Pub Date : 2004-06-09DOI: 10.1109/IWQOS.2004.1309364
A. Millet, Z. Mammeri
Class Based Queueing (CBQ) is a packet scheduling discipline that enables hierarchical link-sharing. Compared to other algorithms, it is modular and intuitive in a first approach, and so is implemented and used nowadays. In this paper, we adapt the discipline to schedule critical real-time flows mixed with other kinds of traffic, as is necessary in a DiffServ environment This requires that some guarantees must be provided deterministically, particularly on queueing delay bounds. Yet theoretical delay bounds for CBQ were never expressed in a general case and with end-to-end derivation, because the nesting of mechanisms makes it hard to predict a worst case scenario. Here we study some cases where an analysis is possible, focusing on two variants of CBQ, and we use network calculus technique to set up a bound that seems realistic. We then show simulations to check the precision of our results.
{"title":"Delay bound Guarantees with WFQ-based CBQ discipline","authors":"A. Millet, Z. Mammeri","doi":"10.1109/IWQOS.2004.1309364","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309364","url":null,"abstract":"Class Based Queueing (CBQ) is a packet scheduling discipline that enables hierarchical link-sharing. Compared to other algorithms, it is modular and intuitive in a first approach, and so is implemented and used nowadays. In this paper, we adapt the discipline to schedule critical real-time flows mixed with other kinds of traffic, as is necessary in a DiffServ environment This requires that some guarantees must be provided deterministically, particularly on queueing delay bounds. Yet theoretical delay bounds for CBQ were never expressed in a general case and with end-to-end derivation, because the nesting of mechanisms makes it hard to predict a worst case scenario. Here we study some cases where an analysis is possible, focusing on two variants of CBQ, and we use network calculus technique to set up a bound that seems realistic. We then show simulations to check the precision of our results.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"120 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114009263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309376
Zhinan Zhou, P. McKinley, S. M. Sadjadi
This paper addresses the energy consumption of forward error correction (FEC) protocols as used to improve quality-of-service (QoS) for wireless computing devices. The paper also characterizes the effect on energy consumption and QoS of the power saving mode in 802.11 wireless local area networks (WLANs). Experiments are described in which FEC-encoded audio streams are multicast to mobile computers across a WLAN. Results of these experiments quantify the tradeoffs between improved QoS, due to FEC, and additional energy consumption caused by receiving and decoding redundant packets. Two different approaches to FEC are compared relative to these metrics. The results of this study enable the development of adaptive software mechanisms that attempt to manage these tradeoffs in the presence of highly dynamic wireless environments.
{"title":"On quality-of-service and energy consumption tradeoffs in FEC-encoded audio streaming","authors":"Zhinan Zhou, P. McKinley, S. M. Sadjadi","doi":"10.1109/IWQOS.2004.1309376","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309376","url":null,"abstract":"This paper addresses the energy consumption of forward error correction (FEC) protocols as used to improve quality-of-service (QoS) for wireless computing devices. The paper also characterizes the effect on energy consumption and QoS of the power saving mode in 802.11 wireless local area networks (WLANs). Experiments are described in which FEC-encoded audio streams are multicast to mobile computers across a WLAN. Results of these experiments quantify the tradeoffs between improved QoS, due to FEC, and additional energy consumption caused by receiving and decoding redundant packets. Two different approaches to FEC are compared relative to these metrics. The results of this study enable the development of adaptive software mechanisms that attempt to manage these tradeoffs in the presence of highly dynamic wireless environments.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132487658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309378
Chengdu Huang, T. Abdelzaher
This paper investigates the performance of a content distribution network designed to provide bounded content access latency. Content can be divided into multiple classes with different configurable per-class delay bounds. The network uses a simple distributed algorithm to dynamically select a subset of its proxy servers for different classes such that a global per-class delay bound is achieved on content access. The content distribution algorithm is implemented and tested on PlanetLab, a world-wide distributed Internet testbed. Evaluation results demonstrate that despite Internet delay variability, subsecond delay bounds (of 200-500ms) can be guaranteed with a very high probability at only a moderate content replication cost. The distribution algorithm achieves a 4 to 5 fold reduction in the number of response-time violations compared to prior content distribution approaches that attempt to minimize average latency. This paper presents the first wide-area performance evaluation of an algorithm designed to bound maximum content access latency, as opposed to optimizing an average performance metric.
