A separation principle between scheduling and admission control for broadband switching

Hyman, Jay; Lazar, Aurel A.; Pacifici, G.

doi:10.1109/49.221207

Cited by 80 publications

(34 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These standards specify the different service classes and the service guarantees available to network applications. The realization of these schemes requires advances in traffic specification [39,43], resource reservation [44], resource mapping [45][46][47] and admission control [48,49], scheduling algorithms 4 [39,[51][52][53][54] and queue management [55], along with various other control and management mechanisms such as traffic policing. Pricing design for multi-service networks has also witnessed a flurry of research activity [56][57][58][59][60][61][62][63][64][65].…”

Section: Transmission-based Qosmentioning

confidence: 99%

Distributed network storage service with quality-of-service guarantees

Chuang

Sirbu

2000

Journal of Network and Computer Applications

View full text Add to dashboard Cite

This paper envisions a distributed network storage service with Quality-ofService (QoS) guarantees, and describes its architecture and key mechanisms. When fully realized, this service architecture would be able to support, in one integrated framework, network storage services ranging from best-effort caching to replication with performance guarantees. Content owners could, through the use of standardized protocols, reserve network storage resources to satisfy their application-specific performance requirements. They would be able to specify either the number and/or placement of the replicas, or higher-level performance goals based on access latency, bandwidth usage or data availability. The network storage provider would then optimally allocate storage resources to meet the service commitments, using leftover capacity for best-effort caching. Content consumers would then retrieve the nearest copy of the data object, be it from a replica, cache, or the original source, in a completely transparent manner. Furthermore, a distributed network storage infrastructure should be integrated with the existing transmission-based QoS framework so that applications can select the optimal combination of storage and transmission resources to satisfy their performance requirements.This work identifies and discusses key research areas and problems that need to be tackled, including those in service specification, resource mapping, admission control, resource reservation and real-time storage management. The paper establishes a QoS framework upon which community discussion on this vision can proceed.

show abstract

Section: Transmission-based Qosmentioning

confidence: 99%

Distributed network storage service with quality-of-service guarantees

Chuang

Sirbu

2000

Journal of Network and Computer Applications

View full text Add to dashboard Cite

show abstract

“…The necessary Schedulable Region and Admission Control Policy objects are downloaded from a management station. The admission control policy used is Complete Sharing [HYM93a].…”

Section: The Xunet Signaling and Admission Control Architecturementioning

confidence: 99%

“…We used peak rate allocation, and according to this scheme, the SR can accommodate a maximum of 7 video calls or 703 voice calls. The admission control policy used was complete sharing [HYM93a]. Figure 13 shows the measurements obtained by gradually increasing the call generation rate.…”

mentioning

confidence: 99%

An architecture for managing virtual circuit and virtual path services in ATM networks

Anerousis

Lazar

1996

J Netw Syst Manage

View full text Add to dashboard Cite

ATM networks rely on the Virtual Circuit (VC) and Virtual Path (VP) concept to provide unicast connection-oriented services with Quality of Service guarantees. This paper presents a model for managing the configuration and performance of the VC and VP services in these networks. The model consists of a connection management architecture that provides the services and is instrumented for network management purposes, and a network management architecture that uses the OSI management model to provide access to the appropriate service monitoring and control functions. The network management architecture proposes complete managed object definitions that achieve a variety of monitoring and control objectives: service configuration, service performance at the call and cell level, and service control. The latter includes the capability to establish VPs and control their allocated networking capacity and also control parameters of the signaling system that affect the performance of the VC service. The architecture was implemented in its entirety on the Xunet ATM testbed, and several experiments were conducted to illustrate the trade-off between the throughput of the VC service and the allocation of capacity to VPs. The experiments further demonstrated that the signaling system can create throughput bottlenecks in the absence of VPs in the network, and therefore, the network operator can increase performance by controlling the VP distribution.Keywords: ATM, Service Management, Virtual Circuit, Virtual Path, Xunet. IntroductionThe significant progress achieved in the past few years in the development of signaling standards for ATM networks has generated a strong interest for architectures that enable the introduction and management of broadband services. This paper presents a model for managing the Virtual Circuit (VC) and Virtual Path (VP) connection services in ATM networks with Quality of Service Guarantees. These services can be regarded as the core broadband services, in the sense that other more complex services such as video-on-demand, video conferencing, virtual networks, etc., can be built on top of them. We give special attention to the VP service for the following reasons: VPs can be provided as an end-to-end connection service to the users or can be employed by the network operator to opti- mize the call level performance of the ATM network. In this case, they can be used to establish connections for the VC service at a reduced signaling processing cost. This implies that the VP configuration (especially with respect to resource allocation) has a direct impact on the VC service performance. Therefore, the observed performance of the VC service should influence the decisions regarding the distribution of networking capacity to VPs (the VP distribution), and consequently, the VC and VP management architectures should be integrated.In addition to the architecture for managing the VC and VP services, there is a need to develop an understanding of the architecture that provides these services, i.e., the conn...

show abstract

“…The fairness problem can be alleviated by using different schemes, e.g., virtual spacing [2], round robin/priority scheduling [3], weighted round-robin scheduling [4], dynamic time-slice [5], asynchronous time sharing [6], and per virtual circuit buffer limit [7]. Although these schemes make possible to protect the well-behaved connections from the misbehaving ones, the complexity of implementation may restrict their applicability, see e.g.…”

Section: Introductionmentioning

confidence: 99%