Figure 7 - uploaded by Klara Nahrstedt
Content may be subject to copyright.
Source publication
Video on demand applications emerge on campus wide networks.
Compressed video streams pass switches which do not have any bandwidth
reservation mechanism, nor any other mechanism against congestion. The
switches, shared among video servers, WWW servers and clients, get
easily congested in critical situations, hence the switches drop pockets
and the...
Context in source publication
Similar publications
The spread of novel multimedia services such as audio and video streaming, HDTV and online gaming have become a ordinary in the home networks. Therefore, the possibility to manage the Quality of Service (QoS) within an home environment becomes a crucial factor for the satisfaction of the user. In this paper we propose an enhanced Admission Control...
In this contribution, we investigate the performance of the output buer of a video streaming server. We assume that the server en- codes the video stream in a scalable way, i.e. the generated video packets contain a base layer ensuring a minimum of guaranteed quality and a stack of additional enhancement layers progressively improving the qual- ity...
Poor performance and network congestion are commonly observed in the streaming media single server system. This paper proposes a scheme to construct a streaming media server cluster system based on FFMpeg. In this scheme, different users are distributed to different servers according to their locations and the balance among servers is maintained by...
Citations
... A potential weakness of multipath-based video delivery entails reordering overhead. Several previous studies (e.g., [29]) have shown that reordering overhead remains acceptable. Another concern is the difference in delays between different video delivery paths. ...
The multipath-based method can effectively improve the video streaming quality. However, it suffers a limitation on the realistic deployment and needs global optimization to improve the network accommodation capability. In this paper, we study a novel multipath-based streaming rate optimization solution for unicast-based video applications. The proposed solution employs a differentiated multipath delivery model, which uses a main path built at the network layer and multiple auxiliary paths built at the application layer. Because of the application layer-based implementation, auxiliary paths overcome the aforementioned limitation on deployment. Based on the proposed multipath delivery model, we study the global multipath-based streaming rate optimization problem, which strives for an effective tradeoff among video streaming quality, network accommodation capability and video delivery stability. The studied optimization problem is complicated, and we solve it approximately using an approximate algorithm and a convex optimization-based technique.
... To improve the quality of multimedia streams delivered to clients over the shared Internet infrastructure, algorithms have been proposed that exploit multipath delivery by splitting streams between different paths [3], [4]. Several works studied multipath solutions specifically addressing the problem of multipath streaming in the application level by using overlay or peer-to-peer infrastructure [5]–[8]. ...
... To improve the quality of multimedia streams delivered to clients over the shared Internet infrastructure, algorithms have been proposed that exploit multipath delivery by splitting streams between different paths [3], [4]. ...
A streaming system that uses an overlay network for multipath streaming needs to make decisions concerning the distribution of the available bandwidth among all of its clients. This decision making should aim at delivering the best possible quality to all clients while providing an optimal utilization of the network resources. We consider a scenario where videos are hierarchically layered-encoded and most requests are negligibly overlapped in time. It implies that using multicast is not efficient, and instead, the streams are striped and allocated to multiple paths from the server to the client. To evaluate how well the rate-allocation algorithms approach optimality, we have earlier built a benchmarking system that provides the optimal solution for assigning available bandwidth to delivery paths. However, as video quality is not linearly related to bitrate, the trivial maximization of the total consumed bandwidth does not necessarily maximize the video quality. To address this problem, we define a metric that assesses video quality for a group of clients that we use as a utility function in the revised benchmarking system. Due to its concavity, this utility function distributes the bandwidth resources proportionally fair between the clients of the system.
... Multipath streaming is one of the approaches that have been proposed in several papers345 in order to overcome packet loss and bandwidth limitations in the Internet during the delivery of multimedia streams. There are mainly two ways of implementing multipath routing. ...
The rapid growth of the Internet multimedia services brings new challenges to how multimedia streams can be delivered to the users over bandwidth-constraint networks. Different strategies that exploit multipath streaming in order to provide better utilization of the Internet resources have been proposed by the research community. However, there exists no metric that allows us to evaluate how close these strategies are to the optimal resource utilization. This paper proposes a static benchmarking system that models the best possible distribution of streams along multiple paths in an overlay network that is shared by several senders and receivers. We have tested it with several different network topologies, and present the test results in this paper.
... Our approach can also be implemented on an overlay structure as well as with the aid of relay nodes, e.g., a P2P prototype implementation of our approach is described in [2]. Other works try to achieve multi-path streaming with the assistance from the lower layers, e.g., [8] utilizes bandwidth on multiple paths and re-distributes workload according to congestion detected by a receiver. But, it requires network layer knowledge and a centralized routing server. ...
