• Journal of Korea Multimedia Society
• /
• v.9 no.2
• /
• pp.197-207
• /
• 2006

When the latency of a flow in a fair packet scheduler, which is determined by its rate, violates its required delay bound, the scheduler should reduce the latency with even raising the rate being reserved for the flow. The excessively reserved rate win enforce some outgoing link bandwidth be lost. This loss can not be, unfortunately, evaluated by the three metrics of latency, fairness and implementation complexity used in previous works. This paper is aimed to first introduce the metric of bandwidth utilization to investigate the bandwidth loss in a scheduler and then evaluate the timestamp based schedulers in terms of the bandwidth and payload utilizations. The results show that the bandwidth utilization increases with loosing the required delay bound and, in particular, schedulers with the latency property of WFQ have much better payload utilization by up to 50% than that in the SCFQ one.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.323-332
• /
• 2006

Fair packet scheduling algorithms supporting quality-of-services of real-time multimedia applications can be classified into the following two schemes in terms of the reference time used in calculating the timestamp of arriving packet; the Finish-Time (FT) and Start-Time (ST) schemes. The FT scheme, used in most schedulers, that has the property of an inversely rate-proportional latency is suitable to support various delay bounds because it can adjust the latency of a flow with raising the flow's reserved rate. However, the scheme may incur some bandwidth loss due to excess rate reservation. Meanwhile, although the ST scheme does not suffer from the bandwidth loss, it is hard to support multiple delay bounds because of its latency property relying on the number of flows. This paper is devoted to propose a ST scheme based scheduler to effectively support multiple delay bounds and analyze its performance comparing to the FT scheme based scheduler. The comparison results show that the proposed scheduler gives better utilization by up to 50%.

• Journal of Korea Multimedia Society
• /
• v.9 no.8
• /
• pp.1020-1029
• /
• 2006

Realization of high-capacity quality-of-service router needs fair packet schedulers with a lower complexity. Timestamp based fair packet schedulers have the ideal complexity of O(log V), where V is the maximum number of admitted flows, but it has been recently reduced to O(1) using bin concept. However, the latency property was deteriorated and the bandwidth utilization was also declined. In addition, traffic flows requiring strong delay bound may not be admitted. To overcome these problems, this paper proposes a Mini-Bin based Start-Time (MBST) scheduler with variable complexity and evaluates its performance. The MBST scheduler uses the timestamp calculation scheme of start-time based schedulers to enhance the bandwidth utilization and also introduces mini-bin concept to improve the latency, The performance evaluation shows that the proposed scheduler can reduce the complexity of the legacy start-tine based schedulers by $1.8{\sim}5$ times without deteriorating the bandwidth utilization property.

• The KIPS Transactions:PartC
• /
• v.13C no.3 s.106
• /
• pp.331-338
• /
• 2006

Most fair packet schedulers supporting quality-of-services of real-time multimedia applications are based on the finish time design scheme in which the expected transmission finish time of each packet is used as its timestamp. This scheme can adjust the latency of a flow with raising the flow's scheduling rate but it may suffer from severe bandwidth loss due to the coupled rate and delay allocation. This paper first introduces the concept of delay resource, and then proposes a scheduling method to improve the bandwidth utilization in which delay resource being lost due to the coupled allocation is transformed into bandwidth one. The performance evaluation shows that the proposed method gives higher bandwidth utilization by up to 50%.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1536-1546
• /
• 2008

RSVP-capable router supporting guaranteed services on the internet generally uses a packet scheduler based on the Weighted Fair Queuing (WFQ) algorithm to secure required qualities of traffic flows. A RSVP-capable router based on the LOFQ (Latency optimized fair queuing) algorithm had been proposed to improve the performance of the WFQ-based RSVP-router, but it required not only the RESV message to be expanded but also its performance could be evaluated only through simulation. This paper proposed a LOFQ based RSVP-capable router using the conventional RESV message and developed an algorithm to analyze the performance of the LOFQ based RSVP-capable routers. The performance evaluation using the developed algorithm showed that in terms of performance improvement the proposed router is inferior to the one using the expanded RESV message under a small packet size, but on the range of a large packet size both routers provide the same improvement.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9B
• /
• pp.1272-1280
• /
• 2010

