Yannis Thomas

Reducing forwarding state in content-centric networks with semi-stateless forwarding.

Routers in the Content-Centric Networking (CCN) architecture maintain state for all pending content requests, so as to be able to later return the corresponding content. By employing stateful forwarding, CCN supports native multicast, enhances security and enables adaptive forwarding, at the cost of excessive forwarding state that raises scalability concerns. We propose a semi-stateless forwarding scheme in which, instead of tracking each request at every on-path router, requests are tracked at every d hops. At intermediate hops, requests gather reverse path information, which is later used to deliver responses between routers using Bloom filter-based stateless forwarding. Our approach effectively reduces forwarding state, while preserving the advantages of CCN forwarding. Evaluation results over realistic ISP topologies show that our approach reduces forwarding state by 54%-70% in unicast delivery, without any bandwidth penalties, while in multicast delivery it reduces forwarding state by 34%-55% at the expense of 6%-13% in bandwidth overhead.

Networked music performance over information-centric networks

Information-centric networking (ICN) constitutes an alternative to the conventional, IP-based, internetworking, with information itself being identified rather than the host where it resides. This approach introduces powerful tools and operations for content delivery, such as native support for multicast. Exploiting this native multicast capability is a very promising approach for multimedia applications such as Networked Music Performance (NMP), where a set of musicians located in different places wish to perform together in real time. While conferencing applications traditionally rely on a Multipoint Conferencing Unit (MCU) that receives media streams from each participant and then retransmits a mixed stream to each one, in NMP we would prefer direct communication between the participants, so as to reduce transmission delays and allow each participant to mix the incoming media streams in the desired manner. In this paper we introduce an ICN-based NMP application exploiting native multicast, and compare its performance with both MCU and non-MCU NMP variants, using both unicast and multicast.

Object-Oriented Packet Caching for ICN

One of the most discussed features offered by Information-centric Networking (ICN) architectures is the ability to support packet-level caching at every node in the network. By individually naming each packet, ICN allows routers to turn their queueing buffers into packet caches, thus exploiting the networks existing storage resources. However, the performance of packet caching at commodity routers is restricted by the small capacity of their SRAM, which holds the index for the packets stored at the, slower, DRAM. We therefore propose Object-oriented Packet Caching (OPC), a novel caching scheme that overcomes the SRAM bottleneck, by combining object-level indexing in the SRAM with packet-level storage in the DRAM. We implemented OPC and experimentally evaluated it over various cache placement policies, showing that it can enhance the impact of ICN packet-level caching, reducing both network and server load.

Multisource and multipath file transfers through publish-subscribe internetworking

We present mmFTP, an information-centric and receiver-driven file transfer protocol for the Publish Subscribe Internetworking (PSI) architecture. mmFTP supports both multisource and multipath transfers, while requiring minimal complexity in terms of network operation. We describe the basic design and operation of mmFTP and present preliminary experimental performance results from a prototype implementation deployed in the PlanetLab testbed.

Towards improving the efficiency of ICN packet-caches

In-network packet-level caching is one of the most promising features offered by Information-centric Networking (ICN) architectures. In ICN, routers can use their queueing buffers as temporal storage units, thus allowing on-path caching by exploiting the networks storage resources. Packet-caches can be highly beneficial for content delivery, but they are also known to have three significant weaknesses: (i) packet-granularity produces huge cache indexes, (ii) Zipf-like content popularity penalizes the hit-ratio at core nodes and (iii) any discontinuity in the stored packets disrupts RTT-based congestion control. This paper presents OPC, a novel caching management strategy designed to support wire-speed in-network caching, while dealing with the above problems. OPC works at the object-level, thus reducing indexing requirements, is destined for access routers, thus avoiding the small hit-ratios of caches at core-nodes, and stores contiguous groups of packets, thus easing RTT-based congestion control.

