We consider a proportional delay model for internet differentiated services. Under this model, an ISP can control the "spacing" of waiting times between different classes of traffic. Specifically, the ISP tr...
详细信息
We consider a proportional delay model for internet differentiated services. Under this model, an ISP can control the "spacing" of waiting times between different classes of traffic. Specifically, the ISP tries to ensure that the average waiting time of class i traffic relative to that of class i-1 traffic is consistently a specifiable ratio. If the ratio is less than one, the ISP can legitimately charge users of class i traffic a higher tariff rate (compared to the rate for class i-1 traffic), since class i users consistently enjoy better performance than class i-1 users. We use time-dependent priority scheduling to realize the proportional delay model. We formally characterize the feasible regions in which given delay ratios can be achieved. Moreover a set of scheduling parameters for obtaining the desired delay ratios can be determined by an efficient control algorithm. Experiments are carried out to illustrate the short-term, medium-term and long-term relative waiting time performances for different service classes.
Multicast is a common method for distributing real-time audio and video over the internet. The Receiver-driven Layered Multicast (RLM) is one of the most popular receiver-based rate adaptation algorithms. However, RLM...
详细信息
ISBN:
(纸本)0769507778
Multicast is a common method for distributing real-time audio and video over the internet. The Receiver-driven Layered Multicast (RLM) is one of the most popular receiver-based rate adaptation algorithms. However, RLM is relatively slow in adapting changes in the bandwidth of the network. Its adaptive control is based on packet loss rate. A number of extensions and variants of RLM have been proposed in the literature to improve some of these weaknesses. However, the responses of the receivers are improved at the expense of protocol complexity. In this paper, a receiver-based adaptive multimedia system using the RLM protocol for rate control is implemented. The RLM algorithm is modified to minimise congestion in the network and to reduce the processing overhead. We have also investigated whether the interframe jitter is an appropriate measure of the network congestion, and how it can be used to decide whether a receiver can subscribe to a higher layer at a given point of time. A heuristic method is used to determine the interframe jitter values that the system can tolerate. The modified RLM algorithm is also integrated with the encoding and decoding of the MPEG video to evaluate the overall performance. The preliminary results demonstrate that rate control using the inter-frame jitter has better video quality than that using packet loss rate.
Synchronization control with VCR-like user interactions in the multi-stream environment is very complicated and difficult. The main reasons are that: (i) those media units stored in the client buffers and flowing in t...
详细信息
Synchronization control with VCR-like user interactions in the multi-stream environment is very complicated and difficult. The main reasons are that: (i) those media units stored in the client buffers and flowing in the networks may be either useful or useless when the user interaction is issued, and (ii) the servers' media transmission should be adjusted according to the presentation status of the client. Additionally, different VCR-like user interactions have their own processing considerations, which result in different control schemes for different VCR-like user interactions. We propose some control schemes to handle interactive multimedia communication in the distributed multi-stream environment and develop an MOD system on SUN SPARC workstations accordingly.
In this paper, we propose a new architecture for guaranteeing the multiple Quality of Services (QoSs) in Differentiated Service internet. We take into account the IETF's Differentiated Service (DiffServ) architect...
详细信息
In this paper, we propose a new architecture for guaranteeing the multiple Quality of Services (QoSs) in Differentiated Service internet. We take into account the IETF's Differentiated Service (DiffServ) architecture as well as the QoS requirements of each user application. The main focus lies in the modeling and performance evaluation of the prioritized packet service scheme in the core router which supports weighted priority services in the packet with three service classes defined in IETF: EF (Expedited forwarding), AF (Assured forwarding) and DF (Default forwarding) PHB (Per Hop Behavior). Via simulation experiments we discuss the implication of the proposed scheme.
We proposed earlier (Athuraliya et al. 2000) an optimization based flow control for the internet called random exponential marking (REM). REM consists of a link algorithm, that probabilistically marks packets inside t...