{"title":"Towards content distribution networks with latency guarantees","authors":"Chengdu Huang, T. Abdelzaher","doi":"10.1109/IWQOS.2004.1309378","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309378","url":null,"abstract":"This paper investigates the performance of a content distribution network designed to provide bounded content access latency. Content can be divided into multiple classes with different configurable per-class delay bounds. The network uses a simple distributed algorithm to dynamically select a subset of its proxy servers for different classes such that a global per-class delay bound is achieved on content access. The content distribution algorithm is implemented and tested on PlanetLab, a world-wide distributed Internet testbed. Evaluation results demonstrate that despite Internet delay variability, subsecond delay bounds (of 200-500ms) can be guaranteed with a very high probability at only a moderate content replication cost. The distribution algorithm achieves a 4 to 5 fold reduction in the number of response-time violations compared to prior content distribution approaches that attempt to minimize average latency. This paper presents the first wide-area performance evaluation of an algorithm designed to bound maximum content access latency, as opposed to optimizing an average performance metric.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116922734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309350
O. Younis, S. Fahmy, P. Santi
Clustering sensor nodes increases the scalability and energy efficiency of communications among them. In hostile environments, unexpected failures or attacks on cluster heads (through which communication takes place) may partition the network or degrade application performance. In this work, we propose a new approach, REED (Robust Energy Efficient Distributed clustering), for clustering sensors deployed in hostile environments. Our primary objective is to construct a k (i.e., k-connected) network, where k is a constant determined by the application. Fault tolerance can be achieved by selecting k independent sets of cluster heads (i.e., cluster head overlays) on top of the physical network, so that each node can quickly switch to other cluster heads in case of failures or attacks on its current cluster head. The independent cluster head overlays also provide multiple vertex-disjoint routing paths for load balancing and security. Network lifetime is prolonged by selecting cluster heads with high residual energy and low communication cost, and periodically reclustering the network in order to distribute energy consumption among sensor nodes. We prove that REED can asymptotically achieve k tolerance if certain constraints on node density are satisfied. We also investigate via simulations the clustering properties of REED, and show that building multiple cluster head overlays does not consume significant energy.
{"title":"Robust communications for sensor networks in hostile environments","authors":"O. Younis, S. Fahmy, P. Santi","doi":"10.1109/IWQOS.2004.1309350","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309350","url":null,"abstract":"Clustering sensor nodes increases the scalability and energy efficiency of communications among them. In hostile environments, unexpected failures or attacks on cluster heads (through which communication takes place) may partition the network or degrade application performance. In this work, we propose a new approach, REED (Robust Energy Efficient Distributed clustering), for clustering sensors deployed in hostile environments. Our primary objective is to construct a k (i.e., k-connected) network, where k is a constant determined by the application. Fault tolerance can be achieved by selecting k independent sets of cluster heads (i.e., cluster head overlays) on top of the physical network, so that each node can quickly switch to other cluster heads in case of failures or attacks on its current cluster head. The independent cluster head overlays also provide multiple vertex-disjoint routing paths for load balancing and security. Network lifetime is prolonged by selecting cluster heads with high residual energy and low communication cost, and periodically reclustering the network in order to distribute energy consumption among sensor nodes. We prove that REED can asymptotically achieve k tolerance if certain constraints on node density are satisfied. We also investigate via simulations the clustering properties of REED, and show that building multiple cluster head overlays does not consume significant energy.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123995072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309383
K. Y. Hui, John C.S. Lui, David K. Y. Yau
This paper considers the problem of how to construct and maintain an overlay structured P2P network based on the small world paradigm. Two main attractive properties of a small world network are (1) low average hop distance between any two randomly chosen nodes, and (2) high clustering coefficient of nodes. Having a low average hop distance implies a low latency for object lookup, while having a high clustering coefficient implies the underlying network can effectively provide object lookup even under heavy demands (for example, in a flash crowd scenario). We present a small world overlay protocol (SWOP) for constructing a small world overlay P2P network. We compare the performance of our system with that of other structured P2P networks such as Chord. We show that the SWOP protocol can achieve improved object lookup performance over the existing protocols. We also exploit the high clustering coefficient of a SWOP network to design an object replication algorithm that can effectively handle heavy object lookup traffic. As a result, a SWOP network can quickly and efficiently deliver popular and dynamic objects to a large number of requesting nodes. To the best of our knowledge, ours is the first piece of work that addresses how to handle dynamic flash crowds in a structured P2P network environment.
