Core Routers Research Articles

RIO-DC Buffer Design for Core Routers in DiffServ Assured Services

In this paper, a parameter optimization method of RIO-DC (RED (Random Early Detection) with In and Out-De-Coupled Queues) scheme for Assured Service (AS) in Differentiated Services (DiffServ) is proposed. In order to optimize QoS (Quality of Service) performance of the RIO-DC policy for AS in terms of maximum tolerable latency, link utilization, fairness, etc., we should design router nodes with proper RIO-DC operating parameter values. Therefore, we propose a RIO-DC configuration method and the admission control criterion, considering the allocated bandwidth to each subclass and the corresponding buffer size, to increase throughput for In-profile traffic and link utilization. Simulation results show that RIO-DC with the proposed parameter values guarantees QoS performance comparable with the RIO scheme and it improves fairness between AS flows remarkably.

Inferring Unseen Components of the Internet Core

Despite many efforts over the past decade, the ability to generate topological maps of the Internet at the router-level accurately and in a timely fashion remains elusive. Mapping campaigns commonly involve {t traceroute}-like probing that are usually non-adaptive and incomplete, thus revealing only a portion of the underlying topology. In this paper we demonstrate that standard probing methods yield datasets that implicitly contain information about much more than just the directly observed links and routers. Each probe yields information that places constraints on the underlying topology, and by integrating a large number of such constraints it is possible to accurately infer the existence of unseen components of the Internet (i.e., links and routers not directly revealed by the probing). Moreover, we show that this information can be used to adaptively re-focus the probing in order to more quickly discover the topology. These findings suggest radically new and more efficient approaches to Internet mapping. Our work focuses on the discovery of the core of the Internet. We define "Internet core" as the set of routers that is roughly bounded by ingress/egress routers from stub autonomous systems. We describe a novel data analysis methodology designed to accurately infer (i) the number of unseen core routers, (ii) the unseen hop-count distances between observed routers, and (iii) unseen links between observed routers. We use a large experimental dataset to validate the proposed methods. For our data set, we show that our methods can predict the number of unseen routers to within a 13% error level, estimate 60% of the unseen distances between observed routers to within a one-hop error, and robustly detect over 35% of the unseen links between observed routers. Furthermore, we use the information extracted by our inference methodology to drive an adaptive active-probing scheme. The adaptive probing method allows us to generate maps on our data set using 50% fewer probes than standard non-adaptive approaches.

An Adaptive Drop Marker for Edge Routers in DiffServ Networks

In this paper, we propose an Adaptive Regulating Drop (ARD) marker, as a novel dropping strategy at the ingressive edge router, to improve TCP fairness in assured services (ASs) without a decrease in the link utilization. To drop packets pertinently, the ARD marker adaptively changes a Temporary Permitted Rate (TPR) for aggregate TCP flows. The TPR is set larger than the current input IN packet rate of aggregate TCP flows while inversely proportional to the measured input OUT packet rate. To reduce the excessive use of greedy TCP flows by notifying droppings of their IN packets constantly to them without a decrease in the link utilization, the ARD marker performs random early fair remarking of their excessive IN packets to OUT packets at the aggregate flow level according to the TPR. In addition, an aggregate dropper is combined to drop some excessive IN packets fairly and constantly according to the TPR. Thus, the throughput of a TCP flow no more depends on only the sporadic and unfair OUT packet droppings at the RIO buffer in the core router. Then, the ARD marker regulates the packet transmission rate of each TCP flow to the contract rate by increasing TCP fairness, without a decrease in the link utilization.

Anomalous Loss Performance for Mixed Real-Time and TCP Traffic in Routers With Very Small Buffers

In the past few years there has been vigorous debate regarding the size of buffers required at core Internet routers. Recent arguments supported by theory and experimentation show that under certain conditions, core router buffer sizes of a few tens of packets suffice for realizing acceptable end-to-end TCP throughputs. This is a significant step toward the realization of optical packet switched (OPS) networks, which are inherently limited in their ability to buffer optical signals. However, prior studies have largely ignored the presence of real-time traffic, which is increasing in importance as a source of revenue for Internet service providers. In this paper, we study the interaction that happens between real-time (open-loop) and TCP (closed-loop) traffic when they multiplex at buffers of very small size (few tens of packets) and make a significant discovery - namely that in a specific range of buffer size, real-time traffic losses increase as buffer size becomes larger. Our contributions pertaining to this anomalous behavior are threefold. First, we exhibit this anomalous loss performance for real-time traffic via extensive simulations using synthetic traffic and real video traces. Second, we develop quantitative models that reveal the dynamics of buffer sharing between real-time and TCP traffic that lead to this behavior. Third, we show how various factors such as the nature of real-time traffic, mixture of long-lived and short-lived TCP flows, and packet sizes impact the severity of the anomaly. Our study is the first to consider interactions between real-time and TCP traffic in very small (potentially all-optical) buffers and informs router manufacturers and network operators of the factors to consider when dimensioning such small buffer sizes for desired performance balance between real-time and TCP traffic.

