Integration of unicast and multicast scheduling in input-queued packet switches

Zhu, Weiying; Song, Min

doi:10.1016/j.comnet.2005.06.004

Cited by 18 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we consider several different traffic conditions and compare the proposed algorithm with ESLIP [13] and fSCIA [15] to evaluate the performance for a 16 × 16 switch. All simulations have been fixed at 100 000 time slots and statistics are gathered when half of the total simulation length has elapsed.…”

Section: Performance Evaluation and Analysismentioning

confidence: 99%

“…However, the HoL blocking problem of multicast traffic limits the throughput achievable by switches. Other algorithms [15] used VOQ for unicast traffic and a small number, k (1 , k ≪ 2 N 2 1), of queues for multicast traffic to alleviate the multicast HoL blocking; this multicast queuing architecture is called k multicast virtual output queuing (k-MC-VOQ). Algorithm in [16] used VOQ queuing structure for unicast and multicast traffic separately to deal with the HoL blocking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integration of unicast and multicast scheduling in a two-stage switch architecture with low scheduling overhead

et al. 2012

View full text Add to dashboard Cite

This study deals with the scalability problems induced by high complexity of integrated scheduling for high-speed switches, and presents a simple two-stage integrated scheduling algorithm that supports both unicast and multicast traffic simultaneously. The first stage of the switching fabric performs switching for unicast traffic and load-balancing for multicast traffic, whereas the second stage performs switching for multicast traffic with a new multicast scheduling algorithm to reduce the multicast head-of-line (HoL) blocking problem. Considering the tradeoff balancing complexity and performance, the proposed integrated algorithm performs without iteration, and reduces the scheduling overhead from traditional O(kN) to O(N ) with a two-phase (request-grant) scheduling for unicast and multicast traffic at each stage. Simulation results show that the proposed integrated algorithm exhibits a good performance in terms of throughput and average delay, at different traffic compositions under various traffic patterns, especially with non-uniform traffic.

show abstract

Section: Performance Evaluation and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Integration of unicast and multicast scheduling in a two-stage switch architecture with low scheduling overhead

et al. 2012

View full text Add to dashboard Cite

show abstract

“…To minimize the HOL blocking, multiple dedicated multicast queues have been utilized in [3] and [14]. In [14], each input port has a set of multicast queues.…”

Section: Related Workmentioning

confidence: 99%

“…In [14], each input port has a set of multicast queues. When a multicast packet arrives, it culls one of the multicast queues to join according to its load balancing policy.…”

Section: Related Workmentioning

confidence: 99%

Multicast Due Date Round-Robin Scheduling Algorithm for Input-Queued Switches

Navaz¹,

Balasubramanian²

2016

IJCNIS

View full text Add to dashboard Cite

Abstract-In recent years, the Internet has incremented the several incipient applications that rely on multicast transmission. This paper discusses the challenges of scheduling algorithms for multicast in high-speed switches that reduces the overhead of adaptation by selecting a HOL (Head of Line Cell) using Round Robin pointer. The objective of this paper is to design a scheduling algorithm called MDDR (Multicast Due Date Round-Robin) scheduling to achieve maximum throughput and low delay that has two phases request and grant. In request phase, MDDR assigns a Due Date (Request Time Slot) for HOL cells of each queue in the input port. Round Robin Pointer is utilized in the grant phase to select a request if HOL occurs. MDDR achieves more preponderant performance than MDRR (Multicast Dual Round-Robin), since the request shall be made when the Due Date is reached. MDDR mainly minimizes many requests made for output ports and time complexity. The simulation results show that the proposed algorithm has good switching performance in throughput and average time delay under Bernoulli and bursty traffic conditions.

show abstract

“…The integration efforts were mainly focused on designing appropriate scheduling and queuing algorithms for input queued [2], combined input and output queued [3], and combined input and crossbar queued switches [4]. The main objective of these algorithms is to maximize the utilization of the switch, but some of them also aim at providing fair bandwidth sharing between unicast and multicast flows, or to achieve a certain trade-off between these two objectives.…”

Section: Introductionmentioning

confidence: 99%

Multicast scheduling with resource fairness constraints

Vukadinović

Karlsson

2007

Wireless Netw

View full text Add to dashboard Cite

Integration of multicast and unicast data in future radio access networks will be necessary in order to improve the resource efficiency and provide new services. Such integration requires new and efficient resource sharing mechanisms. These mechanisms need to be optimized to provide the best possible trade-off between resource efficiency and fairness. In this article, we consider a case where streaming multicast users are multiplexed together with elastic unicast users on a common time-slotted channel. We derive a system model to study the performance of various resource allocations strategies under proportional and resource fairness constraints. Fairness is directly defined in terms of the users' utilities rather than of the throughputs they are assigned to. We also describe an extension of the well-known unicast proportional fair scheduler to the multicast scenario. Through extensive simulations we demonstrate the performance of this scheduler for various traffic loads and multicast group sizes.

show abstract

Integration of unicast and multicast scheduling in input-queued packet switches

Cited by 18 publications

References 16 publications

Integration of unicast and multicast scheduling in a two-stage switch architecture with low scheduling overhead

Integration of unicast and multicast scheduling in a two-stage switch architecture with low scheduling overhead

Multicast Due Date Round-Robin Scheduling Algorithm for Input-Queued Switches

Multicast scheduling with resource fairness constraints

Contact Info

Product

Resources

About