Computer Science Engineering University of South Florida Available bandwidth ? to improve network applications performance. Applications ? different time, accuracy, and overhead from estimators. Evaluation ? determine whether a tool is suitable for an application. Evaluate tools over the same variable network conditions Analytical model to have a theoretical value to compare with Topology Link capacities Packet loss rate Delay Client and server hosting bandwidth estimation tools Intermediate nodes hosting a packet shaper and a traffic generator Phython applications running in all the machines to automatically perform experiments. Internet connected Low cost Eight M/M/1 queues model input and output packet flows. The Jackson model gives the average arrival rate to a node λj = γj + Σλiθij The available bandwidth is the minimum non utilized capacity of the queues associated to the links: A = mini=1,3,5,7 (Ai) = mini=1,3,5,7 (1-ρi) Client Server 1 2 3 4 5 6 7 8 Cross Traffic λ0 λ1 λ2 λ3 λ4 λ5 λ7 λ6 γ1 γ3 γ5 γ7 λ8 Probing packets Probe Rate Model Pathload. TOPP Pathchirp PTR Probe Gap Model IGI Delphy Spruce IGI Pathload Spruce Fleet of probing streams are sent t