No abstract

No abstract

This paper presents and characterizes the performance of CORE, a protocol that brings together the efficiency in spectrum usage of inter-session network coding schemes and the robustness against packet losses of intra-session network coding. We provide in-depth mathematical analysis of the gains of CORE followed by protocol design and implementation details needed for CORE's successful deployment in practice. Finally, we provide extensive measurements with off-the-shelf wireless nodes under various channel and system conditions comparing CORE to other state-of-the-art approaches, namely, forwarding (no coding) and COPE (inter-session network coding). These measurements support our theoretical findings, showing that CORE not only outperforms COPE and forwarding in general, but that order of magnitude gains are possible for cases with high packet losses. Specifically, CORE has a throughput gain of more than 10x over a COPE-like scheme and 7x over forwarding when the error ratio is 50 % on all links. Beyond these gains over other protocols, our measurements show that our CORE implementation can achieve close to optimal performance with a gap of less than 0.43 dB.

This paper introduces a mutually beneficial inter play between network coding and scalable video source coding in order to propose an energy-efficient video streaming approach accommodating multiple heterogeneous receivers, for which cur rent solutions are either inefficient or insufficient. State of the art in media streaming typically acknowledges network and source coding being complementary. Despite this, these research topics are treated separately. By cultivating advantageous behaviour and features in the network and source coding structures a correlation between coding complexity and channel quality is developed. A linear coding structure designed to gracefully en capsulate layered source coding provides both low complexity of the utilised linear coding while enabling robust erasure correction in the form of fountain coding capabilities. The proposed linear coding structure advocates efficient support of multi-resolution video streaming.

Network Coding (NC) for Wireless Mesh Network (WMN) has received a lot of attention from the research community in recent years due to its ability to provide higher throughput, reliability, and efficiency in the use of the available wireless spectrum. NC has had two main research lines focused on inter-flow and intra-flow coding. However, these two domains have historically been studied separately. This paper proposes a testbed implementation of CORE, the first protocol to bridge both approaches such that the structure of intra-flow coding can be exploited during inter-flow coding to both enhance reliability, common of the former, while maintaining an efficient spectrum usage, typical of the latter. This paper uses the intuition provided in [1] to propose a practical implementation of the protocol leveraging Random Linear Network Coding (RLNC) for intra flow coding, a credit based packet transmission approach to decide how much and when to send redundancy in the network, and a minimalistic feedback mechanism to guarantee delivery of generations of the different flows. Given the delay constraints of video applications, we proposed a simple yet effective coding mechanism, Block Coding On The Fly (BCFly), that allows a block encoder to be fed on-the-f1y, thus reducing the delay to accumulate enough packets that is introduced by typical genera tion based NC techniques. Our measurements and comparison to forwarding and COPE show that CORE not only outperforms these schemes even for small packet losses, but that the gains can be of five fold and two orders of magnitude, respectively, for higher packet losses.

We characterize the performance of intra-and inter-session network coding (NC) in wireless networks using real-life implementations. We compare this performance to a recently developed hybrid approach, called CORE, which combines intra-and inter-session NC exploiting the code structure of the former to enhance the gains of the latter. We first motivate our work through measurements in WiFi mesh networks. Later, we compare state-of-the-art approaches, e.g., COPE, RLNC, to CORE. Our measurements show the higher reliability and throughput of CORE over other schemes, especially, for asymmetric and/or high loss probabilities. We show that a store and forward scheme outperforms COPE under some channel conditions, while CORE yields 3dB gains.

Packet losses in wireless networks dramatically curbs the performance of TCP. This paper introduces a simple coding shim that aids IP-layer traffic in lossy environments while being transparent to transport layer protocols. The proposed coding approach enables erasure correction while being oblivious to the congestion control algorithms of the utilised transport layer protocol. Although our coding shim is indifferent towards the transport layer protocol, we focus on the performance of TCP when ran on top of our proposed coding mechanism due to its widespread use. The coding shim provides gains in throughput that exceed 10x for TCP traffic while requiring a limited sacrifice in terms of fairness towards other flows on the channel.

No abstract