People Publications Projects

Back to APM Home

APM Project Description

To improve the efficiency of resource utilization and scheduling of scientific data transfers on high-speed networks, we started a project on Advanced Performance Modeling with combined passive and active monitoring (APM) that investigates and models a general-purpose, reusable and expandable network performance estimation framework. The predictive estimation model and the framework will be helpful in optimizing the performance and utilization of fast networks as well as sharing resources with predictable performance for scientific collaborations, especially in data intensive applications. Our prediction model utilizes a combination of passive historical network performance information from various network activity logs as well as active measurements from network monitoring devices. The prediction model estimates future network usage and the latency in using the network. Historical network performance information is used for throughput prediction without putting extra load on the resources by active measurement collection. For a simple analogy, highway vehicle traffic pattern analysis would give drivers time estimation for travel planning (e.g. it takes roughly about 1.5 hours from Berkeley to San Francisco Airport on Monday morning 8:30am, or about 40 minutes around 1pm). Performance measurements collected by active probing is used judiciously for improving the accuracy of predictions. The planned hybrid estimation model with both passive and active measurements will improve the accuracy in performance estimation for newly added data service nodes on high throughput networks.

To implement this project, we need to address the following challenges:

This research explores fundamental questions on the relationship between monitoring and estimation of network resource performance.