Chamil Kulatunga

Enforcing layered multicast congestion control using ECN-nonce

This paper describes a new protocol using explicit congestion notification (ECN) that protects hosts from the effects of multicast receivers that seek to acquire more than a fair share of network capacity. The technique is described for the IETF asynchrronous layered coding (ALC) but also extensible to other transport protocols. It provides a scalable approach that allows a chosen mediating router to determine if downstream receivers have received congestion-free packets. The protocol allows the congestion behaviour of receivers to be policed, based on the reported ECN-nonce values, knowledge of the subscription rules and synchronisation points used by the transport-layer congestion response algorithm. The reactive policing approach minimises the effects of misbehaving receivers to protect other traffic flows in the network. The method can utilise mediating routers organised in a hierarchy. This increases scalability of the solution, addresses heterogeneity in the delivery tree and assists in incremental deployment of the protocol.

Tackling Bufferbloat in capacity-limited networks

Over-provisioned network buffers, often at the Internet edge, induce large queuing delay and high latency; this issue is known as Bufferbloat. In response to this, a set of recently proposed Active Queue Management (AQM) algorithms attempt to reduce standing queues, while maintaining the bottleneck utilisation at an acceptable level. This paper assesses the performance of two AQM schemes (CoDel and FQ-CoDel) over capacity-limited networks with large Round-Trip Time (RTT). In such settings, these AQM schemes have difficulty controlling the buffering level, resulting in both momentarily high queuing delay and low bottleneck utilisation, even if the methods are claimed to be insensitive to link rates and round-trip delays. We explore this issue and show that it is possible to adapt the parameterisation of CoDel and FQ-CoDel to offer a higher bottleneck utilisation while maintaining a low queuing delay. We present experiments over an emulated test bed and a satellite network to confirm that our new parameterisation improves the download time of moderate-size files and reduces the latency for capacity-limited and large-RTT networks.

Evaluation of the impact of packet drops due to AQM over capacity limited paths

For many years Internet routers have been designed and benchmarked in ways that encourage the use of large buffers. When these buffers accumulate a large standing queue, this can lead to high network path latency. Two AQM algorithms: PIE and CoDel, have been recently proposed to reduce buffer latency by avoiding the drawbacks of previous AQM algorithms like RED. This paper explores the performance of these new algorithms in simulated rural broadband networks where capacity is limited. We compared the new algorithms using Adaptive RED as a reference. We observe that to achieve a small queuing delay PIE and CoDel both increase packet loss. We therefore explored this impact on the quality of experience for loss-sensitive unreliable multimedia applications, such as real-time and near-real-time video. The results from simulations show that PIE performs better than CoDel in terms of packet loss rates affecting video quality. We also noted that the performance of ARED is comparable to that of PIE and CoDel in constant capacity links. This suggests that AQM in general is useful for limited capacity network paths.

Security for FLUTE over Satellite Networks

Data transmission, such as software update, large file broadcasting and video on demand, can take advantage of the wide coverage and the broadcasting features of the satellite networks. The multicast technologies provide the support for these applications by efficiently using the expensive satellite bandwidth. One of them is the File Delivery over Unidirectional Transport (FLUTE) protocol [1] that is ideally for bulk of data reliable transmission over the satellite. However, FLUTE does not address any congestion control and security mechanisms. This paper is analyzing the advantages and drawbacks for security over different layers in a satellite network and presenting security considerations for the FLUTE over satellite networks by analyzing the threats and trying to provide security approaches at the Reliable Multicast Transport (RMT) layer for it. The work presented in this paper also analyzes the logical key hierarchy (LHK) for FLUTE protocol and gives the recommendation on the hierarchy structure for efficient re-key.