{"title":"Small world overlay P2P networks","authors":"K. Y. Hui, John C.S. Lui, David K. Y. Yau","doi":"10.1109/IWQOS.2004.1309383","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309383","url":null,"abstract":"This paper considers the problem of how to construct and maintain an overlay structured P2P network based on the small world paradigm. Two main attractive properties of a small world network are (1) low average hop distance between any two randomly chosen nodes, and (2) high clustering coefficient of nodes. Having a low average hop distance implies a low latency for object lookup, while having a high clustering coefficient implies the underlying network can effectively provide object lookup even under heavy demands (for example, in a flash crowd scenario). We present a small world overlay protocol (SWOP) for constructing a small world overlay P2P network. We compare the performance of our system with that of other structured P2P networks such as Chord. We show that the SWOP protocol can achieve improved object lookup performance over the existing protocols. We also exploit the high clustering coefficient of a SWOP network to design an object replication algorithm that can effectively handle heavy object lookup traffic. As a result, a SWOP network can quickly and efficiently deliver popular and dynamic objects to a large number of requesting nodes. To the best of our knowledge, ours is the first piece of work that addresses how to handle dynamic flash crowds in a structured P2P network environment.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124842560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309391
H. Yan, Rupa Krishnan, S. Watterson, D. Lowenthal, Kang Li, L. Peterson
In mobile devices, the wireless network interface card (WNIC) consumes a significant portion of overall system energy. One way to reduce energy consumed by a mobile device is to transition its WNIC to a lower-power sleep mode when data is not being received or transmitted. This paper investigates client-centered techniques for trading download time for energy savings during TCP downloads, in an attempt to reduce the energy' delay product. Effectively saving WNIC energy during a TCP download is difficult because TCP streams tend to be smooth, leaving little potential sleep time. The basic idea behind our technique is that the client increases the amount of time that can be spent in sleep mode by shaping the traffic. In particular, the client convinces the server to send data in predictable bursts, trading lower WNIC energy cost for increased transmission time. Our technique does not rely on any assistance from the server, a proxy, or IEEE 802.11b power-saving mode. Results show that in Internet experiments our scheme outperforms baseline TCP by 64% in the best case, with an average improvement of 19%.
{"title":"Client-centered energy and delay analysis for TCP downloads","authors":"H. Yan, Rupa Krishnan, S. Watterson, D. Lowenthal, Kang Li, L. Peterson","doi":"10.1109/IWQOS.2004.1309391","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309391","url":null,"abstract":"In mobile devices, the wireless network interface card (WNIC) consumes a significant portion of overall system energy. One way to reduce energy consumed by a mobile device is to transition its WNIC to a lower-power sleep mode when data is not being received or transmitted. This paper investigates client-centered techniques for trading download time for energy savings during TCP downloads, in an attempt to reduce the energy' delay product. Effectively saving WNIC energy during a TCP download is difficult because TCP streams tend to be smooth, leaving little potential sleep time. The basic idea behind our technique is that the client increases the amount of time that can be spent in sleep mode by shaping the traffic. In particular, the client convinces the server to send data in predictable bursts, trading lower WNIC energy cost for increased transmission time. Our technique does not rely on any assistance from the server, a proxy, or IEEE 802.11b power-saving mode. Results show that in Internet experiments our scheme outperforms baseline TCP by 64% in the best case, with an average improvement of 19%.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133279746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309392
G. Karlsson, H. Lundqvist, Ignacio Más Ivars
This paper proposes a scheme for quality of service differentiation for single-service networks that is based on the use of two separate forms of traffic control at the transport layer: Streams are controlled by means of probe-based admission control and elastic flows are controlled by TCP. The controls allow separation of traffic into two distinct service classes. The stream class is designed to provide a consistent quality for interactive audiovisual communication, as favored by human perception. It is responsive to load variations as an aggregate through blocking of sessions, while TCP is responsive on the flow level. Streams can be isolated against disturbances from probes and TCP flows by means of error-control coding. We show that the two traffic controls can coexist without starvation, and the proposed scheme might thus provide a first step towards differentiated services end-to-end.