Impact of File Arrivals and Departures on Buffer Sizing in Core Routers

Traditionally, it had been assumed that the efficiency requirements of TCP dictate that the buffer size at the router must be of the order of the bandwidth-delay (C × RTT) product. Recently, this assumption was questioned in a number of papers, and the rule was shown to be conservative for certain traffic models. In particular, by appealing to statistical multiplexing, it was shown that on a router with N long-lived connections, buffers of size O([(C × RTT)/(√N)]) or even O(1) are sufficient. In this paper, we reexamine the buffer-size requirements of core routers when flows arrive and depart. Our conclusion is as follows: If the core-to-access-speed ratio is large, then O(1) buffers are sufficient at the core routers; otherwise, larger buffer sizes do improve the flow-level performance of the users. From a modeling point of view, our analysis offers two new insights. First, it may not be appropriate to derive buffer-sizing rules by studying a network with a fixed number of users. In fact, depending upon the core-to-access-speed ratio, the buffer size itself may affect the number of flows in the system, so these two parameters (buffer size and number of flows in the system) should not be treated as independent quantities. Second, in the regime where the core-to-access-speed ratio is large, we note that the O(1) buffer sizes are sufficient for good performance and that no loss of utilization results, as previously believed.

A novel burst-outputted model in an OBS core router

In this paper, the performances of a novel burst-outputted model which based on differentiated probability in an optical burst switching (OBS) core router have been proposed and analyzed. Different from the same probability to select output-port model in previous works, proposed model gives a burst-outputted process with different probabilities, which based on the fact that, output-ports may lead to variable distance with the same destination. The burst blocking probability, the system-passed rate, the average output-port occupied value and the efficiency have been given and discussed.

Comparative Evaluation of Spoofing Defenses

IP spoofing exacerbates many security threats, and reducing it would greatly enhance Internet security. Seven defenses that filter spoofed traffic have been proposed to date; three are designed for end-network deployment, while four assume some collaboration with core routers for packet marking or filtering. Because each defense has been evaluated in a unique setting, the following important questions remain unanswered: 1) Can end networks effectively protect themselves or is core support necessary? 2) Which defense performs best assuming sparse deployment? 3) How to select core participants to achieve best protection with fewest deployment points? This paper answers the above questions by: 1) formalizing the problem of spoofed traffic filtering and defining novel effectiveness measures, 2) observing each defense as selfish (it helps its participants) or altruistic (it helps everyone) and differentiating their performance goals, 3) defining optimal core deployment points for defenses that need core support, and 4) evaluating all defenses in a common and realistic setting. Our results offer a valuable insight into advantages and limitations of the proposed defenses, and uncover the relationship between any spoofing defense's performance and the Internet's topology.

Evaluation of Power Consumption in Low Spatial Complexity Optical Switching Fabrics

In this paper, we propose an analytical model to evaluate the power consumption in the switching fabric of a bufferless shared-per-wavelength (SPW) optical packet switch architecture in which one bank of wavelength converters (WC) is dedicated to each wavelength. We assume that both optical gates and WCs are realized in semiconductor optical amplifier technology. In our evaluation, we account for the power consumption of the current drivers needed to both controlling the used active devices and supplying the thermoelectric coolers. SPW allows for a complexity reduction of the spatial switching matrix that leads to reduced power consumption with respect to other switching architectures. Results show the effectiveness in terms of consumed power of the considered architecture with respect to the shared-per-node reference architecture, where a fully sharing strategy of WCs is adopted. The main results show that SPW allows us to reduce the power consumption in the order of 26% for offered traffic equal to 0.6. The obtained results also show how the fabric switching of the SPW optical packet switch consumes much less power per gigabits per second carried than the one of a typical commercial core router.

Green multicast grooming based on optical bypass technology

With the network traffic increasing, the energy consumption of network equipments is growing greatly. Under the background of serious greenhouse effect, the excessive energy consumption has become a major barrier of developing the future information society. For this reason, the issue of saving energy followed by the grooming and optical bypass technology has become particularly important. In this paper, in order to perform the energy-saving for multicast demands, we present the multicast grooming policies and also develop a new auxiliary graph to support the multicast routing in green optical network. Based on the proposed auxiliary graph, a novel Multicast Green Grooming (MGG) approach by using the energy-efficient optical bypass technology and the effective grooming policy combination is proposed to reduce the occupied energy-consuming equipments that mainly include the core router ports, optical transceivers and amplifiers. Simulation results show that, compared to the traditional approach, MGG not only can obtain the lower blocking probability but also is able to save significant energy.

