Rene Rembarz

Design considerations for a network of information

The existing Internet ecosystem is a result of decades of evolution. It has managed to scale well beyond the original aspirations. Evolution, though, highlighted a certain degree of inadequacies that is well documented. In this position paper we present the design considerations for a re-architected global networking architecture which delivers dissemination and non-dissemination objects only to consenting recipients, reducing unwanted traffic, linking information producers with consumers independently of the hosts involved, and connects the digital with the physical world. We consider issues ranging from the proposed object identifier/locator split to security and trust as we transition towards a Network of Information and relate our work with the emerging paradigm of publish/subscribe architectures. We introduce the fundamental components of a Network of Information, i.e., name resolution, routing, storage, and search, and close this paper with a discussion about future work.

What Networking of Information Can Do for Cloud Computing

Cloud computing is making it possible to separate the process of building an infrastructure for service provisioning from the business of providing end user services. Today, such infrastructures are normally provided in large data centres and the applications are executed remotely from the users. One reason for this is that cloud computing requires a reasonably stable infrastructure and networking environment, largely due to management reasons. Networking of Information (NetInf) is an information centric networking paradigm that can support cloud computing by providing new possibilities for network transport and storage. It offers direct access to information objects through a simple API, independent of their location in the network. This abstraction can hide much of the complexity of storage and network transport systems that cloud computing today has to deal with. In this paper we analyze how cloud computing and NetInf can be combined to make cloud computing infrastructures easier to manage, and potentially enable deployment in smaller and more dynamic networking environments. NetInf should thus be understood as an enhancement to the infrastructure for cloud computing rather than a change to cloud computing technology as such. To illustrate the approach taken by NetInf, we also describe how it can be implemented by introducing a specific name resolution and routing mechanism.

Scenarios and Research Issues for a Network of Information

This paper describes ideas and items of work within the framework of the EU-funded 4WARD project. We present scenarios where the current host-centric approach to infor- mation storage and retrieval is ill-suited for and explain how a new networking paradigm emerges, by adopting the information-centric network architecture approach, which we call Network of Information (NetInf). NetInf capital- izes on a proposed identifier/locator split and allows users to create, distribute, and retrieve information using a com- mon infrastructure without tying data to particular hosts. NetInf introduces the concepts of information and data ob- jects. Data objects correspond to the particular bits and bytes of a digital object, such as text file, a specific encod- ing of a song or a video. Information objects can be used to identify other objects irrespective of their particular dig- ital representation. After discussing the benefits of such an indirection, we consider the impact of NetInf with respect to naming and governance in the Future Internet. Finally, we provide an outlook on the research scope of NetInf along with items for future work.

Network Virtualization: A Viable Path Towards the Future Internet

New technologies as well as new ways of using network services are rapidly changing the Internet’s landscape. These developments will have far-reaching implications for the architecture of the networks of the future. However, the current Internet design is plagued with a number of fundamental limitations, which makes its use as the sole basis for the networking applications of the future questionable. We believe that the Future Internet must allow the co-existence of diverse network designs and paradigms, both new and old, to remain open to innovation and meet the challenges of the future. In this paper, we propose to use network virtualization, embedded in an architectural framework, to achieve this goal and to lay the foundation for the deployment of novel concepts such as content-centric networking.

Advances in network-supported media delivery in next-generation mobile systems

This article presents new concepts for network-supported media delivery in mobile networks. Automatic composition and merging of networks are central parts of these concepts. Media delivery is no longer an end-to-end service that only uses the network as an IP transport. Instead, these concepts create a service-aware network and provide customized delivery support through per-service overlay networks. They also integrate specialized processing nodes as part of the delivery topology, which include transcoders but also more complex processors, such as localized program insertions or personalized spam control. This article describes the underlying concepts and how these new network capabilities for media delivery services are requested, invoked, and managed

Private Domains in Networks of Information

The networking research community has recently started looking into so-called information-centric networks, which regard information objects as the primary elements in the network. Users store and retrieve the information objects, denoted by object identifi- ers, from the network without knowing or bothering which host serves the actual request, comparable to earlier initiatives in networking that separate node identifiers from network locations. The capability to address content directly takes many optimizations, such as content- optimized routing or transparent caching, to the next level, while at the same time enabling novel services. In order to prevent unautho- rized access to the information objects that roam around freely in the global network, objects shall be encrypted. We argue that for some use cases, e.g. when dealing with sensitive company-internal information, a stricter partitioning of the network is required. We propose and discuss two solutions to this problem, one focusing on securing the name resolution procedure, the other concentrating on the actual re- trieval. Both mechanisms complement existing proposals by separating information objects in the private network domain while maintaining global reachability.