{"title":"Single-service quality differentiation","authors":"G. Karlsson, H. Lundqvist, Ignacio Más Ivars","doi":"10.1109/IWQOS.2004.1309392","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309392","url":null,"abstract":"This paper proposes a scheme for quality of service differentiation for single-service networks that is based on the use of two separate forms of traffic control at the transport layer: Streams are controlled by means of probe-based admission control and elastic flows are controlled by TCP. The controls allow separation of traffic into two distinct service classes. The stream class is designed to provide a consistent quality for interactive audiovisual communication, as favored by human perception. It is responsive to load variations as an aggregate through blocking of sessions, while TCP is responsive on the flow level. Streams can be isolated against disturbances from probes and TCP flows by means of error-control coding. We show that the two traffic controls can coexist without starvation, and the proposed scheme might thus provide a first step towards differentiated services end-to-end.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115269951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309361
Wei Sun, K. Shin
This paper proposes a novel coordinated aggregate scheduling (CAS) algorithm that combines both EOF (earliest-deadline-first) scheduling and rate-based fair queueing. CAS uses guaranteed rate (GR) scheduling (Goyal, P et al., 1995) for traffic aggregates at the inter-aggregate level, but employs EDF-like scheduling at the intra-aggregate level. Computation of the deadline D/sub N/ of a packet at an intermediate node N is coordinated between the node N and its upstream nodes, and D/sub N/ is related to the packet's guaranteed rate clock (GRC) value at the flow-aggregation node. CAS provides tighter end-to-end (e2e) delay bounds than the "vanilla" GR aggregate scheduling that relies on FIFO queueing within an aggregate. Our in-depth simulation results demonstrate CAS's superior performance. Moreover, as an aggregate-based work-conserving scheduling algorithm, CAS incurs lower scheduling and state-maintenance overheads at routers than per-flow scheduling. These salient features make CAS very attractive for use in Internet core networks.
提出了一种将EOF(最早截止日期优先)调度和基于速率的公平排队相结合的新型协同聚合调度算法。CAS对聚合间级的流量聚合采用保证速率(GR)调度(Goyal, P et al.， 1995)，而在聚合内级采用类似edf的调度。报文在中间节点N处的截止时间D/sub N/的计算由节点N与其上游节点协调，D/sub N/与报文在流聚合节点处的保证速率时钟(GRC)值有关。CAS提供了比“香草”GR聚合调度更严格的端到端(e2e)延迟界限，后者依赖于聚合内的FIFO队列。我们的深入仿真结果证明了CAS的优越性能。此外，作为一种基于聚合的工作节约调度算法，CAS在路由器上产生的调度和状态维护开销比逐流调度更低。这些显著的特性使得CAS在Internet核心网中的应用非常有吸引力。
{"title":"Coordinated aggregate scheduling for improving end-to-end delay performance","authors":"Wei Sun, K. Shin","doi":"10.1109/IWQOS.2004.1309361","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309361","url":null,"abstract":"This paper proposes a novel coordinated aggregate scheduling (CAS) algorithm that combines both EOF (earliest-deadline-first) scheduling and rate-based fair queueing. CAS uses guaranteed rate (GR) scheduling (Goyal, P et al., 1995) for traffic aggregates at the inter-aggregate level, but employs EDF-like scheduling at the intra-aggregate level. Computation of the deadline D/sub N/ of a packet at an intermediate node N is coordinated between the node N and its upstream nodes, and D/sub N/ is related to the packet's guaranteed rate clock (GRC) value at the flow-aggregation node. CAS provides tighter end-to-end (e2e) delay bounds than the \"vanilla\" GR aggregate scheduling that relies on FIFO queueing within an aggregate. Our in-depth simulation results demonstrate CAS's superior performance. Moreover, as an aggregate-based work-conserving scheduling algorithm, CAS incurs lower scheduling and state-maintenance overheads at routers than per-flow scheduling. These salient features make CAS very attractive for use in Internet core networks.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126844687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309365
K. Pandit, J. Schmitt, R. Steinmetz
Quality of Service (QoS) is an area with high academic curiosity. Our long-term goal is to develop a unified mathematical model. This paper is a first step towards this ambitious goal. The most widespread models for network QoS are network calculus and queueing theory. While the strength of queueing theory is its proven applicability to a wide area of problems, Network calculus can offer performance guarantees. We analyse by simulation the benefit of bringing the two of them together, i.e., bounding the stochastic processes of a queue with methods from network calculus. A basic result from network calculus is that enforcing traffic shaping and service curves bounds the buffer. This leads to denying buffer states in queues with infinite buffer. Specifically, we analyse what happens with the probability mass of such buffer states. Finally, we discuss how our results can be used for dimensioning buffers for multiplexed traffic.