HTTP Traffic Model for Web2.0 and Future WebX.0

This article presents a method of estimation for HTTP traffic quality service parameters mean delay and lost packets percentage. This method, based on statistic measurements, includes simulation and analytical modeling. Statistical HTTP traffic models presented earlier take into account typical features of WEB2.0 Internet traffic, which were used for the simulation model. Developed universal simulation models make it possible to research service quality parameters under setting network conditions over a wide range considering Internet development. The presented analytical method based on batch packet arrival model allows an accuracy estimation of mean HTTP-packets delay in Core Router by simple calculations. Objective results of HTTP traffic quality service parameters can be used in QoS standard development for WEB traffic and model QoE standard development.

Active Queue Management within Large-Scale Wired Networks

Signal transmission control protocol sources with the objective of managing queue utilization and delay is actually a feedback control problem in active queue management (AQM) core routers. This paper extends AQM control design for single network systems to large-scale wired network systems with time delays at each communication channel. A system model consisted of several local networks is first constructed. The stability condition guaranteeing overall stability is subsequently derived using Lyapunov stability theory. The results developed have been successfully verified on a network simulator.

Diffserv AQM algorithm for edge and core routers

The existing active queue management (AQM) algo- rithm acts on subscribers and edge routers only, it does not sup- port differentiate-serve (Diffserv) quality of service (QoS), while the existing diffserv QoS has not considered the link capacities between edge routers and connected core routers. When a core router in a two layers' network experiences congestion, the con- nected edge routers have no ability to adjust their access data rates. Thus, it is difficult to achieve the congestion control for the large scale network with many edge routers and core routers. To solve these problems, two difffserve AQM algorithms are proposed for the congestion control of multilayer network. One diffserv AQM algorithm implements fair link capacities of edge routers, and the other one implements unequal link capacities of edge routers, but it requires the core routers to have multi-queues buffers and Diffserv AQM to support. The proposed algorithms achieve the network congestion control by operating AQM parameters on the conditions of proposed three theorems for core and edge routers. The dynamic simulation results demonstrate the proposed control algorithms for core and edge routers to be valid.

Performance evaluation of a new traffic engineering algorithm in NGN based on end-point admission control

In this paper, a new end-point admission control algorithm is proposed which helps to manage the network traffic more efficiently in NGN, where multiple classes of service are required by the applications. In this algorithm, users are allowed to temporarily use lower service classes in the routers along the connection path, whenever the requested service class is not available. The above procedure is applied provided that the end-to-end service quality level is preserved unless a lower service quality is acceptable by the application. This degradation may be temporary until the required quality level becomes available. In this way more calls can be admitted and the throughput of the links is increased. Additionally, using an appropriate rule in core routers can mitigate bandwidth stealing problem in the network while achieving nearly good utilization.

A Delivery System for Streaming Video Over DiffServ Networks

In this letter, we develop a general delivery system for streaming using various coding standards over DiffServ (DS) networks. In the delivery system, the coder at the application layer pre-marks the compressed data according to their importance in terms of the current configuration and characteristics of the coder. Then the system maps these pre-marks to a fixed number of source marks at the real-time transport protocol layer. In terms of the current network congestion state, the edge router of a DS network uses the improved two rate three color maker to map these source marks to differentiated services code points. At last, the core routers transmit these packets according to the per-hop forwarding behaviors. Experimental results show that this system can greatly improve the end-to-end delivery quality of a streaming application.

Architectures, Components, and Subsystems for Future Optical Packet Switches

Rapidly increasing network traffic is posing a challenge to the construction of future routers. While high-capacity transport has kept pace with rising traffic demands through the use of dense wavelength-division multiplexing, the scaling of core routers is slowed by power density limits and complexity and interconnectivity issues. Optical switching has the potential to overcome these scaling restrictions, and as a result, has generated great scientific and commercial interest. In this paper, we present an overview of some optical packet-switching architectures and describe components and subsystems that are required to enable this technology.

Leveraging parallelism for multi-dimensional packetclassification on software routers

We present a software-based solution to the multi-dimensional packet classification problem which can operate at high line speeds, e.g., in excess of 10 Gbps, using high-end multi-core desktop platforms available today. Our solution, called Storm, leverages a common notion that a subset of rules are likely to be popular over short durations of time. By identifying a suitable set of popular rules one can significantly speed up existing software-based classification algorithms. A key aspect of our design is in partitioning processor resources into various relevant tasks, such as continuously computing the popular rules based on a sampled subset of traffic, fast classification for traffic that matches popular rules, dealing with packets that do not match the most popular rules, and traffic sampling. Our results show that by using a single 8-core Xeon processor desktop platform, it is possible to sustain classification rates of more than 15 Gbps for representative rule sets of size in excess of 5-dimensional 9000 rules, with no packet losses. This performance is significantly superior to a 8-way implementation of a state-of-the-art packet classification software system running on the same 8-core machine. Therefore, we believe that our design of packet classification functions can be a useful classification building block for RouteBricks-style designs, where a core router might be constructed as a mesh of regular desktop machines.

