Estimating End-to-End Performance by Collaborative Prediction with Active Sampling

— Accurately estimating end-to-end performance in distributed systems is essential both for monitoring compliance with service-level agreements (SLAs) and for performance optimization (e.g., choosing the highest-bandwidth server for a download request in a content-distribution system). Due to infeasibility of exhaustive pairwise measurements, a natural alternative is to predict unobserved end-to-end performances from available historic data, with minimal additional measurements. In this paper we present an approach to this based on Collaborative Prediction (CP), an estimation method designed to work with sparse data, that has enjoyed much success in other domains (e.g. product recommendation systems), and obviates the need for landmark nodes commonly assumed in other approaches. Specifically, we use Max-Margin Matrix Factorization (MMMF), a linear factor model for CP that has outperformed stateof-art CP techniques. Moreover, our approach readily admits active sampling based on predi...

• Type: Conference
• Year: 2007
• Where: IM
• Authors: Irina Rish, Gerald Tesauro
• Keywords: Active-sampling Cp Approach, Computer Networks, End-to-end Performances, IM 2007, Prediction