{"title":"Network calculus meets queueing theory -a simulation based approach to bounded queues","authors":"K. Pandit, J. Schmitt, R. Steinmetz","doi":"10.1109/IWQOS.2004.1309365","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309365","url":null,"abstract":"Quality of Service (QoS) is an area with high academic curiosity. Our long-term goal is to develop a unified mathematical model. This paper is a first step towards this ambitious goal. The most widespread models for network QoS are network calculus and queueing theory. While the strength of queueing theory is its proven applicability to a wide area of problems, Network calculus can offer performance guarantees. We analyse by simulation the benefit of bringing the two of them together, i.e., bounding the stochastic processes of a queue with methods from network calculus. A basic result from network calculus is that enforcing traffic shaping and service curves bounds the buffer. This leads to denying buffer states in queues with infinite buffer. Specifically, we analyse what happens with the probability mass of such buffer states. Finally, we discuss how our results can be used for dimensioning buffers for multiplexed traffic.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128926201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2004-06-07DOI: 10.1109/IWQOS.2004.1309385
Yi Cui, Yuan Xue, K. Nahrstedt
Although initially proposed as the deployable alternative to IP multicast, overlay multicast actually offers us great flexibilities on QoS-aware resource allocation for network applications. For example, in overlay multicast streaming, (1) the streaming rate of each client can be diversified to better accommodate network heterogeneity, through various end-to-end streaming adaptation techniques; and (2) one can freely organize the overlay session by rearranging the multicast tree, for the purpose of better resource utilization and fairness among all clients. The goal of this paper, is to find the max-min rate allocation in overlay multicast, which is pareto-optimal in terms of network resource utilization, and max-min fair. We approach this goal in two steps. First, we present a distributed algorithm, which is able to return the max-min rate allocation for any given overlay multicast tree. Second, we study the problem of finding the optimal tree, whose max-min rate allocation is optimal among all trees. After proving its NP-hardness, we propose a heuristic algorithm of overlay multicast tree construction. A variation of the heuristic is also designed to handle the dynamic client join/departure. Both of them have approximation bound of 1/2 to the optimal value. Experimental results show that they achieve high average throughput, almost saturate link utilization, and consistent min-favorability.
{"title":"Maxmin overlay multicast: rate allocation and tree construction","authors":"Yi Cui, Yuan Xue, K. Nahrstedt","doi":"10.1109/IWQOS.2004.1309385","DOIUrl":"https://doi.org/10.1109/IWQOS.2004.1309385","url":null,"abstract":"Although initially proposed as the deployable alternative to IP multicast, overlay multicast actually offers us great flexibilities on QoS-aware resource allocation for network applications. For example, in overlay multicast streaming, (1) the streaming rate of each client can be diversified to better accommodate network heterogeneity, through various end-to-end streaming adaptation techniques; and (2) one can freely organize the overlay session by rearranging the multicast tree, for the purpose of better resource utilization and fairness among all clients. The goal of this paper, is to find the max-min rate allocation in overlay multicast, which is pareto-optimal in terms of network resource utilization, and max-min fair. We approach this goal in two steps. First, we present a distributed algorithm, which is able to return the max-min rate allocation for any given overlay multicast tree. Second, we study the problem of finding the optimal tree, whose max-min rate allocation is optimal among all trees. After proving its NP-hardness, we propose a heuristic algorithm of overlay multicast tree construction. A variation of the heuristic is also designed to handle the dynamic client join/departure. Both of them have approximation bound of 1/2 to the optimal value. Experimental results show that they achieve high average throughput, almost saturate link utilization, and consistent min-favorability.","PeriodicalId":266235,"journal":{"name":"Twelfth IEEE International Workshop on Quality of Service, 2004. IWQOS 2004.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126914637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：