Fair Bandwidth Distribution Research Articles

Estimating aggregate resource reservation for dynamic, scalable, and fair distribution of bandwidth

The current best effort approach to Quality of Service in the Internet can no longer satisfy a diverse variety of customer service requirements, and that is why there is a need for alternative strategies. In order to solve this problem a number of service differentiation approaches have been proposed. Unfortunately, these schemes are often inadequate for providing proper service differentiation during periods of congestion. In this paper we introduce a new Bandwidth Distribution mechanism for supporting per-flow Quality of Service guarantees and for dealing with congestion. The Bandwidth Distribution scheme dynamically adjusts resource allocations at the network boundaries based on the network feedback. Within the Bandwidth Distribution framework we introduce a set of techniques for computing per-flow fair share. We evaluate these methods through simulation.

Bandwidth sharing under the assured forwarding Per-Hop behavior

The DiffServ’s Assured Forwarding (af) Per-Hop Behavior (phb) Group defines a differentiated forwarding of packets in four independent classes, each class having three levels of drop precedence. Specific end-to-end services based on thisphb are still being defined. A particular type of service that could assure a given rate to a traffic aggregate has been outlined elsewhere. In such a service, a fair distribution of bandwidth is one of the main concerns.

Improving aggregate flow control in differentiated services networks

The differentiated services (DiffServ) framework provides a simple and scalable methodology for addressing quality of service issues in IP networks. Service differentiation can be achieved through the assured forwarding (AF) per hop behavior packet-handling scheme. One of the more challenging research issues in DiffServ networks is the fair distribution of bandwidth among aggregates sharing the same AF class. Several studies have shown that the number of microflows in aggregates, the round trip time, the mean packet size and TCP/UDP interactions are key factors in the throughput obtained by aggregates using this architecture. In this paper, we examine the behavior of a recent technique suggested to improve fairness in a DiffServ network: the Aggregate Flow Control mechanism. We also propose two alternatives in the control overlay of this scheme and compare them with the original approach. Simulation results indicate that our proposed modifications improve throughput assurance and fairness requirements.

How to increase the efficiency of receiver-driven adaptive mechanisms in a new generation of IP networks

Receiver-driven adaptation allows streaming of multicast multimedia content to different receivers across networks with heterogeneous characteristics, such as different resource availability. However, receivers are only encouraged to adapt if network providers guarantee a fair distribution of bandwidth and also the punishment of receivers that do not adjust their rate in case of congestion. Therefore, we define a receiver-driven adaptive mechanism based on a new fairness protocol that provides the required guarantees for adaptation in heterogeneous networks. We use simulations to evaluate the proposed mechanism and to compare its performance with other receiver-driven mechanisms. Our work contributes to show that the problems of receiver-driven adaptation, such as the induction of losses, can be solved even with simple receiver-driven adaptive mechanisms, when a fair allocation of resources in provided by the network.

IP QoS support in IEEE 802.11b WLANs

This paper addresses the support of IP with Quality of Service (QoS) in IEEE 802.11b WLANs. Both the Distributed Coordination Function (DCF) and Point Coordination Function (PCF) modes of operation are analysed and compared. For DCF, both the original standard and some of the enhancements proposed for IEEE 802.11e are considered. For PCF, two alternative scheduling disciplines are considered: Scheduling based on Estimated Transmission Times (SETT) proposed by the authors and Weighted Deficit Round Robin (WDRR). It is shown that while WDRR is suitable to perform fair bandwidth distribution, SETT also takes into account maximum transmission delay and service priority. Simulation results show that DCF cannot be used to support IP QoS even if 802.11e enhancements are used. On the other hand, PCF performs better with SETT than with WDRR. SETT is able to keep a similar level for network utilisation, while fulfilling the QoS requirements of real-time services such as packet telephony and videoconference, even in the presence of lower priority bursty data. The impact of the high overhead introduced by the IEEE 802.11 PHY and MAC layers was also evaluated, showing that for small packet traffic such as Voice over IP traffic, advanced voice compression is of limited usefulness.

Deficit round-robin scheduling for input-queued switches

We address the problem of fair scheduling of packets in Internet routers with input-queued switches. The goal is to ensure that packets of different flows leave a router in proportion to their reservations under heavy traffic. First, we examine the problem when fair queuing is applied only at output link of a router, and verify that this approach is ineffective. Second, we propose a flow-based iterative deficit-round-robin (iDRR) fair scheduling algorithm for the crossbar switch that supports fair bandwidth distribution among flows, and achieves asymptotically 100% throughput under uniform traffic. Since the flow-based algorithm is hard to implement in hardware, we finally propose a port-based version of iDRR (called iPDRR) and describe its hardware implementation.