Multi-flow congestion control with network assistance

A well-known technique for enhancing the performance and stability of content distribution is the use of multiple dissemination flows. Multipath TCP (MPTCP), the most popular multiflow protocol on the Internet, allows receivers to exploit multiple paths towards a single sender. Nevertheless, MPTCP cannot fully exploit the potential gains of multipath connectivity, as it must fairly share resources with (single-flow) TCP, without a clear understanding of whether the available paths do share any bottleneck links. In this paper, we introduce a hybrid congestion control algorithm for multisource and multipath transport that enables higher bandwidth utilization compared to MPTCP, while remaining friendly to TCP-like flows. Our solution employs (i) an in-network module that offers essential topological information and (ii) Normalized Multiflow Congestion Control (NMCC), a novel end-to-end congestion control algorithm. While NMCC is architecture-independent and the in-network module can be adapted for Multi-Protocol Label Switching (MPLS) or Software Defined Networks (SDNs), our prototype was implemented on the Publish-Subscribe Internetworking (PSI) architecture, which offers centralized path formation and source routing. Using an actual protocol implementation deployed on our test-bed, we provide experimental results which validate the effectiveness of our design in terms of performance, adaptation to shifting network conditions and friendliness to other flows.

QoS-driven multipath routing for on-demand video streaming in a Publish-Subscribe Internet

Aiming to improve the performance of on-demand video streaming services in an Information-Centric Network, we propose a mechanism for selecting multiple delivery paths, satisfying bandwidth, error rate and number-of-paths constraints. Our scheme is developed in the context of the Publish-Subscribe Internet architecture and is shown to outperform state-of-the-art multi-constrained multipath selection mechanisms by up to 7%, and single-path or single-constrained multipath selection schemes by up to 17%, in terms of feasible path discovery, while at the same time improving on bandwidth aggregation. Also, it is suitable for supporting resource-demanding high-definition scalable video streaming services, offering Quality-of-Experience gains.

Demo: Wireless Maritime Networking Experiments with Dedalus

We present Dedalus, a software platform for setting up, executing, and monitoring complex wireless networking experiments running jointly multiple experimental protocols. Although Dedalus can be used for experimentation in a variety of settings, the motivating application, which has influenced its design, is maritime networking. In the case of experiments taking place in FIRE+ RAWFIE testbeds, Dedalus seamlessly makes use of the infrastructure offered by the testbed in order to maximize the scope of the experiments.

IPTV Over ICN

The efficient provision of IPTV services requires support for IP multicasting and IGMP snooping, limiting such services to single operator networks. Information-Centric Networking (ICN), with its native support for multicast seems ideal for such services, but it requires operators and users to overhaul their networks and applications. The POINT project has proposed a hybrid, IP-over-ICN, architecture, preserving IP devices and applications at the edge, but interconnecting them via an SDN-based ICN core. This allows individual operators to exploit the benefits of ICN, without expecting the rest of the Internet to change. In this paper, we first outline the POINT approach and show how it can handle multicast-based IPTV services in a more efficient and resilient manner than IP. We then describe a successful trial of the POINT prototype in a production network, where real users tested actual IPTV services over both IP and POINT under regular and exceptional conditions. Results from the trial show that the POINT prototype matched or improved upon the services offered via plain IP.

Supporting the IoT over Integrated Satellite-Terrestrial Networks Using Information-Centric Networking

We investigate the control and data message overhead when the IoT is supported over an integrated satellite-terrestrial network based on Information-Centric Networking (ICN). We consider a scenario where IoT sensor networks are connected via LEO satellites and present three optimization models: polling and data aggregation at a proxy, confidential data transfer using a single proxy, and individual proxy for each IoT node. The three models are implemented in an integrated ICN testbed that consists of a Publish-Subscribe Internet (PSI) prototype and the OpenSAND satellite emulation. The experimental results show that the optimization models, utilizing PSIs mechanisms, can significantly reduce the satellite traffic load while supporting different levels of security.