详细信息
We proposed earlier (Athuraliya et al. 2000) an optimization based flow control for the internet called random exponential marking (REM). REM consists of a link algorithm, that probabilistically marks packets inside the network, and a source algorithm, that adapts source rate to observed marking. The marking probability is exponential in a link congestion measure, so that the end-to-end marking probability is exponential in a path congestion measure. Because of the finer measure of congestion provided by REM, sources do not constantly probe the network for spare capacity, but settle around a globally optimal equilibrium, thus avoiding the perpetual cycle of sinking into and recovering from congestion. In this paper we compare the performance of REM with Reno over RED (random early detection) through simulation.
This paper presents the modeling and simulation results of an international aeronautical mobile communications system operating within the environment of an international civil aviation internet. The ground-based aero...
详细信息
This paper presents the modeling and simulation results of an international aeronautical mobile communications system operating within the environment of an international civil aviation internet. The ground-based aeronautical mobile communications system uses a network of ground stations to provide the desired airspace coverage utilizing the Very High Frequency (VHF) band (118-137 MHz) allocated for aviation and a Time Division Multiple Access (TDMA) technique to control media access between aircraft and ground stations. Major performance parameters of interest are: transit end-to-end delays; overall connection establishment times; and protocol overheads resulting from the use of various upper layer protocol data units.
We propose an optimization based flow control for the internet called random early marking (REM). In this paper we propose and evaluate an enhancement that attempts to speed up the convergence of REM in the face of la...
详细信息
We propose an optimization based flow control for the internet called random early marking (REM). In this paper we propose and evaluate an enhancement that attempts to speed up the convergence of REM in the face of large feedback delays. REM can be regarded as an implementation of an optimization algorithm in a distributed network. The basic idea is to treat the optimization algorithm as a discrete time system and apply linear control techniques to stabilize its transient. We show that the modified algorithm is stable globally and converges exponentially locally. This algorithm translates into an enhanced REM scheme and we illustrate the performance improvement through simulation.
Single System Image is a desirable property for all services provided by a cluster environment. Coherently with this principle, cluster file systems should make data distribution transparent to the application, giving...
详细信息
Single System Image is a desirable property for all services provided by a cluster environment. Coherently with this principle, cluster file systems should make data distribution transparent to the application, giving rise to a heavy communication workload induced by I/O activity. Hence, I/O performance greatly depends on communication performance and on how the storage and network subsystems interact at all levels. The authors present a detailed performance analysis of the storage and network subsystems of a properly configured cluster node. In particular, we consider the case of an Ultra2 SCSI controller with multiple attached disks sharing the I/O bus with a Gigabit LAN adapter. The analysis helps to understand how the several hardware and software components interact, which are the potential bottlenecks, and how these bottlenecks affect the overall performance.
We deal with mapping performance-oriented IP services such as Integrated Services (IntServ) or Differentiated Services (DiffServ) onto networkperformance parameters for cell-switched transport networks, as for exampl...
详细信息
We deal with mapping performance-oriented IP services such as Integrated Services (IntServ) or Differentiated Services (DiffServ) onto networkperformance parameters for cell-switched transport networks, as for example ATM. The impact of translating IP performance parameters into ATM network services is analyzed and the detrimental effects of careless mappings are illustrated. Then, approaches to circumvent these detrimental effects are presented.
The majority of the traffic (bytes) flowing over the internet today have been attributed to the Transmission control Protocol (TCP). This strong presence of TCP has spurred further investigations into its congestion c...
详细信息
The majority of the traffic (bytes) flowing over the internet today have been attributed to the Transmission control Protocol (TCP). This strong presence of TCP has spurred further investigations into its congestion control mechanism and its effect on the performance of short and long data transfers. We investigate the interaction among short and long TCP flows, and how TCP service can be improved by employing a low-cost service differentiation scheme. Through control-theoretic arguments and extensive simulations, we show the utility, of isolating TCP flows into two classes based on their life-time/size, time/size one class of short flows and another of long flows. With such class-based isolation, short and long TCP flows have separate service queues at routers. This protects each class of flows from the other as they possess different characteristics, such as burstiness of arrivals/departures and congestion/sending window dynamics. We show the benefits of isolation, in terms of better predictability and fairness, over traditional shared queueing systems with both tail-drop and random-early-drop (RED) packet dropping policies.
暂无评论