WFQ (Weighted Fair Queuing) provides not only fairness among traffic flows in using bandwidth but also guarantees the Quality of Service (QoS) that individual flow requires, which is why it has been applied to the resource reservation protocol (RSVP)-capable router. The RSVP allocates an enough resource to satisfy both the rate and end-to-end delay requirements of the flow in condition of no packet loss, and the WFQ guarantees those QoS requirements with the allocated resource. In a practice, however, most QoS-guaranteed services, specially the Voice of IP, allow a few percent of packet loss, so it is strongly desired that the RSVP and WFQ make the best use of this allowable packet loss. This paper enhances the WFQ to allow packet loss and investigates its performance. The performance evaluation showed that allowing the packet loss of 0.4% can improve the flow admission capability by around 40 percent.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.10
• /
• pp.9-16
• /
• 2003

In this paper, we propose an ATM processor suitable for VoDSL subscriber's equipments. The processor is composed of ATM block, AAL protocol block and ATS scheduler, and provides up to 4 VCC which service data and voice traffics on the ATM network. The proposed ATS scheduler can guarantee QoS of the voice traffic and supports multiple AAL2 packet. The ATM processor is manufactured on the 0.35 micron fabrication line of HYNIX semiconductor and provides the maximum data transfer rate of up to 52 Mbps. We implement the LAD, which is the VoDSL subscriber's equipment. The experimental results on the test bed network shows that the proposed hardware scheme successfully services most of the applications of the VoDSL services.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12A
• /
• pp.1380-1386
• /
• 2004

Future communication networks would consist of wired and wireless access networks where there would be various types of traffic services. To meet the QoS requirements of those various traffic services simultaneously, new QoS control schemes are required. Since they are simple to deploy, cheep to manage, and easy to support subscriber mobility, wireless access networks are considered here. In this paper, a wireless joint buffer management and scheduling (W-JoBS) scheme, which is a modified version of the original JoBS algorithm at error-prone wireless access networks, is proposed. W-JoBS scheme is for providing service fairness among traffic classes with service compensation and channel-state dependent packet scheduling schemes. With computer simulation, this proposed W-JoBS scheme is evaluated and the performance of W-JoBS is compared with that of the original JoBS.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1663-1668
• /
• 2005

There have been numerous researches regarding the QoS guarantee in packet switching networks. IntServs, based on a signaling mechanism and scheduling algorithms, suggesting promising solutions, yet has the crucial complexity problem so that not enough real implementations has been witnessed. Flow aggregation is suggested recently to overcome this issue. In order to aggregated flows fairly so that the latency of the aggregated flows is bound, however, a non-work conserving scheduler is necessary, which is not very popular because of its another inherent complexity. We suggest a non-work conserving scheduler, the Round Robin with Virtual Flow (RRVF), which is a variation of the popular Deficit Round Robin (DRR). We study the latency of the RRVF, and observe that the non-work conserving nature of the RRVF yields a slight disadvantage in terms of the latency, but after the aggregation the latency is greatly reduced, so that e combined latency is reduced. We conclude that the flow aggregation through RRVF can actually reduce the complexity of the bandwidth allocation as well as the overall latency within a network.

• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.253-262
• /
• 2008

Providing Quality-of-Service (QoS) guarantee requires the reservation of resource needed to accommodate the traffic flow of service for which resource reservation protocol (RSVP) was introduced. However, if any RSVP-capable router on the path fails to accommodate the traffic flow due to lack of resource, the flow is not allowed no matter how much surplus resources other routers on the path have. In order to solve this problem, this paper proposes a resource reservation method with available resource migration between RSVP-capable routers in which the routers use the recently developed latency optimized fair queuing scheduler. The results of the simulation applying the proposed method to an evaluation network show that it may yield the gain of up to 165% compared to that in the original one in terms of the number of admitted flows.