Under the current Internet infrastructure, quality of service (QoS) in the delivery of continuous media (CM) is still relatively poor and inconsistent. In this paper we consider providing QoS through the exploitation of multiple paths existing in the network. Previous work has illustrated the advantages of this approach. Here we extend this work by considering a more expressive model for characterizing the network path losses. In particular, we propose a variation on the Gilbert model wherein the loss characteristics of a path depend on an application's transmission bandwidth. Using this model, we show the benefits of multi-path streaming over best single-path streaming, under optimal load distribution among the multiple paths. We use extensive simulation and measurements from a system prototype to quantify the performance benefits of our techniques. © 2005 Elsevier B.V. All rights reserved.
... In con-trast, [18] illustrates the utility of considering an application's sending rate and the resulting effects on the loss characteristics of the CM streaming application. Other works try to achieve multi-path streaming with assistance of the lower layers, e.g., [19] focuses a protocol which utilizes bandwidth available on multiple paths and redistributes workload according to congestion detected by a receiver. However, it requires network layer knowledge as well as a centralized routing server to compute the multipath routing which minimizes the number of shared links while satisfying the bandwidth requirement. ...
Quality of service (QoS) in streaming of continuous media over the Internet is poor, which is partly due to variations in delays, bandwidth limitations, and packet losses. Although continuous media applications can tolerate some missing data, non-recoverable information loss degrades these applications' QoS. Consequently, a number of application areas have backed away from streaming of their content over the Internet. Inability to control the resulting visual and auditory quality of the streamed presentation is an important reason for such a trend. We believe that this trend can be reversed. To this end, this paper gives an overview of our efforts in exploring high quality streaming through the exploitation of multiple paths existing in the network. By high quality, we mean with significant bandwidth requirements, of relatively long duration, and without information loss or hiccups in data delivery. We believe this to be a promising approach.
... Our approach can also be implemented on an overlay structure as well as with the aid of relay nodes, e.g., a P2P prototype implementation of our approach is described in [2]. Other works try to achieve multi-path streaming with the assistance from the lower layers, e.g., [8] utilizes bandwidth on multiple paths and re-distributes workload according to congestion detected by a receiver. But, it requires network layer knowledge and a centralized routing server. ...
... Another set of works on the topic considers higher level mechanisms, but requires assistance from the lower layers and/or assumes significant knowledge of network topology and/or link capacities and delays (on all links used for data delivery). Given such knowledge, algorithms are proposed for selecting paths which can avoid congested routes, e.g., in [5,4]. In contrast, our approach does not rely on specific knowledge of topologies, capacities, delays, etc., and only considers whether a set of paths do or do not share joint points of congestion, as can be detected at the end-hosts. ...
Quality of service in streaming of continuous media over the Internet is poor, which is partly due to variations in delays, bandwidth limitations, and packet losses. Although continuous media applications can tolerate some missing data, non-recoverable information loss degrades these applications' QoS. Consequently, a number of application areas (e.g., those related to the entertainment industry) have backed away from streaming of their content over the Internet. Inability to control the resulting visual and auditory quality of the resulting streamed presentation is an important reason for such a trend. We believe that this trend can be reversed. To this end, our work focuses on providing high-quality streaming through the exploitation of multiple paths existing in the network. By high quality, we mean with significant bandwidth requirements, of relatively long duration, and without information loss or hiccups in data delivery. In this article we present evidence that multi-path streaming is a promising approach.
... The majority of the existing schemes proposed for ad hoc networks uses single-path routing [8,10,18], which might not reduce the average end-to-end delay. However, once a set of (s-d) paths is discovered in anticipation, in some cases, it is useful to employ the concept of multipath communication [3]. In fact, earlier research [5,11,14] have shown that it is possible to improve end-to-end performance by taking recourse to simultaneous data transfer over these paths. ...
... This parallelism in transmission is achieved by splitting the original data volume into smaller blocks and sending these blocks of data via selected multiple paths from s to d; which in turn reduces congestion as well as end-toend delay. Although utilization of multiple paths has been explored in the wired networks [1,3,11], in order to provide improved performance against single path, it has also been shown in [14] that deployment of multiple paths does not necessarily result in a lower end-to-end delay. Furthermore, most of the existing work considers only spatial multipath, whereas our work takes into account both spatial and temporal multipaths. ...
