Search

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.comnet.2008.10.019 Byline: Ioannis Psaras, Vassilis Tsaoussidis Keywords: TCP; Congestion control; Transmission scheduling; Flow contention; AIMD; Adaptive AIMD; Adaptive transmission Abstract: We propose AIRA, an Additive Increase Rate Accelerator. AIRA extends AIMD functionality towards adaptive increase rates, depending on the level of network contention and bandwidth availability. In this context, acceleration grows when resource availability is detected by goodput/throughput measurements and slows down when increased throughput does not translate into increased goodput as well. Thus, the gap between throughput and goodput determines the behavior of the rate accelerator. We study the properties of the extended model and propose, based on analysis and simulation, appropriate rate decrease and increase rules. Furthermore, we study conditional rules to guarantee operational success even in the presence of symptomatic, extra-ordinary events. We show that analytical rules can be derived for accelerating, either positively or negatively, the increase rate of AIMD in accordance with network dynamics. Indeed, we find that the "blind", fixed Additive Increase rule can become an obstacle for the performance of TCP, especially when contention increases. Instead, sophisticated, contention-aware additive increase rates may preserve system stability and reduce retransmission effort, without reducing the goodput performance of TCP. Author Affiliation: Democritus University of Thrace, Department of Electrical and Computer Engineering, 12 Vas. Sofias Str., 67100 Xanthi, Greece Article History: Received 25 March 2008; Revised 6 October 2008; Accepted 17 October 2008 Article Note: (miscellaneous) Responsible Editor: J. Zhang

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2008.02.067 Byline: Panagiotis Papadimitriou, Vassilis Tsaoussidis, Lefteris Mamatas Keywords: End-to-end protocols; Rate control; Quality of Service; Video streaming Abstract: We present a new end-to-end protocol, namely Dynamic Video Rate Control (DVRC), which operates on top of UDP and enables the adaptive delivery of layered video streams over the Internet. The protocol optimizes the performance on video delivery with concern to friendliness with interfering traffic. DVRC enables a closed-loop control between server and client, where the receiver detects the state of congestion, determines the proper transmission rate, and eventually opts for the optimal number of layers that should be delivered according to this rate. The protocol relies on a hybrid Additive Increase Additive Decrease (AIAD)/Additive Increase Multiplicative Decrease (AIMD) algorithm (namely AIAMD) that manages to differentiate congestive and non-congestive loss by utilizing history in its control rules. AIAMD combines the most desirable features of AIAD and AIMD, reacting gently to random loss and more aggressively to congestion and adapting effectively to the dynamics of the network. Therefore, DVRC enables the desired smoothness for video streaming applications and at the same time avoids significant damage during congestion. Exploring DVRC's potential through extensive simulations, we identify notable gains in terms of bandwidth utilization and smooth video delivery. Furthermore, our results indicate that the protocol allocates a well-balanced amount of network resources maintaining friendliness with corporate TCP connections. Author Affiliation: Democritus University of Thrace, Electrical and Computer Engineering Department, 12 Vas. Sofias Street, Xanthi, Greece Article History: Received 20 February 2007; Revised 29 February 2008; Accepted 29 February 2008

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.comnet.2007.06.018 Byline: Panagiotis Papadimitriou, Vassilis Tsaoussidis Keywords: End-to-end protocols; Congestion control; Quality of Service; Video streaming Abstract: In this paper, we present a new end-to-end protocol, namely Scalable Streaming Video Protocol (SSVP), which operates on top of UDP and is optimized for unicast video streaming applications. SSVP employs Additive Increase Multiplicative Decrease (AIMD)-based congestion control and adapts the sending rate by properly adjusting the inter-packet-gap (IPG). The smoothness-oriented modulation of AIMD parameters and IPG adjustments reduce the magnitude of AIMD oscillation and allow for smooth transmission patterns, while TCP-friendliness is maintained. Our experimental results demonstrate that SSVP eventually adapts to the vagaries of the network and achieves remarkable performance on real-time video delivery. In the event where awkward network conditions impair the perceptual video quality, we investigate the potential improvement via a layered adaptation mechanism that utilizes receiver buffering and adapts video quality along with long-term variations in the available bandwidth. The adaptation mechanism sends a new layer based on explicit criteria that consider both the available bandwidth and the amount of buffering at the receiver, preventing wasteful layer changes that have an adverse effect on user-perceived quality. Quantifying the interactions of SSVP with the specific adaptation scheme, we identify notable gains in terms of video delivery, especially in the presence of limited bandwidth. Author Affiliation: Democritus University of Thrace, Electrical and Computer Engineering Department, 12 Vas. Sofias Street, Xanthi, Greece Article History: Received 1 September 2006; Revised 1 May 2007; Accepted 13 June 2007 Article Note: (miscellaneous) Responsible Editor: Buyurman Baykal

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.comnet.2006.10.006 Byline: Ioannis Psaras, Vassilis Tsaoussidis Keywords: TCP; Congestion control; Retransmission timeout; Flow contention; Packet scheduling Abstract: We argue that the design principles of the TCP timeout algorithm are based solely on RTT estimations and may lead to flow synchronization, unnecessary retransmission effort and unfair resource allocation. We present a new Window-Based Retransmission Timeout algorithm (WB-RTO) for TCP, which exhibits two major properties: (i) it cancels retransmission synchronization, which dominates when resource demand exceeds resource supply and (ii) it reschedules flows on the basis of their contribution to congestion. WB-RTO achieves better fairness and slightly better goodput with significant less retransmission effort. Author Affiliation: Demokritos University of Thrace, Department of Electrical and Computer Engineering, 2 Vas. Sofias Str., 67100 Xanthi, Greece Article History: Received 15 April 2006; Revised 29 September 2006; Accepted 5 October 2006 Article Note: (miscellaneous) Responsible Editor: R. Sivakumar