Proceedings of the 2014 ACM SIGCOMM workshop on Capacity sharing workshop

Abstract

Welcome to the Capacity Sharing Workshop (CSWS) at ACM SIGCOMM 2014. Today's Internet traffic consists of a wide variety of application and services that have very different requirements on the Quality of Service (QoS) the network should provide. The continuously growing demand for bandwidth (massive growth of mobile network user population and increasing data rates) and the fast increasing deployment of virtualization (in data centers, mobile core network, access networks) make effective and efficient capacity sharing a key element for managing cost as well of quality of experience for users. The objective of CSWS is to provide a forum for exchanging recent research results and new ideas addressing these issues -- focusing on two research areas: (Per-user) fair and (economically) efficient capacity sharing including generalization of data center techniques to Internet; and Support of application requirements, especially low latency, and measurements/measurement techniques for assessing the current Qos/QoE in the Internet. CSWS-2014 provides a forum for sharing research and experimentation results from a number of current (sub-)activities in the area of capacity sharing. This includes the bufferbloat initiative (aiming at reducing excessive delay caused by over-dimensioned and badly managed buffers in network equipment), new work on active queue management (such as CoDel and PIE), new approaches to better expose, respond to and police congestion (Congestion Exposure, MPTCP, Data Center TCP), and congestion control/mitigation for real-time media streams (IETF RMCAT). With the help of an excellent technical program committee of 39 international researchers, we finally selected 9 interesting papers for the workshop program that, as we believe, not only address important current research topics in the fields but are also suitable to create interesting and fruitful discussions at the workshop. Moreover, the workshop features a keynote by Dave Taht, a networking researcher and developer, known for his contributions to overcome Bufferbloat. The technical program is structured into three topic blocks on 1) design and evaluation of Queuing and Scheduling mechanisms, 2) new extensions to Transport Protocols, and 3) rate adaptation and bandwidth allocation strategies in Mobile Networks.