Fair scheduling for input buffered switches

Input buffered switch architecture has become attractive for implementing high performance switches for workstation clusters. It is challenging to provide a scheduling technique that is both highly efficient and fair in resource allocation. In this paper, we first introduce an iterative Fair Scheduling (iFS) scheme for input buffered switches that supports fair bandwidth distribution among the flows and achieves asymptotically 100% throughput. We then apply the idea of fair scheduling to switches with multicasting capability and propose an mFS scheme which allocates bandwidth to various flows according to their reservations. We show that mFS produces throughput comparable to the existing schemes while distributing the bandwidth as per the given reservations. Extensive simulation results are presented to validate the effectiveness of our proposed schemes.

Fair scheduling in Internet routers

Input buffered switch architecture has become attractive for implementing high performance routers and expanding use of the Internet sees an increasing need for quality of service. It is challenging to provide a scheduling technique that is both highly efficient and fair in resource allocation. In this paper, we first introduce an iterative fair scheduling (IFS) scheme for input buffered switches that supports fair bandwidth distribution among the flows and achieves asymptotically 100 percent throughput. The IFS is evaluated both under synthetic workload and with Web traces from the Internet. Compared to the commonly used synthetic input, our simulation results reveal significant difference in performance when the real network traffic is employed. We then consider fair scheduling under various buffer management mechanisms and analyze their impact on the fairness in bandwidth allocation. Our studies indicate that early packet discard in anticipation of congestion is necessary and per-flow based buffering is effective for protecting benign users from being adversely affected by misbehaving traffic. Buffer allocation according to bandwidth reservation is especially helpful when the input traffic is highly bursty.

Modeling and Simulation of an ABR Flow Control Algorithm Using a Virtual Source/Virtual Destination Switch

The Available Bit Rate (ABR) service class of Asynchronous Transfer Mode networks uses a feedback control mechanism to adapt to varying link capacities. The Virtual Source/Virtual Destination (VS/VD) technique offers the possibility to segment the otherwise end-to-end ABR control loop into separate loops. The improved feedback delay and the control of ABR traffic inside closed segments provide a better performance for ABR connections. This article will present the use of classical linear control theory to model and develop an ABR VS/VD flow control algorithm. Discrete event simulations are used to analyze the behavior of the algorithm with respect to transient behavior and correctness of the control model. Linear control theory offers the means to derive correct choices of parameters and to assess performance issues, like stability of the system, during the design phase. The performance goals are a high link utilization, fair bandwidth distribution, and robust operation in various environments, which are verified by discrete event simulations. The major contribution of this work is the use of analytic methods (linear control theory) to model and design an ABR flow control algorithm tailored for the special layout of a VS/VD switch, and the use of simulation techniques to verify the result.

Fairness performance of dynamic weights in the ATM ABR service

Traditional schemes fail to achieve fair distribution of bandwidth among available bit rate connections. In this paper, a new scheme called Active Fairness is proposed which substantially improves fairness in bandwidth allocation. Contrary to one set of weights used in traditional schemes, Active Fairness maintains two sets of weights at each link. The first set is the same as that used in traditional schemes, which represents the relative bandwidth allocation desired out of the available bandwidth at the link. If these weights are used directly in bandwidth allocation, the actual proportion of the bandwidth utilized by an individual connection can deviate substantially due to factors such as the number of links traversed by the connection, its round-trip propagation delay, etc. In order to take into account these factors, another set of weights (dynamic in nature) is derived at each link, which is used in bandwidth allocation. Active Fairness achieves significant fairness improvement which is demonstrated through simulations involving bursty background traffic, network bottlenecks, dynamic VC mixes and different fairness definitions.

A centralized TDMA-based scheme for fair bandwidth allocation in wireless IP networks

A unified time-division multiple access (TDMA) based centralized wireless access scheme is proposed for performing the statistical multiplexing of bursty data sources in a wireless packet data network. This scheme combines dynamic bandwidth allocation with admission control and packet conditioning (at the mobile stations) to provide fair bandwidth distribution among bursty data flows with different profile rates (or subscription levels) in an error-prone environment. The dynamic bandwidth allocation policy is credit-based and both the burst-level and the packet-level bandwidth allocations are considered. The performance of the scheme is evaluated using computer simulations for different total subscription levels, for different compositions of flows with different profile rates, and for different channel quality with different channel-error correlation patterns. The simulation results show that the throughput variability among flows with the same level of subscription is considerably small except for long range dependent flows with very high traffic burstiness. The relative throughput fairness among flows with different profile rates can also be achieved. The post facto loss and delay values (i.e., observed average packet delay and average packet loss values) for the flows depend on the corresponding delay tolerance limits of the data bursts, TDMA frame-length, and the wireless link utilization level. The energy efficiency of the wireless access scheme is evaluated in terms of the average transmitter usage time and the average receiver usage time in the mobile stations for both the burst-level and the packet-level bandwidth allocation. The proposed scheme can be used in an adaptive quality-of-service (QoS) framework for dynamically adjusting the QoS for flows in order to accommodate wireless channel errors and user mobility.