Evaluation of a new method for measuring the internet degree distribution: Simulation results

Many contributions rely on the degree distribution of the Internet topology. However, current knowledge of this property is based on biased and erroneous measurements and is subject to much debate. Recently, in [1], a new approach, referred to as the Neighborhood Flooding method, was proposed to avoid issues raised by classical measurements. It aims at measuring the neighborhood of Internet core routers by sending traceroute probes from many monitors distributed in the Internet towards a given target router. In this paper, we investigate the accuracy of this method with simulations. Our results show that Neighborhood Flooding is free from the bias highlighted in the classical approach and is able to observe properly the exact degree of a vast majority of nodes in the core of the network. We show how the quality of the estimation depends on the number of monitors used and we carefully examine the influence of parameters of the simulations on our results. We also point out some limitations of the Neighborhood Flooding method and discuss their impact on the observed distribution.

Dimensioning Drop-tail and AQM (RED) buffers at access networks for optimal performance with bulk data TCP traffic

Dimensioning buffers is still an area open to research efforts and discussions and much study work has been conducted on this topic recently. Most of this work is focused on sizing buffers in core routers in which a huge number of flows compete. Different, sometimes contradictory theories and buffer dimensioning formulae are put forward, which take into account statistical properties when aggregating many TCP flows. In our study we also work under the widely accepted assumption that persistent TCP flows account for most of the buffer demand and short-lived (e.g. web-traffic) TCP or non-elastic (e.g. streaming) flows just add a little bit more to the buffer requirement. In the research dedicated to core routers, these are assumed as bottlenecks, which, given the high-bandwidth backbone networks today, is not very frequent. Very often, however, the narrow bandwidth last-mile network is the bottleneck for a TCP connection. Therefore, we explore buffers in the access network equipment (e.g. in a DSLAM access module), in which a few long-lived TCP-controlled connections compete, synchronization between flows is a frequent phenomenon, and we elaborate on the impact of buffer configuration on the access (down-) link performance. In this paper, a formula is presented for dimensioning access network (bottleneck) buffers for no loss on the flows competing through them, given the flows’ parameters are known (number of flows, propagation delays, and advertized windows). The formula is validated against simulations. Further, we explore the sensitivity of this buffer dimensioning function to its parameters. As we show, in order to avoid buffer-incurred losses, the required buffer becomes easily very large, of the order of hundreds of packet units only for a few flows. This is not feasible for equipment implementation, nor is desirable because of other side-effects, e.g. like largely augmented delay. Therefore, we also study the impact of shorter buffers than necessary on the performance criteria: link utilization, fairness between flows. We also derive a formula for calculating the buffer fluctuation period, in particular Drop-tail buffer synchronization conditions. We show that Drop-tail buffers very often fail to meet the performance criteria. Further on, we present a methodology for optimally dimensioning RED-managed buffers. This is a compilation of other acknowledged works in the area, passed through the prism of our own research and we demonstrate that such buffers, if properly configured and working in a stable regime, can outperform Drop-tail buffers.

Performance analysis of an improved burst-outputted model for an OBS core router

Differentiated probability outputted scheme (DPOS) is an improved burst-outputted paradigm in optical burst switching (OBS) core routers. In this paper, the blocking performance for multi-priority traffic in a DPOS applied OBS core router with limited buffers has been analyzed and discussed firstly. Several simulation results indicted that DPOS had a better performance in blocking than the outputted model presented in the previous work had. Besides, our proposed scheduling mechanism can supported the quality-of-service (QoS) efficiently for OBS networks.

A novel technique for resolving burst contention in OBS networks

In this article, in order to resolve burst contention (burst dropping), a new scheme for an optical burst switching (OBS) network has been proposed which is based on the integration of wavelength selection and burst assignment. The proposed scheme provides proportional differentiated services in bufferless OBS networks by dynamically assigning more and longer periods of wavelengths to higher priority classes. In addition, burst head packets (BHPs) are buffered electrically so that fiber delay lines are unnecessary at core nodes. As a result, BHP of a lower priority class is buffered at the core router when it cannot find an available wavelength. It has an opportunity to reschedule its burst to the wavelengths that have been assigned to higher priority classes but have not yet been reserved. The proposed integrated scheme not only provides proportional differentiated services but also achieves lower average dropping probability without any preemption or segmentation mechanisms. Compared with existing approaches, the proposed integrated scheme does not need to generate any special packets and needs to maintain only a few parameters at core nodes.The proposed scheme has several attractive features such as fast, simple implementation and improved burst dropping performance. Extensive simulation results have been used to demonstrate the effectiveness of the proposed scheme in comparison to traditional schemes.