An Analysis of Web Caching in Current Mobile Broadband Scenarios

The web caching business has significantly changed over the recent years. The percentage of content that is suitable for caching has constantly decreased, e.g. due to unfavorable content formats like Flash or varying URLs due to usage of CDNs. While this of course has a negative impact on the effectiveness of caching, also other parts of the equation have changed: Transmission cost has dropped significantly, and so has the cost to run a cache, especially in times where Cloud Computing approaches commoditize such operations. At the same time, the topic of caching as such remains highly relevant, as the data volumes in the networks continue to grow exponentially and net-work operators are seeking ways to cope with this demand in an efficient manner. We have therefore analyzed a realistic mobile network topol-ogy consisting of primary and secondary telecommunication sites that can be found in many deployments, and have determined the efficiency of web caching, taking into account the latest changes in the ecosystem. An abstract telecommunication site model has been developed and parameterized with a realistic traffic and cost structure for a Western European operator. We find that, contrary to other research that suggests the days of caching are over, there is a clear business case for introducing web caches in primary sites. With current hosting costs and economies of scale, a caching system can already be efficient if only 5.1% of the traf-fic is suitable for caching. For the secondary sites the same effect can be observed and, although the effect is not that distinct, also here web caching can bring clear benefits in certain scenarios.

Enhancing resilience for high availability IP-based signaling transport

With network operators migrating from circuit-switched networks to IP networks, the need for a concept to provide operator grade trunk signaling over IP arises. A solution to enable signaling transport over IP is defined by the IETF SIGTRAN framework that allows for interworking with the Signaling System No. 7 (SS7). SIGTRAN is based on the stream control transmission protocol (SCTP) that also has a built-in redundancy mechanism, which allows switching to an alternative destination address (failover). Existing work showed that a failover performance comparable to SS7 can be achieved by aggressively setting the SCTP protocol parameters. However, this brings about possible stability issues because these parameter settings seriously impair the protocol mechanisms responsible for reacting to delay variations and congestion situations. We propose a set of network redundancy mechanisms that resolve most network failures transparently to SCTP. In order to eliminate possible stability issues, we use the default SCTP protocol parameters. Simulation results confirm that the proposed architecture can noticeably improve the robustness to concurrent network failures and achieve a similar delay behavior without jeopardizing the protocol stability

Validation of the Ambient Networks System Architecture

The Ambient Networks project develops a complete and coherent solution for control architectures in future networks. In particular, the concept of Ambient Control Space has been proposed to support a technology-agnostic, modular and dynamic control plane. The second phase of the project (2006-2007) has an increased focus on validation, where two complementary tracks are being followed: proof-of- concept prototyping and performance evaluation through simulations. The prototype modules, focusing on requirement engineering, were validated during the process of integrating them into a common control space prototype, which was later used to build the demonstration setups. The system performance evaluation through simulations deals with aspects such as capacity utilization, reachability, cost and performance trade-offs and also provides evidence that the additional AN features (e.g., composition) do not introduce excessive signaling overhead. We target different composition aspects, advertising & discovery, negotiation of composition agreements and their interaction with multi-radio access and mobility control. Our validation approach is based on several use cases.

Network Supported Media Delivery in Ambient Networks (Netzwerkunterstützte Medienverteilung)

This paper presents the vision of Ambient Networking, which is proposed to constitute the control layer of future B3G networks. The main characteristics of the Ambient Network Control Space are introduced and the Ambient Network Media Delivery function is explained in more detail to provide an example for a typical control space component. The description of a Media Delivery prototype complements this article. Dieser Beitrag stellt das Ambient Networking Konzept vor. Dieses Konzept ist ein Vorschlag für eine Steuerungsschicht zukünftiger B3G (beyond 3G) Netze. Die Hauptmerkmale des Ambient Control Spaces werden beschrieben und die Steuerungsfunktion Ambient Media Delivery wird als Beispiel einer typischen Steuerungskomponente des Ambient Control Spaces näher betrachtet. Als Ergänzung der Beschreibung wird im letzten Abschnitt die prototypische Implementierung dieser Steuerungskomponente dargestellt.