TFMCC Protocol Behaviour in Satellite Multicast with Variable Return Path Delays

This paper investigates the performance of TCP-friendly multicast congestion control (TFMCC) protocol in satellite networks. TFMCC is a sender-driven congestion control protocol that extends the TFRC congestion control mechanism into multicast. To provide receiver feedback, the TFMCC protocol requires two-way communication like in DVB-RCS that allows a return path over the satellite link to the sender. The adverse effects due to large and varying DVB-RCS delay in slow-start, throughput and congestion response time are analyzed with simulations. It also provides protocol adaptations to improve congestion response using early identification of the leading receiver and dynamic group size determination

Integration of TESLA and FLUTE over satellite networks

Researches on multicast has explored security challenges faced by group communications. Multicast transport protocols and multicast security protocols need to work closely to provide reliable and secure multicast services. However, there has been comparatively little work carried out to specify how exactly the two technologies can work together efficiently. In this paper, authors present an example of partially integrating the Timed Efficient Stream Loss-Tolerant Authentication (TESLA) protocol and the File Delivery over Unidirectional Transport (FLUTE) protocol. TESLA provides source authorization and data integrity for multicast groups while FLUTE ensures reliability of the multicast transmission. This paper proposes a loose synchronization mechanism for a unidirectional transmission environment, suited to satellite networks. The proposed algorithm was implemented on a testbed with multicast tunnel between University of Surrey and University of Aberdeen and the results are presented in this paper.

TESLA with FLUTE over Satellite Networks

Multicast research has explored the security challenges faced in group communications. Multicast transport and multicast security need to work in close collaboration to realise a multicast service. However, there has been comparatively little work to combine the two technologies. In this paper the authors, presenting an example of partially integrating Timed Efficient Stream Loss-Tolerant Authentication (TESLA) protocol and the File Delivery over Unidirectional Transport (FLUTE) protocol. TESLA provides source authorization and data integrity for multicast groups. This paper proposes a loose synchronization mechanism for a unidirectional transmission environment, suited to satellite networks. It also analyses the effects on Forward Error Control (FEC) and the congestion control building blocks of FLUTE when used with TESLA.

Operating ranges, tunability and performance of CoDel and PIE

Bufferbloat is excessive delay due to the accumulation of packets in a routers oversized queues. CoDel and PIE are two recent Active Queue Management (AQM) algorithms that have been proposed to address bufferbloat by reducing the queuing delay while trying to maintain a high bottleneck utilization. This paper fills a gap by outlining what are the operating ranges, that is the network characteristics (in terms of round-trip times and bottleneck capacity), for which these algorithms achieve their design goals. This new approach to the problem lets us identify deployment scenarios where both AQM schemes result in poor performance when used with default parameters. Because PIE and CoDel have been proposed with REDs deployment issues in mind, it was essential to evaluate to what extent we can tune them to achieve various trade-offs and let them control the queuing delay outside their default operating range. We find that, by appropriate tuning (1) the amount of buffering can easily be controlled with PIE, (2) the Round Trip Time (RTT) sensitivity of CoDel can be reduced. Also, we observe there is more correlation between the congestion level, the achieved queuing delay and the targeted delay with CoDel than with PIE. This paper therefore concludes there is no single overall best AQM scheme, as each scheme proposes a specific trade-off.

The Integration of TESLA and FLUTE over Satellite Networks

Multicast research has explored the security challenges faced in group communications. Multicast transport and multicast security need to work in close collaboration to realise a multicast service. However, there has been comparatively little work to combine the two technologies. In this paper the authors is presenting an example of partially integrating Timed Efficient Stream Loss-Tolerant Authentication (TESLA) protocol and the File Delivery over Unidirectional Transport (FLUTE) protocol. The security concern raised by the proposed algorithm is analysed for satellite network. The proposed algorithm was implemented on a testbed with multicast tunnel between University of Surrey and University of Aberdeen and the results are presented in this paper.

Performance impact of ECN on multimedia traffic with satellite delay

Explicit Congestion Notification (ECN) is a mechanism that can be used to provide early indication of impending Internet congestion, and as such can be used to reduce the latency and improve the throughput of applications using the Internet. This paper examines the impact of using ECN with Quality of Service classification for Internet paths that include a satellite delay. Specifically, it provides a practical analysis of the impact when multimedia applications using the User Datagram Protocol are transmitted over a network path for which ECN is enabled. Since ECN impacts the end-to-end performance, the paper discusses the effect of a larger path delay, as found in a satellite environment. The method is shown to offer benefit to a satellite operator and the network user.