David P. Wagner

Using data center TCP (DCTCP) in the Internet

Data Center TCP (DCTCP) is an Explicit Congestion Notification (ECN)-based congestion control and Active Queue Management (AQM) scheme. It has provoked widespread interest because it keeps queuing delay and delay variance very low. There is no theoretical reason why Data Center TCP (DCTCP) cannot scale to the size of the Internet, resulting in greater absolute reductions in delay than achieved in data centres. However, no way has yet been found for DCTCP traffic to coexist with conventional TCP without being starved. This paper introduces a way to deploy DCTCP incrementally on the public Internet that could solve this coexistence problem. Using the widely deployed Weighted Random Early Detection (WRED) scheme, we configure a second AQM that is applied solely to ECN-capable packets. We focus solely on long-running flows, not because they are realistic, but as the critical gating test for whether starvation can occur. For the non-ECN traffic we use TCP New Reno; again not to seek realism, but to check for safety against the prevalent reference. We report the promising result that, not only does the proposed AQM always avoid starvation, but it can also achieve equal rates. We even derived how the sharing ratio between DCTCP and conventional TCP traffic depends on the various AQM parameters. The next step beyond this gating test will be to quantify the reduction in queuing delay and variance in dynamic scenarios. This will support the standardization process needed to define new ECN semantics for DCTCP deployment that the authors have started at the IETF.

Architecture for dynamic management of QoS policies for heterogeneous Internet environments

In heterogeneous Internet access network environments (UMTS, WLAN, WIMAX, WLAN DVB-T, DVB-H) there is a challenge for automated configuration and adaptation of policies aimed at management of quality of service (QoS) guarantees and resource usage. The paper is focussed on a QoS policy management architecture, which allows interaction and adaptation of QoS policies of different actors (network operator, service provider and user) using a scalable policy repository. Design issues of such an architecture are discussed, emphasising on policy information models for dynamic resource, transport and measurement adaptation in heterogeneous network environments, modular and extendable ontology driven policy repository design, as well as flexible management interfaces for policy specification.

Evaluation of ARED, CoDel and PIE

In this paper we compare the three Active Queue Management (AQMs) Adaptive Random Early Detection (ARED), Controlled Delay (CoDel) and Proportional Integral controller Enhanced (PIE) in static as well as dynamic scenarios. We find significant issues when these algorithms are used for big Round Trip Times (RTTs) as well as a significant utilization decrease when used for high bandwidth links. When used for low and medium sized links, CoDel, PIE and ARED are suitable alike, but for corner scenarios clear recommendations can be given.

Experimental Demonstration of Network Virtualization and Resource Flexibility in the COMCON Project

In the recent past, Network Virtualization (NV) received much attention. Nevertheless, Virtual Networks (VNs) are still not available on the market. The consortium of the COntrol and Management of COexisting Networks (COMCON) project examines the potential interactions in vertically and horizontally divided markets and evaluates the applicability of existing technologies, like Generalized Multi-Protocol Label Switching (GMPLS), for automated virtualization-enabled network management. To promote the manifold research, a selected scenario was demonstrated at the EuroView 2011 comprising a Video on Demand (VoD) service using a Scalable Video Codec (SVC). All necessary components have been implemented and the selected scenario was performed on a real network based on Linux PCs. In this paper, we describe the components, the scenario, and the gained insights in detail.

Design and Development of Essential Use-Cases for Self-management in Future Internet Wireless Networks

The paper discusses and describes several selected use-cases for autonomic/cognitive management purposes in the scope of the Future Internet (FI) evolution, as these have been identified upon the original context of the EU-funded Self-NET Project effort. The essential aim is to “delimit” new paradigms for the management of complex and heterogeneous wireless network infrastructures and systems, by proposing the operation of self-managed FI elements around a novel feedback-control cycle, known as the MDE cognitive cycle. Thus, the paper intends to “identify” an integrated validation environment for the prototyping and the assessment of relevant concepts and artifacts, via the establishment of appropriate use-cases and corresponding scenarios of use and the explicit description/set-up of relevant test-beds and/or implementation platforms, towards network and node management. The three proposed use-cases have been selected as “proper drivers” for the design and the validation of Self-NET architecture and concepts.

Towards Dynamic Protocol Configuration and its Configuration and Control in Autonomous Communication Environments

The ability to dynamically adopt protocol functionality to the current situation will greatly improve performance, service availability and quality of service in the Future Internet. Nevertheless this provides a huge set of configuration and adaption options which have to be controlled intelligently and also in a timely manner. This creates need for a multi-level control and configuration framework. This paper presents a architecture for Dynamic Protocol Composition with some experimentation results and the design of a control and configuration framework that allows for efficient and reactive Protocol Composition and Execution while providing many options for configuration for a cognitive system and network management.

Multicast Mobility in Heterogeneous Technologies: Experimental Validation

The convergence of services and technologies has been driven by service and network providers with the aim to develop a unified infrastructure. From the services side, we have multimedia through unicast, multicast and broadcast services. From the technologies side, we have wired and wireless technologies, including unidirectional technologies such as Digital Video Broadcasting (DVB). These trends allied to the increasing mobility and QoS demands, introduce strong requirements to future telecommunication networks. This paper presents an innovative approach to handle multicast services in a heterogeneous networks environment, including broadcast technologies. The presented architecture aims at guaranteeing end-to-end QoS in mobile scenarios, efficiently handling the underlying network resources and integrating the emerging broadcast technologies. This architecture was developed in a real environment with mobility of multicast sessions through heterogeneous technologies, Wi-Fi and DVB, using also Wi-Fi as a return channel. The results show that the architecture is able to support the seamless mobility of users receiving multicast sessions, with low degradation on the running communications.