We propose an adaptive framework for computing multiple paths in temporal and spatial domains to transmit a large volume of data packets from a source s to a destination d in ad hoc wireless networks. The objective is to achieve quality of service (QoS) by minimizing end-to-end delay for packet delivery. We consider two aspects in this framework. The first aspect is to perform preemptive route rediscoveries before the occurrence of route errors while transmitting a large volume of data from s to d. This helps us to find out dynamically a series of possible paths in temporal domain to complete the data transfer. The second aspect is to select multiple paths in spatial domain for data transfer at any instant of time, and to distribute the data packets in sequential blocks over those paths in order to reduce congestion and end-to-end delay. A notion of link stability and path stability is also defined, and a unified mechanism is proposed to address the above two aspects that relies on evaluating a path based on link and path stability. Our solution method uses Lagrangean relaxation and subgradient heuristics to solve an optimization formulation of the problem in order to compute the paths and the corresponding data distribution, both in temporal and spatial domains. Simulation experiments demonstrate that the proposed framework helps in significantly reducing the end-to-end delay and the required number of route-rediscoveries.
... Given such knowledge, algorithms are proposed for selecting paths which can avoid congested routes. For instance, in [4], the authors focus on adaptation of delivery rate along the different paths, based on losses observed at the receiver, and Chen and Chan [2] consider proper scheduling of the initial portion of the video so as to reduce the start-up delay. In contrast, our approach does not rely on specific knowledge of topologies, capacities, delays, etc., and only considers whether a set of paths do or do not share joint points of congestion, as can be detected at the end-hosts. ...
Quality of service (QoS) in delivery of continuous media (CM) over the Internet is still relatively poor and inconsistent. Although many such applications can tolerate some degree of missing information, significant losses degrade an application's QoS. In this paper, we investigate the potential benefits of mitigating this problem through the exploitation of multiple paths existing in the network between a set of senders and a receiver of CM. Our focus in this work is on providing a fundamental understanding of the benefits of using multiple paths to deliver CM over best-effort wide-area networks. Specifically, we consider pre-recorded CM applications and use the following metrics in evaluating the performance of multi-path streaming as compared to single-path streaming: (a) data loss rate, (b) conditional error burst length distribution, and (c) lag1-autocorrelation. The results of this work can be used in guiding the design of multi-path CM systems streaming data over best-effort wide-area networks.
... In other scenarios, for example the Internet, the bandwidth reservations may require additional mechanisms, such as RSVP 45], and speci c queuing implementations at the routers 7]. Our framework is di erent from the dynamic frameworks which utilize feedback mechanisms 24,11,4] to provide only \soft" guarantees. Our potential applications include the transmission of: (a) les of varied sizes, for example, ranging from small robot control packets to large image les, and (b) data streams such as video-on-demand or robot vision data. ...
... Utilization of multiple paths to provide improved performance compared to single paths has been explored extensively in the past for various network problems. To name a few, some of the early works are due to 17,21], and some of the recent works are due to 4,11]. In particular, the two problems described in the introduction bare resemblances to a number of network ow problems studied extensively in the eighties, and also to QoS problems of more recent origin. ...
... A majority of recently proposed QoS routing algorithms that provide bounds on end-to-end delay and/or transmission rates are limited to single paths 44,43] with the possible exception of 27,11,4]. The rst problem is extensively studied for single paths under the title of the quickest path problem 9, 35, 33]. ...
vii 1 Introduction 1 1.1 Relation to Prior Work : : : : : : : : : : : : : : : : : : : : : : : : : : 2 1.2 Contribution and Organization of the Paper : : : : : : : : : : : : : : 3 2 Problem Formulation 4 3 Message Transmission Problem 5 3.1 Shortest-Widest Paths : : : : : : : : : : : : : : : : : : : : : : : : : : 5 3.2 Properties of Multipaths : : : : : : : : : : : : : : : : : : : : : : : : : 6 3.3 NP-Completeness of MTP : : : : : : : : : : : : : : : : : : : : : : : : 10 3.4 Approximate Routing Algorithm : : : : : : : : : : : : : : : : : : : : 14 3.5 Relation to Maximum Flow Algorithm : : : : : : : : : : : : : : : : : 16 3.6 Simulation Results : : : : : : : : : : : : : : : : : : : : : : : : : : : : 18 3.7 Delay-Bandwidth Product : : : : : : : : : : : : : : : : : : : : : : : : 24 4 Sequence Transmission Problem 25 4.1 Intractability Results : : : : : : : : : : : : : : : : : : : : : : : : : : : 25 4.2 Approximation Algorithm : : : : : : : : : : : : : : : : : : : : : : : : 28 5 Concl...
