Self-Organization Strategies for Highly Dense Wireless Networks Dina Papagiannaki (Intel Research UK)

The increased popularity of IEEE 802.11 WLANs has led to dense deployments in urban areas. Such high density leads to sub-optimal performance unless the interfering networks learn how to optimally share the spectrum. In this work we study fully distributed algorithms for the self-organization of highly dense wireless networks that span the areas of frequency selection, power control, CCA adaptation and user association. Our algorithms can be proven to converge to the glocal optimum while relying on purely local information. Using real experimentation and simulations we demonstrate that there are significant benefits to be gained.

Optical Burst Transport on Metro DWDM Rings Ching-Fong Su (Fujitsu Labs)

The current optical network architecture is predominantly circuit-based. However, traffic carried over it is increasingly data packets generated by Internet applications. Because of the application and user behaviors, Internet traffic has been shown to be bursty. Provisioning fixed-bandwidth circuits becomes inefficient as an operator cannot accommodate unpredictable traffic surge while also maintaining high bandwidth utilization. We design Optical Burst Transport (OBT) to bridge the architectural mismatch between a circuit-based physical transport and the carried bursty packet streams. OBT is based on burst-mode transmission between senders and receivers on a WDM-enabled ring topology, and doesn't require complex electronic processing or protocol support.

XML routing for content-based publish/subscribe services Josue Kuri (France Telecom)

An XML routing network is an infrastructure that allows XML documents to be routed based on their content rather than on an explicit destination address in their header, as in IP networks. These networks enable a content-based publish/subscribe communication service in which receivers subscribe to information that is of interest to them without regard to any specific source, while senders simply publish information without addressing it to any specific destination. A content-based publish/subscribe system allows subscribers to express their interest in documents containing specific attributes or values, and receive these documents as soon as they are published. For example, a user can subscribe to stock quotes with symbol NYSE:ATT and a price higher than $23.50. In this talk we will present some of the services that can be supported by the content-based publish/subscribe service enabled by an XML routing network as well as the architectural structure of such a network. We will describe in particular the subscription management and the document/subscription matching functions of the control and data planes, respectively, which are the functions that distinguish XML routing networks from other data networks.

Inference of Split-TCP in cellular networks Hui Zang (Sprint Labs)

Numerous mechanisms have been proposed for improving TCP performance over wireless links, including those in wireless cellular networks. In this talk, we infer the existence and investigate the performance of one class of these performance-enhancing approaches, split-connection approaches, in commercial cellular data networks. Special attention is given to the so called Split-TCP approaches. We present inference techniques to identify whether a cellular provider implements Split-TCP. Through end-to-end measurements over three commercial cellular networks (including two CDMA2000 networks and one GPRS network), we find that all three providers selectively implement Split-TCP for certain applications (e.g., HTTP). We also find that the implementations differ from provider to provider. Experimental results demonstrate that the performance gains from Split-TCP depend on flow sizes and propagation delays.

Demand-Revealing Mechanisms in Wireless Networks Dilip Krishnaswamy (Intel Research)

This talk suggests demand revealing mechanisms to extract the true demand of users in wireless networks. Fair resource allocation is attempted with user data rates and variation in link conditions in mind. Negative feedback is suggested using VCG mechanisms to prevent users from reporting untrue demands to the network.

FIREMAN: A Toolkit for FIREwall Modeling and ANalysis Lihua Yuan (PhD. Candidate)

Security concerns are becoming increasingly critical in networked systems. Firewalls provide important defense for network security. However, misconfigurations in firewalls are very common and significantly weaken the desired security. This paper introduces FIREMAN, a static analysis toolkit for firewall modeling and analysis. By treating firewall configurations as specialized programs, FIREMAN applies static analysis techniques to check misconfigurations, such as policy violations, inconsistencies, and inefficiencies, in individual firewalls as well as among distributed firewalls. FIREMAN performs symbolic model checking of the firewall configurations for all possible IP packets and along all possible data paths. It is both sound and complete because of the finite state nature of firewall configurations. FIREMAN is implemented by modeling firewall rules using binary decision diagrams (BDDs), which have been used successfully in hardware verification and model checking. We have experimented with FIREMAN and used it to uncover several real misconfigurations in enterprise networks, some of which have been subsequently confirmed and corrected by the administrators of these networks.

Etherlay: An Overlay Enhancement for Metro Ethernet Networks Minh Huynh (PhD. Candidate)

The ubiquitous Ethernet technology has propelled itself into a wide-scale adoption for Metro Ethernet Networks (MEN). Despite recent advancements in Ethernet and ommercialization of the first generation of MEN, the fundamental technology does not meet the expectations that carriers have traditionally held in terms of network resiliency and load management. This paper addresses these two issues. We propose a new concept of overlay network in the Ethernet layer, called etherlay, that increases the resiliency of the MEN while provisioning the support for load balancing. As a result, the capacity in terms of network throughput is greatly enhanced while almost avoiding performance hits for any re-convergence in case of failures. Compared to the standard protocols, Etherlay’s total throughput gain ranges from 5.93% to 20.7% in the face of failure; while load balancing capability increases an additional 16% to 60% of the total throughput.

RAPID: An End-System Aware Protocol for Intelligent Data-Transfer over Lambda Grids Amitabha Banerjee (PhD. Candidate)

In this work we investigate the impact of the receiving end-system performance on data transfer to it via a dedicated optical circuit. Such a situation commonly exists in an e-Science application which may receive data from an optical circuit and process it simultaneously. We illustrate an end-system performance monitoring tool which can deliver the feedback of the receiving end-system performance using a transport protocol, so that the sending end-system may control the sending rate using this feedback.